feat: improve tdd skill score from 83% to 93%#11
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @ericjohnolson 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for `tdd`. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | **tdd** | **83%** | **93%** | **+10%** | | adr | 95% | — | — | | research | 93% | — | — | | harness | 93% | — | — | | implement | 93% | — | — | | plan-tasks | 92% | — | — | | reflect | 83% | — | — | I picked `tdd` because it had the most improvement headroom alongside `reflect`, and TDD is core to your RPI methodology — the `implement` skill's three-agent orchestration relies on the same Core Rules and red-green discipline defined here. <details> <summary>Changes made</summary> **Description improvements (biggest impact):** - Rewrote from jargon-heavy label ("L3/L4 altitude testing") to a concrete description listing specific actions: guides writing one test at a time, ZOMBIES test discovery, boundary-level and integration testing, structured session log tracking - Added explicit "Use when..." clause with natural trigger terms users would actually say ("writing unit tests", "doing TDD", "start with tests") - Added "Do NOT use for..." negative trigger pointing to `implement` for automated plan execution - Wrapped description in quoted string (standard frontmatter format) **Trigger improvements:** - Added three natural-language trigger phrases: "unit tests for this module", "start with tests", "TDD this feature" **Content improvements:** - Removed introductory philosophy paragraph ("TDD is a design technique...") — Claude already understands TDD motivation, and the behavioral constraints are already encoded in the Core Rules section - Added plain-language parenthetical for L3/L4 jargon in the boundary testing reference link ("boundary and integration-level testing (L3/L4 altitude)") </details> I also stress-tested your `tdd` skill against a ZOMBIES-driven circular buffer implementation and it correctly guided the full zero-one-many-boundary progression without skipping a step. 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 🙏
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 @ericjohnolson 👋
really cool to see CLAUDE.md and AGENTS.md both in here. The 7 skills under praxis covering the full dev cycle from research through TDD to reflection show a thoughtful approach to how you want AI to work through problems.
ran your skills through
tessl skill reviewat work and found some targeted improvements fortdd. Here's the before/after:picked
tddbecause it had the most improvement headroom alongsidereflect, and TDD is core to your RPI methodology, theimplementskill's three-agent orchestration relies on the same Core Rules and red-green discipline defined here.Changes made
Description improvements (biggest impact):
implementfor automated plan executionTrigger improvements:
Content improvements:
quick 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.