CommunityKunst & Designgithub.com

coroboros/skillward

Take an agent skill apart before installing it — the complete deterministic scanner ensemble, fused into one offline verdict.

Funktioniert mit~Claude Code~Codex CLI~Cursor
npx skills add coroboros/skillward

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Dokumentation

skillward

Vets an untrusted agent skill — one folder, a directory of skills, or a remote https Git URL — by running the complete deterministic scanner ensemble offline and fusing the findings into one verdict. The CLI does the detection; this skill adds the one intelligent step: reading the report and saying what it means.

Install

The CLI is the engine. Install it once:

cargo binstall skillward     # prebuilt binary
brew install coroboros/tap/skillward
npx @coroboros/skillward     # Node toolchains

Then pull the scanner bundle (one-time, needs Docker):

skillward install

If skillward is not on PATH, stop and tell the user to install it with one of the commands above — do not improvise a scan. A hand-rolled check misses what the ensemble catches, so it would report a false all-clear.

Use

Run skillward --help for the full surface. The default scan, with a JSON report for triage:

skillward <target> --format json -o report.json

<target> is a skill folder, a directory of skills, or an https:// Git repo URL. Exit code 20 means findings reached the --fail-on threshold (default high); 0 means clean or below it.

Analyze

After the scan, read report.json and produce a triage — not a re-print of the findings:

  1. Lead with the verdict. PASS or FAIL, the worst severity, and whether findings are corroborated (multiple tools agreeing is high-confidence).
  2. Explain the real risk of the top findings in plain language — what an attacker gains, citing the specific file and rule (e.g. "exfiltrates AWS credentials on every invocation — setup.sh:7, flagged by skillspector and semgrep").
  3. Note any tool_errors — a scanner that did not run means the picture is incomplete; say so rather than implying all-clear.
  4. Make the call: install, don't-install, or remediate-then-reinstall. For remediate, name the exact change.

Keep it short and decision-oriented. The findings are in the report; the judgment is the work.

Verwandte Skills

vercel-labs/vercel-composition-patterns

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

community

AgriciDaniel/skill-forge

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

community

howardrock88/semcanvas-ai

Semantic AI image editing canvas with local Codex CLI, SAM/FastSAM segmentation, and pluggable image APIs.

community

wondelai/drive-motivation

Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isnt working", "team incentives", "autonomy", "mastery", "purpose-driven", "employee engagement", or "reward systems". Also trigger when designing onboarding progression systems, fixing broken gamification, or building team structures that sustain high performance. Covers why carrot-and-stick fails and how to build progress systems. For habit-forming product loops, see hooked-ux. For retention behavior design, see improve-retention.

community

gbechtold/Hi-Fidelity-Design

Claude Code skill: high-fidelity design↔implementation audits (numeric per-element deltas, not pixel-diff). Invariant core + swappable adapters (IDML/Figma/PDF/PNG ↔ DOM).

community

WellDunDun/skills

Small, composable Agent Skills for better agent feedback loops, design judgment, and verification habits.

community