feat: improve skill scores across 5 lowest-scoring skills#1
Open
rohan-tessl wants to merge 2 commits intoalffei:mainfrom
Open
feat: improve skill scores across 5 lowest-scoring skills#1rohan-tessl wants to merge 2 commits intoalffei:mainfrom
rohan-tessl wants to merge 2 commits intoalffei:mainfrom
Conversation
Hey 👋 @alffei 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 | |-------|--------|-------|--------| | requesting-code-review | 57% | 93% | +36% | | systematic-debugging | 54% | 85% | +31% | | executing-plans | 63% | 93% | +30% | | writing-skills | 63% | 93% | +30% | | receiving-code-review | 70% | 96% | +26% | | writing-plans | 54% | 80% | +26% | | brainstorming | 59% | 84% | +25% | | spec-architect | 80% | 100% | +20% | | api-expert | 70% | 88% | +18% | | ruoyi-code-generator | 75% | 93% | +18% | | code-reviewer | 76% | 93% | +17% | | springboot-init | 86% | 100% | +14% | | report-generator | 74% | 84% | +10% | | project-planner | 80% | 89% | +9% | | doc-pipeline | 84% | 93% | +9% | | formatting-wechat-tech-posts | 86% | 93% | +7% | | writing-wechat-tech-posts | 83% | 89% | +6% | | planning-wechat-tech-account | 84% | 89% | +5% | | finishing-a-development-branch | 88% | 93% | +5% | | evidencing-wechat-tech-posts | 86% | 89% | +3% | | ideating-wechat-tech-topics | 86% | 89% | +3% | | iterating-wechat-tech-posts | 86% | 89% | +3% | | outlining-wechat-tech-posts | 86% | 89% | +3% | | titling-wechat-tech-posts | 86% | 89% | +3% | <details> <summary>Changes made</summary> - **Expanded frontmatter descriptions** with specific capability statements and "Use when..." trigger clauses for better skill discovery - **Converted description format** to quoted strings (standard frontmatter format) - **Added concrete examples** — executable code snippets, input/output pairs, and expected output formats where skills lacked actionability - **Structured workflows** into numbered steps with validation checkpoints at each phase - **Added "When to Use" sections** with natural trigger keywords in both English and Chinese where appropriate - **Progressive disclosure** — referenced existing sibling files (references/, assets/) rather than inlining heavy content - **Preserved all domain expertise** — Chinese content stays Chinese, specialized terminology (FastAPI, Pydantic, RuoYi, WeChat, etc.) retained throughout - **Removed redundancy** — consolidated overlapping sections, trimmed unnecessary explanations of known concepts </details> <details> <summary>🤖 Tessl Skill Review GitHub Action — automated feedback on future PRs</summary> This PR also adds `.github/workflows/skill-review.yml` — a lightweight GitHub Action that automatically reviews `SKILL.md` files on pull requests: - **What it does:** On PRs that touch any `**/SKILL.md`, the workflow runs [`tesslio/skill-review`](https://github.com/tesslio/skill-review) and posts **one** PR comment with Tessl scores and feedback (updated on new pushes). - **Zero extra accounts:** Contributors do **not** need a Tessl login — only the default `GITHUB_TOKEN` is used to post the comment. - **Non-blocking by default:** The check is **feedback-only** — no surprise red CI. You can optionally add `with: fail-threshold: 70` later if you want PRs to fail on low scores. - **Not a build replacement:** This is purely review automation for skill markdown, not a substitute for any existing CI/CD pipeline. </details> 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 - [@rohan-tessl](https://github.com/rohan-tessl) - if you hit any snags. Thanks in advance 🙏
rohan-tessl
force-pushed
the
improve/skill-review-optimization
branch
from
089b13e to
8fc947f
Compare
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 @alffei 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements.Here's the full before/after:
This PR intentionally caps changes at 5 skills to keep it reviewable — the included GitHub Action (see below) will surface Tessl feedback on future
SKILL.mdchanges so the rest of the library can improve incrementally.What changed
dispatching-parallel-agents — Expanded frontmatter description with concrete actions (grouping by subsystem, creating focused prompts, integrating parallel results) and explicit trigger terms.
subagent-driven-development — Rewrote description to specify the full cycle (implement → spec-review → quality-review → fix → re-review) with clear trigger terms like "dispatching subagents" and "two-stage code review."
using-superpowers — Reframed description around concrete capabilities (skill discovery, Skill tool invocation, TodoWrite conversion) instead of the overly broad "any conversation" trigger. Trimmed redundant EXTREMELY-IMPORTANT block and consolidated Red Flags table from 12 to 6 entries.
test-driven-development — Added comprehensive description with Red-Green-Refactor cycle, concrete trigger terms (TDD, test-first, failing test). Consolidated the redundant "Why Order Matters" and "Common Rationalizations" sections into a single concise table, eliminating ~60 lines of duplicated content.
springboot-init — Added "Use when..." clause with specific triggers (new Spring Boot project, Java backend init, Maven dependencies, CRUD module). Added verification steps to workflows (
mvn compile, endpoint testing) and an inline Controller example for immediate actionability.🤖 Tessl Skill Review GitHub Action
This PR also adds
.github/workflows/skill-review.yml— a GitHub Action that automatically reviews anySKILL.mdchanges on future PRs:**/SKILL.md, the workflow runstesslio/skill-reviewand posts one comment with Tessl scores and feedback (updated on new pushes).GITHUB_TOKENis used to post comments.fail-threshold: 70later if you want a hard gate.with: fail-threshold: 70(or any score) later if you want PRs to fail on low skill scores.SKILL.mdgets automatic review comments, so the rest of the library improves incrementally.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 🙏