jonhill90/skills
Portable Agent Skills for consistent workflows across coding harnesses.
field: Developer tools workflow: Planning & specsPR / code reviewTesting & TDDDocsFrontend & design runs claude in CI
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit jonhill90/skills/skills ./rig-skills/skills 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 jonhill90/skills/skills/adopt-or-build .claude/skills/adopt-or-build $ npx degit jonhill90/skills/skills/ask-a-council .claude/skills/ask-a-council $ npx degit jonhill90/skills/skills/close-the-loop .claude/skills/close-the-loop $ npx degit jonhill90/skills/skills/create-skill .claude/skills/create-skill $ npx degit jonhill90/skills/skills/decide-by-variant .claude/skills/decide-by-variant $ npx degit jonhill90/skills/skills/derive-independently-then-compare .claude/skills/derive-independently-then-compare $ npx degit jonhill90/skills/skills/determine-intent .claude/skills/determine-intent $ npx degit jonhill90/skills/skills/determine-signals .claude/skills/determine-signals $ npx degit jonhill90/skills/skills/devils-advocate .claude/skills/devils-advocate $ npx degit jonhill90/skills/skills/dispatch-brief .claude/skills/dispatch-brief $ npx degit jonhill90/skills/skills/dispatching-subagents .claude/skills/dispatching-subagents $ npx degit jonhill90/skills/skills/distill .claude/skills/distill $ npx degit jonhill90/skills/skills/durable-fact-before-label .claude/skills/durable-fact-before-label $ npx degit jonhill90/skills/skills/failing-test-first .claude/skills/failing-test-first $ npx degit jonhill90/skills/skills/github-cli .claude/skills/github-cli $ npx degit jonhill90/skills/skills/keep-me-honest .claude/skills/keep-me-honest $ npx degit jonhill90/skills/skills/linear .claude/skills/linear $ npx degit jonhill90/skills/skills/loop-contract .claude/skills/loop-contract $ npx degit jonhill90/skills/skills/loop-memory .claude/skills/loop-memory $ npx degit jonhill90/skills/skills/mechanize .claude/skills/mechanize $ npx degit jonhill90/skills/skills/memory-conventions .claude/skills/memory-conventions $ npx degit jonhill90/skills/skills/mine-transcripts .claude/skills/mine-transcripts $ npx degit jonhill90/skills/skills/notify .claude/skills/notify $ npx degit jonhill90/skills/skills/obsidian .claude/skills/obsidian $ npx degit jonhill90/skills/skills/organize-repository .claude/skills/organize-repository $ npx degit jonhill90/skills/skills/plan-parallel-execution .claude/skills/plan-parallel-execution $ npx degit jonhill90/skills/skills/prd .claude/skills/prd $ npx degit jonhill90/skills/skills/primer .claude/skills/primer $ npx degit jonhill90/skills/skills/progressive-disclosure .claude/skills/progressive-disclosure $ npx degit jonhill90/skills/skills/prompt-corpus .claude/skills/prompt-corpus $ npx degit jonhill90/skills/skills/refuse-invented-identity .claude/skills/refuse-invented-identity $ npx degit jonhill90/skills/skills/research-the-limit .claude/skills/research-the-limit $ npx degit jonhill90/skills/skills/safe-deletion .claude/skills/safe-deletion $ npx degit jonhill90/skills/skills/sanity-check .claude/skills/sanity-check $ npx degit jonhill90/skills/skills/spec-driven-development .claude/skills/spec-driven-development $ npx degit jonhill90/skills/skills/spec .claude/skills/spec $ npx degit jonhill90/skills/skills/supervised-lane-loop .claude/skills/supervised-lane-loop $ npx degit jonhill90/skills/skills/tdd .claude/skills/tdd $ npx degit jonhill90/skills/skills/test-in-the-consumer-context .claude/skills/test-in-the-consumer-context $ npx degit jonhill90/skills/skills/tmux .claude/skills/tmux
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 (42)
adopt-or-buildask-a-councilclose-the-loopcreate-skilldecide-by-variantderive-independently-then-comparedetermine-intentdetermine-signalsdevils-advocatedispatch-briefdispatching-subagentsdistilldurable-fact-before-labelfailing-test-firstgithub-clikeep-me-honestlinearloop-contractloop-memorymechanizememory-conventionsmine-transcriptsnotifyobsidianorganize-repositoryplan-parallel-executionprdprimerprogressive-disclosureprompt-corpusrefuse-invented-identityresearch-the-limitsafe-deletionsanity-checkspec-driven-developmentspecsupervised-lane-looptddtest-in-the-consumer-contexttmuxverify-the-instrumentwire-it-when-you-write-it
Similar rigs
dnouri/ai-config
Skills and extensions for pi-coding-agent, Claude Code, Codex CLI
Pragmatist 2.4k tok · · Q0
HumanDealer/vibeproof
Vibe-code anything. Ship like a senior. A drop-in rulebook + skills that turn any AI coding agent (Codex, Claude Code, Cursor) into a disciplined senior engineer — built for domain experts who build with AI.
Pragmatist 2.0k tok · · Q8
kato-yoshiharu/dotfiles
—
Skill Collector 956 tok · · Q15
pg013c/pg-toolkit
My Claude Code toolkit: spec-first, test-first workflow as a plugin (skills, reviewer agent, hooks).
Skill Collector 1.5k tok · · Q3