feat: improve 5 lowest-scoring skill definitions#210
Open
rohan-tessl wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 @dhruv0811 👋
I ran your skills through
tessl skill reviewat work and found targeted improvements in your skills. Here's the before/after:These were easy changes to bring the skill's structure and activation in line with what performs well against Anthropic's best practices. Total line reduction: 1540 to 655 lines (~57% smaller) with all domain expertise preserved.
What changed in deploy
Removed duplicated Quick Deploy section (kept the step-by-step workflow), removed CI/CD Pipeline, Monitoring, Adding Resources, and Best Practices sections that belong in other skills or AGENTS.md. Condensed troubleshooting into a compact table. 436 to 105 lines.
What changed in lakebase-setup
Removed both full
databricks.ymlexamples that duplicated the step-by-step snippets, removed overlapping Use Cases/Overview sections, removed the LakebaseClient API reference and Service Principal identifiers sections. Kept the 7-step workflow with compact YAML snippets. 467 to 196 lines.What changed in agent-openai-memory
Removed "How Sessions Work" and "Key Concepts" sections Claude already knows. Added a Lakebase connectivity verification checkpoint before testing. 176 to 127 lines.
What changed in long-running-server
Deduplicated two near-identical SDK code blocks into a single block with inline comments for SDK differences. Added verification checkpoints. Trimmed start_server.py to show only key changes. 343 to 145 lines.
What changed in quickstart
Removed template placeholder noise, removed verbose "What Quickstart Configures" section, added "Verify Setup" with concrete auth and .env validation commands. 118 to 82 lines.
In addition, I stress-tested your
lakebase-setupskill against a few real-world scenarios, and it held up really well. This means that your skill meaningfully improves agent steering and contributes to stronger output quality. 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.
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 @rohan-tessl, if you hit any snags.