feat: improve tdd-init skill score (77% → 96%)#1
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @kelp 👋 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 | |-------|--------|-------|--------| | tdd-init | 77% | 96% | +19% | The other skills scored well out of the box — `kb-research-policy` at 96%, `kb-capture` at 90%, `tdd-orchestrate` at 87%, and `cross-review` at 80%. **Note on zig-claude-kit skills:** `zig-patterns`, `zig-check`, and `zig-init` scored 17–18% due to a missing `name` field in their frontmatter, which causes validation to fail before the content is even evaluated. After adding `name: zig-patterns` etc., they jump to 92–100% — the content itself is excellent. Similarly, `kb-ingest` scored 17% because of `<url>` XML-style tags in the description field. Figured I'd flag that in case it's useful. <details> <summary>Changes to <code>tdd-init</code></summary> - **Expanded frontmatter description** — listed the specific configuration elements the template inserts (test commands, path patterns, build integration, verify gates, language context) and added an explicit "Use when..." clause with trigger terms like "test-driven development", "red-green-refactor", and "TDD workflow" - **Converted description format** — switched from YAML block scalar (`>`) to a quoted string for standard frontmatter compatibility - **Added executable bash snippets** — replaced prose descriptions of file operations with concrete `cat`, `grep`, and conditional bash commands so the agent can copy-paste the workflow - **Concrete placeholder examples** — replaced generic "fill in the template values" with specific placeholder names and example values (e.g. `<TEST_COMMAND>` → `pytest tests/test_{module}.py`) - **Tightened intro** — connected `tdd-init` to `tdd-orchestrate` so the purpose is immediately clear </details> I also stress-tested your `tdd-orchestrate` skill against a few real-world task evals and it held up really well on dispatching the full 7-stage pipeline with proper gate enforcement between red and green phases. 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 🙏
Author
|
hey @kelp, just a friendly follow-up in case this got buried, happy to help move it forward! Totally fine if there's a process, just wanted to keep it visible. |
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 @kelp 👋
this is excellent work. The three plugins feel very focused on making Claude Code produce better, more reliable code in practice. The Zig 0.15.x corrective patterns are especially strong fixing 12 specific code-gen mistakes shows real hands-on experience, not just theory. And pairing that with a language-agnostic TDD pipeline is a smart move.
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:The other skills scored well out of the box
kb-research-policyat 96%,kb-captureat 90%,tdd-orchestrateat 87%, andcross-reviewat 80%.Changes to
tdd-init>) to a quoted string for standard frontmatter compatibilitycat,grep, and conditional bash commands so the agent can copy-paste the workflow<TEST_COMMAND>→pytest tests/test_{module}.py)tdd-inittotdd-orchestrateso the purpose is immediately clearquick 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.