Improve/skill review optimization#7
Open
yogesh-tessl wants to merge 2 commits intoorientpine:mainfrom
Open
Conversation
Hey @orientpine 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | agent-development | 62% | 89% | **+27%** | | plugin-structure | 62% | 86% | **+24%** | > **Note on baseline scores:** The original `agent-development` and `plugin-structure` skills had name fields with spaces and capitals (`"Agent Development"`, `"Plugin Structure"`) instead of kebab-case, which caused them to fail validation entirely (scoring ~17%). I fixed the names first, then re-evaluated to get a fair 62% baseline before optimizing the content. The name fixes alone are valuable — they bring the skills into compliance with the Agent Skills Specification. **Both skills — frontmatter fixes:** - Fixed `name` fields to kebab-case (matching directory names per Agent Skills Spec) - Rewrote `description` fields as quoted strings with concrete capability statements + "Use when..." triggers - Removed `version: 0.1.0` (not a valid SKILL.md frontmatter key) **agent-development (62% → 89%):** - Removed duplicate DO/DON'T checklist, redundant system prompt template, duplicate validation rules - Trimmed verbose model descriptions and color guidelines to concise inline lists - ~90 lines of redundancy removed, all domain-specific content preserved **plugin-structure (62% → 86%):** - Condensed name requirements, path rules, and "never use" patterns - Removed explanations of basic concepts Claude already knows - Collapsed duplicate auto-discovery explanation - Trimmed generic best practices, kept plugin-specific advice - ~90 lines of redundancy removed, all structural guidance preserved Focused on the 2 skills with the biggest improvements to keep the diff reviewable (215 lines). Also reviewed skill-development (+12%), pptx-design-styles (+12%), and wiki-gen (93%) but dropped them for PR size. Happy to follow up in a separate PR.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @orientpine 👋
18 plugins unified into a single marketplace - the breadth at v3.28, from ISD research proposals to patent trend analysis to Obsidian skills, is impressive. Baekdong Cha's investment analysis agent lineup (equity-research, macro-analysis, stock-consultation) is particularly well put together. Wanted to suggest a few improvements to the SKILL.md.
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:Changes Summary
Both skills - frontmatter fixes:
namefields to kebab-case (matching directory names per Agent Skills Spec)descriptionfields as quoted strings with concrete capability statements + "Use when..." triggersversion: 0.1.0(not a valid SKILL.md frontmatter key)agent-development (62% → 89%):
plugin-structure (62% → 86%):
Focused on the 2 skills with the biggest improvements to keep the diff reviewable (215 lines). Also reviewed skill-development (+12%), pptx-design-styles (+12%), and wiki-gen (93%) but dropped them for PR size. Happy to follow up in a separate PR.
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.
I also added a lightweight GitHub Action that auto-reviews any skill.md changed in a PR (includes min permissions, uses a pinned action version, only posts a review comment).
This means that it gives you and your contributors an instant quality signal before you have to review yourself (no signup, no tokens needed).
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 🙏