Skip to content

mgiovani/ai-arsenal / skills/create-skill

create-skill

Verified

Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent capability, or slash command, including phrasings like 'make a command for X', 'create a slash command', 'turn this into a reusable skill', or 'package this workflow as a skill'. Not for editing CLAUDE.md/AGENTS.md memory rules (use create-rule) or discovering/installing existing third-party skills (use find-skills).

evals/trigger-eval.json

View on GitHub
[
  {"query": "create a new skill that generates changelog entries from git commits", "should_trigger": true},
  {"query": "make a command for me that scaffolds a new React component", "should_trigger": true},
  {"query": "turn this workflow I just described into a reusable skill", "should_trigger": true},
  {"query": "can you build a slash command that runs our lint + test suite", "should_trigger": true},
  {"query": "I want an agent capability that posts standup summaries to Slack, can you make one", "should_trigger": true},
  {"query": "package this deploy process as a skill so the team can reuse it", "should_trigger": true},
  {"query": "help me author a new SKILL.md for validating OpenAPI specs", "should_trigger": true},
  {"query": "create a subagent skill that drafts release notes from merged PRs", "should_trigger": true},
  {"query": "I keep repeating these steps manually, can you make them a slash command", "should_trigger": true},
  {"query": "write a new skill from scratch for auditing Dockerfiles", "should_trigger": true},
  {"query": "add a rule to CLAUDE.md saying we always use conventional commits", "should_trigger": false},
  {"query": "add a project instruction that agents should never touch the migrations folder", "should_trigger": false},
  {"query": "is there an existing skill on skills.sh for Terraform linting I could install", "should_trigger": false},
  {"query": "find a skill that already does Jira standup reports", "should_trigger": false},
  {"query": "search for a third-party skill that handles Kubernetes manifests", "should_trigger": false},
  {"query": "implement a rate limiter for the /api/upload endpoint", "should_trigger": false},
  {"query": "fix the bug where the CSV export downloads an empty file", "should_trigger": false},
  {"query": "review this PR for security issues before we merge", "should_trigger": false},
  {"query": "write a conventional commit message for these staged changes", "should_trigger": false},
  {"query": "generate an architecture decision record for switching to Postgres", "should_trigger": false},
  {"query": "run the visual regression diff and tell me if anything broke", "should_trigger": false},
  {"query": "add a personal coding-style rule about never using default exports", "should_trigger": false}
]
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall