Skip to content

feat: improve skill scores for donna#71

Open
rohan-tessl wants to merge 1 commit intoTiendil:mainfrom
rohan-tessl:improve/skill-review-optimization
Open

feat: improve skill scores for donna#71
rohan-tessl wants to merge 1 commit intoTiendil:mainfrom
rohan-tessl:improve/skill-review-optimization

Conversation

@rohan-tessl
Copy link
Copy Markdown

@rohan-tessl rohan-tessl commented Apr 2, 2026

Hey @mahlernim 👋

I ran your skills through tessl skill review at work and found some targeted improvements.

image

Here's the full before/after:

Skill Before After Change
aptner-visitor-reservation 83% 100% +17%
Changes summary
  • Added workflow summary — clear 4-step sequence (Authenticate → Check existing → Create/Delete → Verify) at the top for quick orientation
  • Progressive disclosure — moved the full raw HTTP API reference to references/raw-api.md, keeping the main SKILL.md focused on the Python client which is more actionable for agents
  • Error handling in recurring example — added try/except with automatic re-authentication on token expiry mid-batch and graceful error reporting
  • Structured error table — replaced the bullet-point error list with a table showing error, cause, and recovery action
  • Frontmatter description — converted from chevron (|) to quoted string format for better compatibility
  • Removed redundancy — eliminated duplicate API documentation between raw HTTP and Python client sections

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 and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags.

Thanks in advance 🙏

Hey @Tiendil 👋

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 |
|-------|--------|-------|--------|
| donna-do | 59% | 84% | +25% |
| donna-start | 49% | 90% | +41% |
| donna-stop | 52% | 96% | +44% |

All 3 skills in the repo were improved — no scope cap needed since there are only 3.

Changes are applied to both `donna/fixtures/skills/` (the source of truth) and
`.agents/skills/` (the installed copies) to keep them in sync.

donna-do: Expanded description with FSM-driven workflow specifics, restructured
body with Workflow/Error handling/Context recovery sections, added workflow
discovery guidance.

donna-start: Rewrote description with concrete orchestration capabilities, added
section headings, workflow discovery step, and error handling.

donna-stop: Added natural trigger terms, concrete behavioral guidance for when
Donna is stopped, cross-referenced related skills for resumption.
@rohan-tessl rohan-tessl marked this pull request as ready for review April 2, 2026 07:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant