feat: improve skill review scores for 5 skills (+73% avg)

[rohan-tessl]

Hey @robertohluna 👋

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
brainstorm	10%	93%	+83%
build	10%	85%	+75%
harden	10%	84%	+74%
batch	10%	79%	+69%
write	10%	75%	+65%

This PR covers 5 of the 114 skill(s) in the repo. These five were the lowest-scoring — all at 10% due to missing YAML frontmatter — selected from across different categories (development, strategy, workflow, content, security) for maximum variety. The included GitHub Action covers ongoing review for the remaining skills on future PRs.

What changed in brainstorm

• Added YAML frontmatter with name, description (quoted string with "Use when..." clause), user-invocable: true, and triggers array
• Description rewritten with concrete action verbs and explicit use case guidance
• Added Arguments table for structured flag documentation
• Added Output section with a realistic worked example showing the full recommendation format
• Renamed sections from "Implementation" to "Workflow" for consistency with higher-scoring skills

What changed in build

• Added YAML frontmatter with name, description, user-invocable: true, and triggers array
• Description rewritten with concrete action verbs, toolchain detection details, and "Use when..." clause
• Added Arguments table documenting flags (--clean, --verbose, --target)
• Added Output section with structured build report example showing error diagnostics and suggested fixes
• Renamed "Implementation" to "Workflow" for consistency

What changed in harden

• Added YAML frontmatter with name, description, user-invocable: true, and triggers array
• Description rewritten listing specific hardening measures (HSTS, CSP, CVE updates) with "Use when..." clause
• Expanded Workflow with concrete tool references (mix audit, npm audit, cargo audit, pip-audit) for each assessment domain
• Added verification feedback loop — re-run audit commands after applying changes
• Added Output section with before/after comparison table

What changed in batch

• Added YAML frontmatter with name, description, user-invocable: true, and triggers array
• Description rewritten with token savings claim, coordination model, and "Use when..." clause
• Added Arguments table for --max-agents and --batch-size flags
• Added Output section with batch execution summary showing agent assignments and token savings
• Renamed "Implementation" to "Workflow" for consistency

What changed in write

• Added YAML frontmatter with name, description, user-invocable: true, and triggers array
• Description rewritten covering Signal Theory framework, all 13 supported genres, and "Use when..." clause
• Added Arguments table for --for, --topic, --tone flags
• Expanded Workflow with inline genre skeleton definitions (brief, spec, plan, pitch, email, report, ADR)
• Defined the 6 encoding principles referenced in validation step with actionable one-line checks
• Added receiver fallback — asks user for preferences when person not found in registry
• Added Output section with a realistic brief example

Tessl Skill Review GitHub Action ✅

I've also included a GitHub Action (.github/workflows/skill-review.yml) that automatically reviews any SKILL.md changed in future PRs and posts scores as a PR comment.

What this gives you:

• 🔍 Automatic tessl skill review runs on every PR touching SKILL.md
• 💬 One updated PR comment with scores and improvement feedback
• 🔓 Zero extra accounts — contributors don't need a Tessl login; only GITHUB_TOKEN is used
• ✅ Non-blocking by default — feedback-only, no surprise red CI (add fail-threshold: 70 later if you want a hard gate)
• 📈 Covers future skills incrementally as contributors edit them

Note: Your CONTRIBUTING.md asks that new CI workflows start with a Discussion first — totally understand if you'd prefer to split the workflow into a separate PR or discussion. Happy to do that.

Want automatic AI optimization on every SKILL.md change? 🚀

The action I've added gives you review scores on PRs. We also have a more powerful variant — tesslio/skill-review-and-optimize — that can:

• Run AI-powered optimization suggestions on every SKILL.md PR (requires adding TESSL_API_TOKEN as a repo secret)
• Let contributors accept suggested improvements by commenting /apply-optimize
• Still works in review-only mode with zero secrets

Interested? Tick the box and I'll raise a follow-up PR:

• Yes please! Add the tesslio/skill-review-and-optimize action so every SKILL.md PR gets AI optimization suggestions + the /apply-optimize flow
• No thanks — the review scores action is enough for now

---

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 🙏