Skip to content

feat: improve skill review scores for 5 plugin/tdd skills#14

Open
rohan-tessl wants to merge 1 commit intosequenzia:mainfrom
rohan-tessl:improve/skill-review-optimization
Open

feat: improve skill review scores for 5 plugin/tdd skills#14
rohan-tessl wants to merge 1 commit intosequenzia:mainfrom
rohan-tessl:improve/skill-review-optimization

Conversation

@rohan-tessl
Copy link
Copy Markdown

@rohan-tessl rohan-tessl commented Mar 31, 2026

Hey @JaimeParker 👋

I ran your skills through tessl skill review at work and found some targeted improvements.

image

Here's the full before/after:

Skill Before After Change
academic-grant-writer 10% 80% +70%
continuous-agent-loop 34% 90% +56%
continuous-learning-v2 40% 84% +44%
iterative-retrieval 47% 79% +32%
python-patterns 48% 82% +34%

This PR is intentionally scoped to 5 skills to keep it reviewable — more skills can be improved in follow-ups or via automated review on future PRs.

Changes summary
  • academic-grant-writer: Added missing YAML frontmatter (was causing 10% score — deterministic validation failure). Added proper name and description fields with "Use when..." trigger clause. Tightened workflow sections for conciseness while preserving all domain-specific content (总分总 structure, LaTeX notation, Zotero integration, word count targets).

  • continuous-agent-loop: Expanded description with concrete actions and "Use when..." clause. Added an executable sequential loop example with quality gate checks. Replaced vague failure/recovery lists with a structured table mapping failure modes to detection signals and specific recovery actions.

  • continuous-learning-v2: Fixed broken title line break ("Instinct\n-Based" → single line). Trimmed ~50% of content by removing version comparison tables, backward compatibility notes, and architectural explanations that don't help agent execution. Added a verification step for hooks. Improved description with natural trigger terms.

  • iterative-retrieval: Rewrote description with concrete actions and "Use when..." clause. Trimmed the "Problem" section (agent already understands context limitations). Streamlined phase descriptions while preserving the core 4-phase loop, examples, and best practices.

  • python-patterns: Reduced from ~750 lines to ~130 by removing patterns the agent already knows (EAFP, basic comprehensions, context managers, etc.). Focused on project-specific conventions: type hint style, error handling hierarchy, concurrency selection, performance patterns, and tooling config. Added "Use when..." trigger clause.

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 and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags.

Thanks in advance 🙏

$(cat /tmp/tessl-pr-body.md)
@rohan-tessl rohan-tessl marked this pull request as ready for review March 31, 2026 07:10
@rohan-tessl rohan-tessl requested a review from sequenzia as a code owner March 31, 2026 07:10
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