Skip to content

feat: improve morphir-architect skill score (53% → 73%)#438

Open
yogesh-tessl wants to merge 1 commit into
finos:mainfrom
yogesh-tessl:improve/skill-review-optimization
Open

feat: improve morphir-architect skill score (53% → 73%)#438
yogesh-tessl wants to merge 1 commit into
finos:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl
Copy link
Copy Markdown

Hey @DamianReeves 👋

I ran your skills through tessl skill review at work and found some targeted improvements for your morphir-architect skill. Here's the before/after:

Skill Before After Change
morphir-architect 53% 73% +20%
What changed

Description (50% → 100%)

  • Replaced vague "providing guidance on" with concrete actions: "Designs AST node structures, implements IR-to-code transformations, applies functional programming patterns, and architects code generation backends"
  • Added explicit Use when... clause with specific scenarios (building Morphir IR types, Classic/Modern IR conversions, visitor patterns, code generation pipelines)
  • Qualified overly-generic trigger terms - "architecture" → "Morphir architecture", "design patterns" → "Morphir design patterns", "IR" → "IR transformation"

Content (trimmed ~280 lines)

  • Replaced inlined Pattern Catalog (3 full patterns with code examples duplicating knowledge base content) with concise KB reference links
  • Removed duplicate Automation Scripts section (already documented in Review Capability section)
  • Removed Cross-Agent Compatibility section (generic agent invocation examples, not actionable instructions)
  • Removed Feedback Loop / Quarterly Review section (organizational process, not skill execution guidance)

I also stress-tested your morphir-architect skill against a few real-world task evals and it held up really well on Dual IR type design with Classic/Modern conversion bridging. Kudos for that.

Honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.

If you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.

Hey @DamianReeves 👋

I ran your skills through `tessl skill review` at work and found some targeted improvements for your `morphir-architect` skill. Here's the full before/after:

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| morphir-architect | 53% | 73% | **+20%** |
| vulnerability-resolver | 84% | — | — |
| release-manager | 81% | — | — |
| elm-to-fsharp-guru | 70% | — | — |
| aot-guru | 70% | — | — |
| technical-writer | 67% | — | — |
| qa-tester | 66% | — | — |
| template | 15% | — | — |

## Proposed Changes

Focused improvements to the `morphir-architect` skill to improve its description quality and reduce content verbosity — the description score jumped from 50% to 100% and the overall score from 53% to 73%.

## Types of changes

- [x] New feature (non-breaking change which adds functionality)

## Checklist

- [x] Build and tests pass locally
- [x] I have added tests that prove my fix is effective or that my feature works (if appropriate)
- [x] I have added necessary documentation (if appropriate)

<details>
<summary>What changed</summary>

**Description (50% → 100%)**
- Replaced vague "providing guidance on" with concrete actions: "Designs AST node structures, implements IR-to-code transformations, applies functional programming patterns, and architects code generation backends"
- Added explicit `Use when...` clause with specific scenarios (building Morphir IR types, Classic/Modern IR conversions, visitor patterns, code generation pipelines)
- Qualified overly-generic trigger terms — "architecture" → "Morphir architecture", "design patterns" → "Morphir design patterns", "IR" → "IR transformation"

**Content (trimmed ~280 lines)**
- Replaced inlined Pattern Catalog (3 full patterns with code examples duplicating knowledge base content) with concise KB reference links
- Removed duplicate Automation Scripts section (already documented in Review Capability section)
- Removed Cross-Agent Compatibility section (generic agent invocation examples, not actionable instructions)
- Removed Feedback Loop / Quarterly Review section (organizational process, not skill execution guidance)

</details>

I also stress-tested your `morphir-architect` skill against a few real-world task evals and it held up really well on Dual IR type design with Classic/Modern conversion bridging. Kudos for that.

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute.

Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags.

Thanks in advance 🙏

🤖 Generated with [Claude Code](https://claude.com/claude-code)
@linux-foundation-easycla
Copy link
Copy Markdown

CLA Not Signed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant