improve jarvis-identity skill clarity and structure

[fernandezbaptiste]

hey @epicrunze, really cool concept with JaRVIS - the idea of journaling as recurrent versioned identity sculpting is a creative approach to agent memory. kudos on the project! I've just starred it.

ran your jarvis-identity skill through agent evals and spotted a few quick wins that took it from ~86% to ~90% performance:

• rewrote the description to list concrete actions (update personality traits, expertise claims, working principles, tool mastery) instead of the generic "evolve identity" phrasing, which helps agent routing pick the right skill

• converted the Step 2 evaluation questions from rhetorical prose into a compact checklist format, making each dimension scannable and directly actionable

• removed the flavor text opener ("Time to sculpt your identity based on what you've learned") that added no actionable value and consumed tokens

these were easy changes to bring the skill in line with what performs well against Anthropic's best practices. honest disclosure, I work at tessl.io where we build tooling around this. not a pitch, just fixes that were straightforward to make.

if you want to review your other skills, two options: I can open a follow-up PR with a GitHub Action that auto-scores skill.md changes on every PR (no signup, no token needed). or if you'd rather do it yourself, spin up Claude Code and run tessl skill review.

happy to answer any questions on the changes.