ehnruiz/claude-skills
Claude Code skills, subagents and hooks for an agent that proves its work.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit ehnruiz/claude-skills/agents ./rig-claude-skills/agents $ npx degit ehnruiz/claude-skills/skills ./rig-claude-skills/skills $ npx degit ehnruiz/claude-skills/hooks ./rig-claude-skills/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit ehnruiz/claude-skills/skills/confluence-jira-links .claude/skills/confluence-jira-links $ npx degit ehnruiz/claude-skills/skills/diagnosing-bugs .claude/skills/diagnosing-bugs $ npx degit ehnruiz/claude-skills/skills/epic-review .claude/skills/epic-review $ npx degit ehnruiz/claude-skills/skills/explain-the-number .claude/skills/explain-the-number $ npx degit ehnruiz/claude-skills/skills/grilling .claude/skills/grilling $ npx degit ehnruiz/claude-skills/skills/handoff .claude/skills/handoff $ npx degit ehnruiz/claude-skills/skills/leader-1-1-prep .claude/skills/leader-1-1-prep $ npx degit ehnruiz/claude-skills/skills/llm-integration .claude/skills/llm-integration $ npx degit ehnruiz/claude-skills/skills/no-ai-attribution .claude/skills/no-ai-attribution $ npx degit ehnruiz/claude-skills/skills/open-in-my-browser .claude/skills/open-in-my-browser $ npx degit ehnruiz/claude-skills/skills/pick-up .claude/skills/pick-up $ npx degit ehnruiz/claude-skills/skills/plain-writing .claude/skills/plain-writing $ npx degit ehnruiz/claude-skills/skills/regression-proof .claude/skills/regression-proof $ npx degit ehnruiz/claude-skills/skills/research .claude/skills/research $ npx degit ehnruiz/claude-skills/skills/retro .claude/skills/retro $ npx degit ehnruiz/claude-skills/skills/security-audit-runner .claude/skills/security-audit-runner $ npx degit ehnruiz/claude-skills/skills/skill-collision-audit .claude/skills/skill-collision-audit $ npx degit ehnruiz/claude-skills/skills/supervisor .claude/skills/supervisor $ npx degit ehnruiz/claude-skills/skills/tdd .claude/skills/tdd $ npx degit ehnruiz/claude-skills/skills/ticket-digest .claude/skills/ticket-digest $ npx degit ehnruiz/claude-skills/skills/ticket-trim .claude/skills/ticket-trim $ npx degit ehnruiz/claude-skills/skills/ticket-write .claude/skills/ticket-write $ npx degit ehnruiz/claude-skills/skills/writing-for-agents .claude/skills/writing-for-agents
$ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/ehnruiz/claude-skills/main/agents/tester.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (23)
confluence-jira-linksdiagnosing-bugsepic-reviewexplain-the-numbergrillinghandoffleader-1-1-prepllm-integrationno-ai-attributionopen-in-my-browserpick-upplain-writingregression-proofresearchretrosecurity-audit-runnerskill-collision-auditsupervisortddticket-digestticket-trimticket-writewriting-for-agents
Subagents (6)
| doc-writer model: haiku | Writes prose from facts it is given, on the cheapest model: a changelog entry, a README or docs section, a pull request description, a release note, a message draft. It does not investigate beyond the |
| implementer model: sonnet | Builds one scoped ticket test-first on a mid-tier model: a feature, a config option, a bug fix whose cause is known. Give it the ticket, where the change goes, the command that proves it and the files |
| researcher model: sonnet | Reads primary sources in the background on a mid-tier model and writes one cited Markdown note: a vendor's docs or API, a standard, a library's source, how a tool really behaves. Give it the question |
| reviewer model: opus | Reviews a diff on the strongest model along two axes, the ask and the repository's standards, and gives each finding file:line, a concrete failure scenario and a verdict (confirmed, needs_validation o |
| scout model: haiku | Read-only finder on the cheapest model. Use for "where is X", which files touch Y, the callers of a function, or a summary of a long file or log. Returns file:line pointers and short quotes, never who |
| tester model: sonnet | Writes and runs tests without touching production code, on a mid-tier model: a regression test for a reported bug, a missing negative case, a fixture fix, or a full suite run with exit codes. |
Similar rigs
Essential-kit/skills
Installable agent skills for planning, implementation, review, and code quality.
Skill Collector 1.6k tok · · Q0
Marco-Cricchio/moh
Your terminal, with a coding agent inside: reads your code, edits files, runs commands — with permission gates on every risky step.
Skill Collector 1.3k tok · · Q0
davner/dotfiles
My Macs as code: nix-darwin and home-manager for macOS settings, Homebrew, CLI tools and zsh, plus a Claude Code setup of skills, hooks and rules. One branch, keyed by macOS username.
Skill Collector 4.3k tok · · Q0
cjumeow/watch-less
Hover a YouTube thumbnail to get a neutral, evidence-backed summary in Heptabase
Skill Collector 3.6k tok · · Q18