feat: improve coding skill score from 52% to 75%#81
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @isolomatov-gd 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for the `coding` skill. Here's the before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | coding | 52% | 75% | **+23%** | The other skills I baselined (planning 66%, debugging 71%, self-organization 78%, orchestrator-contract 75%, etc.) were left untouched — this PR focuses on the single highest-impact change. <details> <summary>Changes made</summary> **Description improvements (biggest impact):** - Replaced abstract buzzwords ("KISS/SOLID/DRY principles, zero-tolerance quality") with concrete actions: "implement features, fix bugs, refactor code with environment-aware configuration (local/dev/test/prod), dependency-ordered validation (databases → APIs → browser → mobile)" - Added explicit "Use when..." clause with specific triggers: code changes, DevOps scripts, CI/CD pipelines, code review, impact analysis - Description specificity went from 1/3 → 3/3 and completeness from 2/3 → 3/3 **Content improvements:** - Added explicit 6-step implementation workflow: Load context → Analyse impact → Implement → Validate → Review → Update docs - Added feedback loop for validation failures: diagnose with `debugging` skill → fix → re-validate from step 4 - Compressed well-known principle acronyms (KISS, SOLID, DRY, YAGNI, MECE) into actionable constraints — Claude already knows these; the tokens are better spent on workflow structure - Expanded pitfalls from 1 → 4 items covering common failure modes (missed callers, redundant patterns, cross-environment validation, working directory issues) - Moved `best_practices` guidance into the workflow steps where it's actionable, eliminating a separate section - Workflow clarity went from 2/3 → 3/3 </details> I also stress-tested your `coding` skill against a task eval involving dependency-ordered validation across database schema changes, API endpoints, and browser flows — it navigated the layered validation sequence really well. 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 🙏
yogesh-tessl
requested review from
ElizaVetaFomka and
YevheniiaLementova
as code owners
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 @isolomatov-gd 👋
seriously thoughtful work. Rosetta is going after exactly the right problem - meta-prompting, context engineering, and centralised instruction management are where things get hard, and you’re tackling it head-on. The 31 well-structured skills, covering everything from workspace discovery to risk assessment, show real depth.
also ran your skills through
tessl skill reviewat work and found some targeted improvements for thecodingskill. Here's the before/after:The other skills I baselined (planning 66%, debugging 71%, self-organization 78%, orchestrator-contract 75%, etc.) were left untouched. This PR focuses on the single highest-impact change.
Changes made
Description improvements (biggest impact):
Content improvements:
debuggingskill → fix → re-validate from step 4best_practicesguidance into the workflow steps where it's actionable, eliminating a separate sectionalso stress-tested your
codingskill against a task eval involving dependency-ordered validation across database schema changes, API endpoints, and browser flows. It navigated the layered validation sequence really well. Kudos for that.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.