feat: improve warehouse-init skill score (65% → 90%)#216
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @kaxil 👋 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 | |-------|--------|-------|--------| | warehouse-init | 65% | 90% | **+25%** | | airflow | 94% | 94% | — | | managing-astro-local-env | 95% | 95% | — | | airflow-hitl | 97% | 97% | — | | delegating-to-otto | 94% | 94% | — | | analyzing-data | 92% | 92% | — | | setting-up-astro-project | 90% | 90% | — | | migrating-ai-sdk-to-common-ai | 90% | 90% | — | | dag-factory | 90% | 90% | — | | blueprint | 90% | 90% | — | | airflow-plugins | 90% | 90% | — | _(Showing top 11 of 25 skills reviewed — remaining 14 skills scored 78–86% with no changes.)_ <details> <summary>Changes made to <code>warehouse-init</code></summary> - **Expanded description** with natural trigger terms (`explore their database`, `list all tables`, `scan schema`, `what tables are available`, `check what data exists`) — improves skill selection accuracy - **Replaced pseudocode Task() calls** in Steps 2–3 with clear agent instructions and executable CLI commands — the original subagent invocation syntax was illustrative, not actionable - **Added validation checkpoints** after Steps 3, 5, and 6 (verify discovery results, confirm merged output, read back generated file) — these were missing from the original workflow - **Removed verbose sections** that inflated token count without proportional value: full example session (~38 lines), codebase patterns table, stale cache signs, redundant output format template - **Condensed Step 8** (CLAUDE.md integration) from ~20 lines to a focused 2-line instruction - **Tightened Refresh Behavior** into a single paragraph instead of a 6-item numbered list </details> I also stress-tested your `analyzing-data` skill against a few real-world task evals and it held up really well on multi-table JOIN queries with concept→table cache lookups. 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 @kaxil, just resurfacing this in case it slipped by, let me know if any changes are needed! |
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 @kaxil 👋
cool stuff truly. 26 skills and counting, from authoring DAGs to migrating Airflow 2 to 3. The breadth here is impressive, and pairing that with the MCP server for Astro Airflow makes this feel like a complete toolkit, not just a collection.
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the before/after:Changes made to
warehouse-initexplore their database,list all tables,scan schema,what tables are available,check what data exists) - improves skill selection accuracyalso stress-tested your
warehouse-initskill against a few real-world task evals and it held up really well on multi-table JOIN queries with concept→table cache lookups. 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.