feat: improve token efficiency for grove-create skill#6307
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @cbullinger 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for `grove-create`. It already scores really well (93%) — these changes focus on trimming token footprint by 13% (292 → 255 lines) while keeping the same quality score. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | grove-create | 93% | 93% | 0 (13% fewer tokens) | The other skills in the repo score well too — here are the baselines for context: | Skill | Score | |-------|-------| | grove-migrate | 94% | | grove-maintain | 90% | | grove-setup | 90% | | grove-test | 86% | | grove-run | 83% | | add-redirects | 90% | | jira | 90% | | mongosh-release-notes | 90% | | open-pr | 90% | | review-skill | 88% | | staging-preview | 85% | | unified-toc | 85% | | triage | 80% | | mcp-release-notes | 80% | | language-tabs-to-composable-scripted | 77% | | compass-release-notes | 74% | | drivers-ticket-assistant | 74% | | style-guide | 68% | | release-notes-base | 67% | <details> <summary>Changes made</summary> **Token efficiency improvements (main focus):** - Condensed Step 2 language confirmation — removed verbose example prompt while keeping the explicit user-confirmation gate - Condensed Step 5 data strategy — replaced block-quoted prompt template with a compact bullet list covering the same decision criteria - Removed inline Bluehawk Key Principles section — this content is already covered in the bundled `references/bluehawk-tags.md` file - Shortened Step 3 convention file reference — the `{language}` pattern is self-explanatory without enumerating all six filenames - Tightened Mongosh and C# EF Core notes in Step 2 — routing logic is already detailed in Step 1, so Step 2 just points to the convention files **Frontmatter fix:** - Changed description from YAML block scalar (`>`) to quoted string format for more portable frontmatter </details> I also stress-tested your `grove-create` skill against a few real-world task evals and it held up really well on Mongosh vs JavaScript routing disambiguation — the explicit trigger keyword matching (`db.collection.find()` vs `MongoClient`) keeps it from guessing wrong on ambiguous requests. 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 @cbullinger 👋
ran your skills through
tessl skill reviewat work and found some targeted improvements forgrove-create. It already scores really well (93%). These changes focus on trimming token footprint by 13% (292 → 255 lines) while keeping the same quality score. Here's the before/after:Some of the other skills in the repo score well too.
Changes made
Token efficiency improvements (main focus):
references/bluehawk-tags.mdfile{language}pattern is self-explanatory without enumerating all six filenamesFrontmatter fix:
>) to quoted string format for more portable frontmatteralso stress-tested your
grove-createskill against a few real-world task evals and it held up really well on Mongosh vs JavaScript routing disambiguation. The explicit trigger keyword matching (db.collection.find()vsMongoClient) keeps it from guessing wrong on ambiguous requests. Kudos for that.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.