feat: improve carta-portfolio-alerts skill score (17% → 96%)#43
Open
yogesh-tessl wants to merge 1 commit into
Open
feat: improve carta-portfolio-alerts skill score (17% → 96%)#43yogesh-tessl wants to merge 1 commit into
yogesh-tessl wants to merge 1 commit into
Conversation
Hey @vijayCarta 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for `carta-portfolio-alerts`. Here's the before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | carta-portfolio-alerts | 17% | 96% | +79% | The 17% baseline was caused by `allowed-tools` using a YAML array instead of a quoted string — this blocked the evaluation judge entirely across all your skills. I fixed it on this one skill so the judge could actually score the content, then tightened up the description and body. <details> <summary>Changes made</summary> - **Fixed `allowed-tools` format** — converted from YAML array to a quoted comma-separated string, which is the format the skill spec expects. This was the main blocker keeping all skills at 17%. - **Enriched description with trigger terms and "Use when..." clause** — added natural phrases like "expiring", "note maturities", "low option pool alerts", "SAFE exposure warnings", "portfolio health audit", "red-flag scan", "deadlines", "renewals approaching". Also added explicit skill differentiation pointing to `carta-portfolio-query` and `carta-market-benchmarks` for non-risk queries. - **Folded `when_to_use` into description** — removed the non-standard frontmatter key (was flagged as unknown) and integrated its content into the standard `description` field. - **Consolidated redundant sections** — merged Per-Company Commands, Key Fields, and Workflow Step 2 into a single section. The fetch commands, their key response fields, and the parallel execution guidance now live in one place instead of three. - **Compacted severity threshold tables** — merged four separate single-row tables into one unified table and removed the Rationale columns (the thresholds speak for themselves). - **Trimmed intro** — removed the HTML comment and "Builds on the carta-portfolio-query pattern" line that didn't add actionable guidance. </details> I also stress-tested your `carta-portfolio-alerts` skill against a few real-world task evals and it held up really well on cross-portfolio 409A expiry scans with mixed severity classifications. 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 @vijayCarta 👋
ran your skills through
tessl skill reviewat work and found some targeted improvements forcarta-portfolio-alerts. Here's the before/after:The 17% baseline was caused by
allowed-toolsusing a YAML array instead of a quoted string. This blocked the evaluation judge entirely across all your skills. I fixed it on this one skill so the judge could actually score the content, then tightened up the description and body.Changes made
allowed-toolsformat - converted from YAML array to a quoted comma-separated string, which is the format the skill spec expects. This was the main blocker keeping all skills at 17%.carta-portfolio-queryandcarta-market-benchmarksfor non-risk queries.when_to_useinto description - removed the non-standard frontmatter key (was flagged as unknown) and integrated its content into the standarddescriptionfield.also stress-tested your
carta-portfolio-alertsskill against a few real-world task evals and it held up really well on cross-portfolio 409A expiry scans with mixed severity classifications. 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.