feat: improve skill score for update-gems#2641
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @instructure 👋 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 | |-------|--------|-------|--------| | update-gems | 63% | 99% | +36% | | ketchup | 10% | 68% | +58% | | create-commit-msg | 17% | 63% | +46% | | squash-migrations | 75% | 75% | — | | rspec | 70% | 70% | — | > **Note:** `ketchup` and `create-commit-msg` had near-zero baseline scores due to YAML parse errors — `ketchup` had unquoted brackets in `argument-hint`, and `create-commit-msg` used underscores instead of kebab-case in the `name` field. I fixed those formatting issues to unblock proper evaluation. Their "Before" scores above reflect the corrected baselines (68% and 63%), not the original broken scores (10% and 17%). The deep optimization targeted **`update-gems`** — it had the most improvement headroom and the cleanest diff potential for clearly additive changes. <details> <summary>What changed</summary> **`update-gems` (63% → 99%)** - Expanded the frontmatter description with a `Use when...` clause and concrete trigger terms (`bundle update`, `Gemfile`, `outdated gems`, `bundler`, `dependency upgrade`) - Restructured the body into a numbered Workflow section (Audit → Update → Sync → Verify → Commit) for clearer sequencing - Added a verification step with error recovery guidance for dependency conflicts and lockfile sync failures - All existing Canvas-specific rules, gem groupings, and domain terminology preserved exactly as-is **`ketchup` (formatting fix only)** - Quoted the `argument-hint` value to fix YAML flow-collection parse error **`create-commit-msg` (formatting fix only)** - Changed `name: create_commit_msg` → `name: create-commit-msg` (kebab-case) </details> I also stress-tested your `squash-migrations` skill against a few real-world task evals and it held up really well on quarterly migration squashing with cross-plugin `InitCanvasDb` consolidation. 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
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 @instructure 👋
Canvas is one of those repos where you can tell the team is already thinking seriously about AI tooling. Seeing both CLAUDE.md and AGENTS.md alongside dedicated Claude Code Review workflows shows real commitment to that space. With 6.7k stars and the scale of this codebase, figured a well-structured SKILL.md could be a useful addition
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:The deep optimisation targeted
update-gems- it had the most improvement headroom and the cleanest diff potential for clearly additive changes.What changed
update-gems(63% → 99%)Use when...clause and concrete trigger terms (bundle update,Gemfile,outdated gems,bundler,dependency upgrade)ketchup(formatting fix only)argument-hintvalue to fix YAML flow-collection parse errorcreate-commit-msg(formatting fix only)name: create_commit_msg→name: create-commit-msg(kebab-case)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.