Skip to content

chore(deps): update all dependencies to v12#32

Open
gw0-bot wants to merge 1 commit into
mainfrom
renovate/major-all-deps
Open

chore(deps): update all dependencies to v12#32
gw0-bot wants to merge 1 commit into
mainfrom
renovate/major-all-deps

Conversation

@gw0-bot
Copy link
Copy Markdown
Collaborator

@gw0-bot gw0-bot commented May 23, 2026 •
edited
Loading

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Update Change
sickn33/antigravity-awesome-skills major 10.10.0 → 12.2.1

Release Notes

sickn33/antigravity-awesome-skills (sickn33/antigravity-awesome-skills)

v12.2.1: "Security Scan Follow-up"

Compare Source

[12.2.1] - 2026-06-07 - "Security Scan Follow-up"

Patch release for the June 7 security scan remediation after 12.2.0.

Security

  • Hardened user-thoughts runtime file handling against symlink traversal and realpath escapes inside .ustht/.
  • Fixed tar archive validation to prefer PAX path / linkpath headers before GNU long-name headers.
  • Replaced risky documentation examples for unquoted Git branches, placeholder git add, predictable /tmp installer paths, token-printing Vercel commands, and unsafe JSON-LD injection.
  • Removed public Google and Bing site-verification tokens from the web app.
  • Raised risk labels and plugin metadata for external-code and remote-execution skills, including runapi-cli, open-dynamic-workflows, and polis-protocol.

Improvements

  • Marked 2slides-ppt-generator plugin setup as manual with declared Python requirements.
  • Fixed broken plugin bundle links and the mobile plugin skill list.
  • Regenerated plugin compatibility reports, skill indexes, web assets, and plugin mirrors after the remediation.

v12.2.0: "Education, Media, Workflow, and Creative Skill Intake"

Compare Source

[12.2.0] - 2026-06-07 - "Education, Media, Workflow, and Creative Skill Intake"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release packages the June 7 maintainer batch: accepted community PRs for education, media processing, workflow orchestration, media-generation APIs, and article illustration workflows. The catalog is synced to 1,525+ skills, plugin mirrors are refreshed, and the hosted web-app SEO metadata now matches the current catalog count.

New Skills

  • cv-generator - ATS-ready CV and resume generation guidance for FlowCV, Canva, and structured career-document workflows.
  • open-dynamic-workflows - dynamic multi-agent workflow orchestration guidance for planning, parallel execution, and adversarial verification.
  • video-content-extractor - FFmpeg and Tesseract OCR workflows for extracting timestamped screen text and structured Markdown reports from MP4 videos.
  • runapi-cli - official RunAPI CLI guidance for generating AI images, videos, music, audio, and related model API jobs.
  • article-illustrations - Grav-style hand-drawn article illustration workflow with whiteboard sketches, sparse annotations, visual metaphors, and QA checks.

Improvements

  • Refined examprep-ai release metadata and education category support as part of the accepted education skill update.
  • Added README source credits and structured provenance metadata for newly imported external/community skills.
  • Synced generated registry, catalog, compatibility reports, plugin mirrors, docs, sitemap, and web assets for the 1,525-skill catalog.
  • Updated web-app home metadata, llms.txt, social preview copy, prerender fallback text, and SEO verification tests from 1,520+ to 1,525+.
  • Kept PR #​642 open because it still targets a non-canonical shadow path and includes generated star-history noise instead of the live registry pipeline.

Credits

v12.1.0: "Community Skills, Release Sync, and Dependency Hardening"

Compare Source

[12.1.0] - 2026-06-05 - "Community Skills, Release Sync, and Dependency Hardening"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release packages the June 5 maintainer batch: accepted community PRs, dependency security updates, web-app SEO count fixes, generated registry sync, and data-use guardrails for scraping-oriented documentation. The catalog is synced to 1,520+ skills.

New Skills

  • antigravity-agent-manager - agent lifecycle and project orchestration guidance for Antigravity workflows.
  • linkedin-content-generator - LinkedIn post, carousel, newsletter, and content-calendar generation helpers.
  • event-staffing-ordering - staffing-order workflow guidance for event operations.
  • event-staffing-compliance - compliance review guidance for event staffing workflows.
  • 2slides-ppt-generator - 2Slides API workflows for generating, exporting, and narrating presentation decks.
  • examprep-ai - education and exam-preparation assistant workflows.
  • hasdata - HasData API workflows for compliant web-data collection.
  • hasdata-cli - HasData CLI workflows with safer install guidance and data-use guardrails.
  • anti-sycophancy - prompt and review patterns for reducing agreement bias in AI assistants.
  • permission-manager - permission review and approval-flow guidance for agent work.
  • skill-suggester - skill recommendation workflow for routing tasks to relevant playbooks.
  • smart-git-automation - Git automation patterns for safer repository operations.

Improvements

  • Updated React Router dependencies to resolve the current high-severity Dependabot/audit findings.
  • Hardened vercel-optimize sanitizer coverage and star-history refresh automation.
  • Fixed web-app SEO count verification after the catalog grew to 1,520+ skills.
  • Synced generated registry, catalog, compatibility reports, plugin mirrors, docs, sitemap, and web assets for the 1,520-skill catalog.
  • Tightened scraping-related wording and documentation safety guidance for HasData skills.

Credits

v12.0.0: "Specialized Plugins, Discovery SEO, and Community Skill Intake"

Compare Source

[12.0.0] - 2026-06-03 - "Specialized Plugins, Discovery SEO, and Community Skill Intake"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release packages the June 2-3 maintainer work into a major catalog update: specialized Codex bundle plugins, stronger GitHub/AI discovery metadata, webmaster verification, star-history refreshes, and the accepted community PR batch. It keeps PR #​642 open because it still targets a non-canonical shadow path rather than the live registry pipeline.

New Skills

  • skill-issue - activation-audit workflow for grading skill descriptions, diagnosing prompt matching, and finding collision clusters before a skill fails to fire.
  • polis-protocol - multi-agent coordination workflow using capability cards, routing history, and protocol amendments.
  • accesslint-scan - full-page accessibility scans through AccessLint Chrome and CLI tooling.
  • accesslint-diff - baseline-vs-branch accessibility regression review for changed pages.
  • accesslint-audit - issue-focused accessibility audit workflow for larger remediation passes.
  • composition-patterns - React composition guidance for compound components, explicit variants, state boundaries, and React 19 patterns.
  • debugging-toolkit - structured debugging workflow for reproducible traces, hypotheses, and fixes.
  • deploy-to-vercel - Vercel deployment workflow with CLI/scripted project setup.
  • python-development - Python project workflow guidance for implementation, testing, and environment hygiene.
  • react-native-skills - React Native rules for performance, UI primitives, navigation, state, and Expo-friendly implementation.
  • tdd-workflows - test-first development workflow for small, verified changes.
  • vercel-cli-with-tokens - token-aware Vercel CLI operations for automation contexts.
  • vercel-optimize - deep Vercel performance and cost optimization workflow with scanners, gates, support topics, and report rendering.
  • vercel-react-view-transitions - React/Next.js View Transitions guidance and implementation recipes.

Improvements

  • Added specialized Codex bundle plugins for agent/MCP building, automation, data analytics, DevOps/cloud, documents/presentations, marketing/SEO/growth, and related high-signal workflows.
  • Refreshed plugin marketplace manifests, editorial bundle docs, specialized-plugin documentation, and candidate analysis so the plugin direction is visible from the README and docs.
  • Improved AI and search discovery signals with stronger repository metadata, prerendered home/catalog metadata, a specialized plugin landing page, and a live SEO discovery smoke check.
  • Added Bing and Google webmaster verification assets and standardized the sitemap namespace for crawler compatibility.
  • Updated the star-history chart and removed the old contributor-grid explainer from the README.
  • Replaced deprecated shadcn-ui CLI references with the current shadcn command in the Radix UI design-system guidance.
  • Synced generated registry, catalog, compatibility reports, plugin mirrors, docs, sitemap, web assets, and SEO skill-count claims for the 1,508-skill catalog.
  • Fixed the web app SEO verifier after the catalog grew from 1,494+ to 1,508+, restoring the Pages deploy workflow to green.

Credits

v11.11.0: "User Thoughts, MiniMax M3, and Registry Hardening"

Compare Source

[11.11.0] - 2026-06-02 - "User Thoughts, MiniMax M3, and Registry Hardening"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges the accepted maintainer batch from June 2, adds project-local user intent persistence, updates MiniMax CLI guidance for MiniMax-M3, fixes the agy installer layout, and closes the current Dependabot critical alerts.

New Skills

  • user-thoughts - project-local mdbase memory for persisting user decisions, constraints, UI/UX rationale, backlog items, and project preferences across sessions and agents.

Improvements

  • Updated mmx-cli documentation so chat workflows point at MiniMax-M3 as the default model.
  • Added batch output guidance across the accepted SEO and production QA skill updates.
  • Normalized user-thoughts source metadata, README attribution, runtime templates, references, scripts, and plugin mirrors in English for public catalog use.
  • Fixed agy installer guidance so Antigravity installs use directory-based skill layouts instead of flat markdown files.
  • Bumped the web app Vitest stack to close the critical Dependabot alerts and verified npm audit returns zero open vulnerabilities.
  • Synced generated registry, catalog, compatibility reports, plugin mirrors, docs, sitemap, and web assets for the 1,494-skill catalog.

Credits

v11.10.0: "SEO, Yield, YouTube, and Release Hardening"

Compare Source

[11.10.0] - 2026-05-31 - "SEO, Yield, YouTube, and Release Hardening"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges the accepted community PRs from the current maintainer batch, adding SEO production workflows, passive-income analysis, grounded math-spec extraction, AI disruption planning, and API-backed YouTube research.

New Skills

  • nextjs-seo-indexing - Next.js indexing diagnostics and production SEO remediation for metadata, rendering, canonicals, sitemaps, robots, and Search Console workflows.
  • schema-markup-generator - structured-data generation and validation for products, articles, FAQs, breadcrumbs, organizations, local businesses, and rich-result eligibility.
  • social-metadata-hardening - Open Graph, Twitter/X card, preview-image, and share-surface hardening for production web pages.
  • vibe-code-cleanup - production cleanup workflow for AI-generated web apps, removing placeholders, fragile logic, and demo-only artifacts before launch.
  • vibecode-production-qa-validator - launch QA for AI-assisted web builds across SEO, accessibility, copy, responsive behavior, performance, and deployment readiness.
  • yield-intelligence - passive-income portfolio analysis across Treasuries, dividend ETFs, REITs, and preferred stocks.
  • doc2math - grounded conversion of narrative technical documents into Mathematical Problem Specifications.
  • moatmri - AI disruption pressure mapping with 10-vector exposure scoring and a 90-day defensive plan.
  • youtube-full - TranscriptAPI-backed YouTube transcript, search, channel, playlist, and monitoring workflows for cloud-safe video research.

Improvements

  • Added batch output options and refreshed generated registry, catalog, compatibility, plugin mirror, documentation, and web assets for the expanded catalog.
  • Hardened unsafe skill guidance and made security hygiene tests self-contained for CI.
  • Improved agy install handling and Windows test portability.
  • Updated the star history chart and release-state metadata.

Credits

v11.9.0: "Container, CI, Market, and Wallet Guard Skills"

Compare Source

[11.9.0] - 2026-05-30 - "Container, CI, Market, and Wallet Guard Skills"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges the accepted community and official skill PRs from the current maintainer batch, adding container hardening, advanced GitHub Actions workflows, Longbridge market-data guidance, and paid-inference wallet guards.

New Skills

  • container-security-hardening - Docker/container image and runtime hardening for base images, CVE scanning, SBOM/signing, seccomp/AppArmor, and Kubernetes pod-security controls.
  • github-actions-advanced - production-grade GitHub Actions CI/CD design, debugging, reusable workflows, OIDC authentication, caching, environments, secrets, and release automation.
  • longbridge - official Longbridge Securities market-data workflow for quotes, charts, fundamentals, portfolios, options, and trilingual HK/US/A-share/SG market analysis.
  • runaway-guard - cost-safety discipline for paid AI/inference APIs with per-run, per-day, iteration, concurrency, and provider-dashboard wallet caps.

Improvements

  • Normalized incoming PR metadata, source credits, and security-sensitive install snippets before merge so maintainer CI stayed green.
  • Synced generated registry, catalog, compatibility, plugin mirror, documentation, and web assets for the expanded skill catalog.

Credits

v11.8.0: "Decision, Messaging, Algorithm, and Supply-Chain Skills"

Compare Source

[11.8.0] - 2026-05-27 - "Decision, Messaging, Algorithm, and Supply-Chain Skills"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges the accepted community skill PRs from the current maintainer batch, adding decision support, Sendblue messaging workflows, algorithmic discipline playbooks, and a Bumblebee supply-chain inventory wrapper.

New Skills

  • lemmaly - gateway discipline for stating Big-O, data structure, and algorithm family before writing loops, queries, or recursion.
  • mathguard - large-input acceleration playbook for Bloom filters, HyperLogLog, Count-Min Sketch, FFT, LSH, and related techniques.
  • invariant-guard - correctness-first workflow for contracts, loop invariants, termination arguments, and edge cases.
  • complexity-cuts - corrective workflow for improving shipped code with poor Big-O one transformation at a time.
  • sendblue-cli - Sendblue CLI guidance for iMessage, SMS, and RCS workflows.
  • sendblue-api - Sendblue HTTP/JSON API guidance for application code.
  • sendblue-notify - notification patterns for texting a user when an agent task is done.
  • textme - local daemon workflow for bridging inbound iMessages into Claude Code sessions.
  • bumblebee - read-only supply-chain inventory and exposure scanning with Perplexity's Bumblebee CLI.
  • decision-navigator - targeted-question workflow for helping users gain clarity on decisions before choosing a path.

Improvements

  • Added a stdlib-only Bumblebee report renderer for local Markdown summaries from NDJSON scan output.
  • Synced generated registry, catalog, compatibility, plugin mirror, documentation, and web assets for the expanded skill catalog.

Credits

v11.7.0: "Community Skill Intake and Merge Hygiene"

Compare Source

[11.7.0] - 2026-05-26 - "Community Skill Intake and Merge Hygiene"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges the clean community skill PRs from the current maintainer batch, refreshes generated catalog/plugin/web assets to 1,470+ skills, and hardens batch merges so unwanted Claude co-author trailers are stripped from future squash commits.

New Skills

  • mesh-memory - structured memory mesh workflow for persistent agent context and recall.
  • flowhunt-skill - automation discovery audit for workflow intake, tool-by-tool review, and productivity opportunity prioritization.
  • socialclaw - social media campaign scheduling and publishing across major platforms from a single workspace API key.
  • geminiignore-finops - .geminiignore setup patterns for context-window efficiency and token cost reduction.
  • ii-commons - deterministic research retrieval across arXiv, PubMed/PMC, and supported US policy corpora.

Improvements

  • Synced generated registry, catalog, compatibility, plugin mirror, documentation, and web assets to the new 1,470+ skill count.
  • Updated the maintainer batch merge script to pass explicit squash commit subjects/bodies and remove Claude/Anthropic co-author trailers from future merge commits.

Credits

v11.6.0: "Audit Hardening and Karpathy Guidelines"

Compare Source

[11.6.0] - 2026-05-23 - "Audit Hardening and Karpathy Guidelines"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release hardens the repository after a full audit pass, fixes issue #​611 by syncing andrej-karpathy to English upstream guidelines, and improves release/security guardrails.

Security

  • Replaced executable pipe-to-shell install examples across canonical skills with package-manager or download-inspect-execute flows, and removed the obsolete allowlist comments.
  • Hardened the web-app refresh archive fallback by pre-validating tar/zip paths, rejecting archive symlink entries, and verifying extracted real paths before moving downloaded skills into place.
  • Replaced the Telegram Node boilerplate and docs examples with Telegraf to remove the deprecated vulnerable request dependency chain and avoid putting bot tokens in webhook URLs.
  • Hardened WhatsApp webhook signature validation so malformed x-hub-signature-256 headers return 401 instead of throwing on timingSafeEqual buffer length mismatches.
  • Refused installer migrations through symlinked target directories and added regression coverage for symlink target failures.
  • Restored TLS verification by default in Junta scraper implementations, with insecure TLS only available through the shared JUNTA_INSECURE_TLS escape hatch.

Fixed

  • Replaced the non-English andrej-karpathy skill content with English Karpathy coding guidelines synced from the upstream multica-ai/andrej-karpathy-skills source.
  • Made audit:skills:strict enforce an explicit legacy warning budget so strict skill-audit debt is tracked and regressions fail without blocking on the historical backlog.
  • Replaced realistic AWS/private-key examples with unmistakable placeholders and taught security:docs to block those patterns from returning.
  • Rebuilt local documentation link validation as a deterministic, path-aware checker for README.md, docs/, and docs_zh-CN/, and repaired the broken localized/internal markdown links it now catches.
  • Refreshed stale Chinese documentation release/count claims to 11.5.0 / 1,465+ and marked the old final validation report as a historical snapshot.
  • Made the Chinese glossary validation report deterministic by removing timestamps and machine-specific absolute paths.
  • Stopped publishing .disabled skills as web static assets during app:setup.
  • Updated web-app SEO counts and social metadata to 1,465+, aligned the SEO verifier and Pages workflow with the linked site.webmanifest, and corrected the documented canonical URL environment variables.
  • Added generated-index duplicate-ID protection so future nested skill basename collisions fail during index generation.
  • Fixed the Remotion chart rule typo from implmentation to implementation.

v11.5.0: "Security Boundary Hardening and New Agent Skills"

Compare Source

[11.5.0] - 2026-05-21 - "Security Boundary Hardening and New Agent Skills"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

This release hardens plugin-safe distribution boundaries, resolves the current Dependabot ws alert in the web app lockfile, and merges PR #​604 and PR #​605 through the maintainer workflow.

New Skills

  • subagent-orchestrator - quota-aware parallel subagent coordination for large, multi-file Antigravity tasks.
  • bilig-workpaper - formula-backed WorkPaper JSON and MCP guidance for deterministic spreadsheet-style agent workflows.

Security

  • plugin-safe boundary hardening - blocks critical-risk or third-party setup-sensitive community skills from the generated Codex and Claude plugin-safe distributions.
  • ingest-youtube input hardening - validates single-video YouTube URLs, terminates yt-dlp options with --, ignores user config, adds subprocess timeouts, and neutralizes untrusted metadata in generated markdown.
  • web app dependency fixes - updates ws to the patched 8.20.1 range and refreshes vulnerable transitive audit entries in apps/web-app/package-lock.json.

Improvements

  • generated artifact sync - refreshes compatibility data, skill indexes, plugin mirrors, docs, and visible skill counts to 1,464+.
  • subagent-orchestrator metadata - normalizes PR #​604 metadata so the skill passes repository validation.

Who should care

  • Plugin users get a safer marketplace-style distribution that excludes setup-sensitive critical workflows from safe plugin bundles.
  • Vault users get safer YouTube transcript ingestion with stricter URL and markdown handling.
  • Agent workflow builders get two new community skills for parallel agent coordination and formula-backed workbook automation.

Credits

v11.4.1

Compare Source

[11.4.1] - 2026-05-20 - "Installer Supply-Chain Hardening"

Patch release for the npm installer used by Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

This release hardens the npm installer after reviewing Socket.dev's AI-detected code-anomaly warning for tools/bin/install.js.

Improvements

  • release-pinned installs - default npx antigravity-awesome-skills installs now clone the matching package release tag instead of the repository tip, reducing drift between npm package contents and installed skills.
  • git ref validation - --tag and --version refs are validated before invoking git clone, while still allowing explicit branch installs such as --tag main.
  • destination symlink guard - installer copy operations now refuse to write through pre-existing destination symlinks.
  • installer docs and regression coverage - documents the release-pinned default and adds installer tests for release-tag resolution and unsafe ref rejection.

Who should care

  • npm users get installer behavior that is pinned to the published package version by default.
  • security scanners and maintainers get a narrower supply-chain surface for the installer path Socket flagged.

v11.4.0: "Mercury MCP, Photopea Embeds, and Codex Bundle Names"

Compare Source

[11.4.0] - 2026-05-20 - "Mercury MCP, Photopea Embeds, and Codex Bundle Names"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges PR #​598 and PR #​601 through the maintainer workflow, fixes issue #​597 by shortening Codex bundle plugin identifiers, and reduces antivirus false-positive risk in the Linux privilege-escalation guidance from issue #​600.

New Skills

  • mercury-mcp - lookup reference for Mercury MCP tools covering messages, threads, tasks, automations, agent context, and admin-scoped team graph tools.
  • photopea-embedded-editor - web-app integration guide for embedding Photopea with photopea.js, file loading, scripting, exports, layers, text, selections, and template editing patterns.

Improvements

  • Codex bundle names - generated Codex bundle plugins now use compact agyb-* names while preserving existing repo-local source directories, keeping qualified skill names within the 64-character loader limit.
  • bundle regression tests - adds coverage that every generated Codex bundle plugin name and plugin:skill qualified name stays within the 64-character limit.
  • security skill false-positive reduction - replaces a pipe-to-shell LinPEAS example with download, inspect, chmod, and explicit execution steps for authorized labs.
  • generated artifact sync - refreshes catalog, skill index, plugin mirrors, web assets, contributor credits, package metadata, and visible skill counts to 1,462+.

Who should care

  • Codex CLI users can enable editorial bundles without losing valid skills to long qualified plugin names.
  • MCP users get a compact Mercury tool reference for agent messaging, task tracking, and automations.
  • Web app builders get a practical Photopea embedding guide for browser-based image editing workflows.
  • Security learners and maintainers get safer documentation patterns that are less likely to trigger local antivirus heuristics.

Credits

v11.3.0: "Discovery Manifests and Recommendation Pipelines"

Compare Source

[11.3.0] - 2026-05-16 - "Discovery Manifests and Recommendation Pipelines"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release closes issue #​596 with a stable discovery-manifest contract and merges PR #​595 through the maintainer squash-merge workflow. It keeps contributor PRs source-only while making main the canonical owner of generated manifests, web assets, and release metadata.

New Skills

  • recsys-pipeline-architect - recommendation, ranking, and feed pipeline design using a Source -> Hydrator -> Filter -> Scorer -> Selector -> SideEffect architecture.

Improvements

  • stable discovery manifest - keeps root skills_index.json as the canonical public manifest, mirrors it exactly to data/skills_index.json, and documents lazy-loading usage for downstream tools.
  • manifest schema and docs - adds schemas/skills-index.v1.schema.json plus user and integration docs that distinguish the canonical root manifest from the compatibility mirror.
  • CI-safe drift checks - extends consistency auditing and PR artifact previews so root/data/web-backup manifest drift is visible and enforced on main.
  • generated artifact sync - refreshes catalog, skill index, plugin mirrors, web assets, contributor credits, package metadata, and visible skill counts to 1,460+.

Who should care

  • Tool builders and indexers get a stable manifest contract they can validate and consume without loading every skill up front.
  • Users with large installs get clearer guidance for filtering by category, risk, source, and description before lazy-loading individual skills.
  • Recommendation-system builders get a focused skill for designing composable feed and ranking pipelines across TypeScript, Go, Python, and adjacent stacks.
  • Maintainers get a source-only PR path with canonical generated artifacts refreshed on main before release.

Credits

v11.2.0: "Market Intelligence, Token Routing, and Chinese Growth Skills"

Compare Source

[11.2.0] - 2026-05-13 - "Market Intelligence, Token Routing, and Chinese Growth Skills"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges PRs #​587, #​588, #​589, #​590, and #​591 through the maintainer workflow. It adds measurement-driven model routing, Chinese market strategy skills, MCP tool-building guidance, options-flow analysis, RSS news sentiment briefings, and a refreshed Hermes Tweet path for the X/Twitter scraper.

New Skills

  • tokenwise - measurement-driven Claude Code model routing with local cost logs, A/B validation, and guarded Haiku/Sonnet/Opus task routing.
  • mcp-tool-developer - end-to-end MCP server and tool development guidance across schema design, TypeScript/Python implementation, testing, deployment, and registry publishing.
  • wechat-official-account-strategist - WeChat Official Account content strategy, publishing cadence, topic planning, and growth guidance.
  • xiaohongshu-content-strategist - Xiaohongshu content planning, SEO-style discovery, visual hooks, and China-market creator workflows.
  • options-flow-analyzer - real-versus-lottery options flow analysis that filters deep OTM noise from raw put/call ratios.
  • news-sentiment-engine - multi-source RSS news aggregation and Claude-powered sentiment briefing workflow.

Improvements

  • x-twitter-scraper refresh - documents the Hermes Tweet plugin path alongside the existing X/Twitter scraping guidance.
  • overlap cleanup - resolves the duplicate options-flow-analyzer PR overlap by keeping the richer release-ready metadata, usage, and limitations coverage.
  • generated artifact sync - refreshes catalog, skill index, plugin mirrors, web assets, package metadata, and visible skill counts to 1,459+.

Who should care

  • Claude Code users get a practical cost-routing skill for measuring and reducing model spend.
  • Market and research users get options-flow filtering plus structured news sentiment briefings.
  • China-market operators get platform-specific WeChat and Xiaohongshu strategy workflows.
  • MCP builders get a focused skill for designing, testing, and shipping tool servers.
  • Maintainers get a cleaned-up five-PR batch with synced contributors, generated assets, and release validation.

Credits

v11.1.0: "Trace Audits, YouTube Ingest, and Reasoning Harnesses"

Compare Source

[11.1.0] - 2026-05-11 - "Trace Audits, YouTube Ingest, and Reasoning Harnesses"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges PRs #​582, #​583, #​584, and #​586 through the maintainer squash-merge workflow, including fork-run approval, PR body normalization, source-credit fixes, branch conflict refreshes, and generated-state syncs on main. It refreshes the X/Twitter scraper skill, adds local session auditing with agenttrace, adds single-video YouTube transcript ingestion, and adds an Ejentum MCP reasoning-harness workflow.

New Skills

  • agenttrace-session-audit - local AI coding-agent session audits for token and cost spikes, tool failures, retry loops, latency gaps, anomalies, health scores, and session diffs.
  • ingest-youtube - YouTube video transcript ingestion into markdown vaults with yt-dlp metadata, VTT cleanup, idempotent vault writes, and capture-seed stubs.
  • ejentum-reasoning-harness - MCP-based cognitive harness workflow for reasoning, code review, anti-deception checks, and memory-drift analysis.

Improvements

  • x-twitter-scraper refresh - updates the existing skill to the current Xquik public API surface and TweetClaw plugin path.
  • source provenance and credits - adds README community credits for agenttrace, ai-brain-starter, and ejentum-mcp, with license provenance for the new externally sourced skills.
  • generated artifact sync - refreshes catalog, skill index, plugin mirrors, web assets, package metadata, and visible skill counts to 1,453+.

Who should care

  • Maintainers and power users get trace-level visibility into local AI coding sessions before retrying or comparing runs.
  • Knowledge-base builders get a source-normalized YouTube transcript ingest path for markdown vault workflows.
  • Agent workflow designers get MCP-backed reasoning harnesses for higher-risk reasoning, coding, honesty, and memory-drift tasks.
  • Social and automation users get fresher X/Twitter scraper guidance aligned with the current source API and plugin ecosystem.

Credits

v11.0.0: "Agent Execution, Game Planning, and Skill Writer References"

Compare Source

[11.0.0] - 2026-05-08 - "Agent Execution, Game Planning, and Skill Writer References"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.

Start here:

This release merges PRs #​575, #​577, #​578, #​579, and #​581 through the maintainer squash-merge workflow, including fork-run approval, PR body refreshes, source-credit fixes, contributor sync, and generated-state refreshes on main. It adds on-chain transaction orchestration, richer clarification, mock-data auditing

✂ Note

PR body was truncated to here.

Configuration

📅 Schedule: (in timezone UTC)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

  • If you want to rebase/retry this PR, check this box

This PR has been generated by Mend Renovate.

@gw0-bot gw0-bot force-pushed the renovate/major-all-deps branch 3 times, most recently from 3bc7db1 to 0b8f6c3 Compare May 28, 2026 05:25
@gw0-bot gw0-bot force-pushed the renovate/major-all-deps branch 3 times, most recently from edd78a7 to 7d57d36 Compare June 3, 2026 05:39
@gw0-bot gw0-bot changed the title chore(deps): update dependency sickn33/antigravity-awesome-skills to v11 chore(deps): update all dependencies to v11 Jun 3, 2026
@gw0-bot gw0-bot force-pushed the renovate/major-all-deps branch from 7d57d36 to 1eedcc1 Compare June 4, 2026 05:37
@gw0-bot gw0-bot changed the title chore(deps): update all dependencies to v11 chore(deps): update all dependencies to v12 Jun 4, 2026
@gw0-bot gw0-bot force-pushed the renovate/major-all-deps branch from 1eedcc1 to be71eeb Compare June 6, 2026 05:18
@gw0-bot gw0-bot force-pushed the renovate/major-all-deps branch from be71eeb to a5f2066 Compare June 8, 2026 05:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@gw0-bot