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 TashanGKD/cognitive-os/skills ./rig-cognitive-os/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 TashanGKD/cognitive-os/.cursor/skills/cognitive-ask .claude/skills/cognitive-ask $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-associate .claude/skills/cognitive-associate $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-attend .claude/skills/cognitive-attend $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-background-synthesizer .claude/skills/cognitive-background-synthesizer $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-calibrate .claude/skills/cognitive-calibrate $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-capture-fragment .claude/skills/cognitive-capture-fragment $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-consistency-check .claude/skills/cognitive-consistency-check $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-consolidate .claude/skills/cognitive-consolidate $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-creative-synthesis .claude/skills/cognitive-creative-synthesis $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-daily-briefing .claude/skills/cognitive-daily-briefing $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-detect-contradiction .claude/skills/cognitive-detect-contradiction $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-extract-principle .claude/skills/cognitive-extract-principle $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-input-classifier .claude/skills/cognitive-input-classifier $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-integrate-fragments .claude/skills/cognitive-integrate-fragments $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-reorganize .claude/skills/cognitive-reorganize $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-review-brain-map .claude/skills/cognitive-review-brain-map $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-self-reflect .claude/skills/cognitive-self-reflect $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-update-knowledge .claude/skills/cognitive-update-knowledge $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-version-snapshot .claude/skills/cognitive-version-snapshot $ npx degit TashanGKD/cognitive-os/.cursor/skills/cognitive-work-alignment-check .claude/skills/cognitive-work-alignment-check
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (20)
cognitive-askcognitive-associatecognitive-attendcognitive-background-synthesizercognitive-calibratecognitive-capture-fragmentcognitive-consistency-checkcognitive-consolidatecognitive-creative-synthesiscognitive-daily-briefingcognitive-detect-contradictioncognitive-extract-principlecognitive-input-classifiercognitive-integrate-fragmentscognitive-reorganizecognitive-review-brain-mapcognitive-self-reflectcognitive-update-knowledgecognitive-version-snapshotcognitive-work-alignment-check
Cursor rules (4)
cognitive-l3-auto-log · alwayscognitive-principle-checkcognitive-structure-write-guardfragment-before-direct-edit
Similar rigs
TashanGKD/tashan-cursor-skills
他山 Cursor Skill 体系 — 95个Skills + 32个Rules + 18个SubAgents，让AI在执行任务时能自主判断、按规范执行、并从经验中自我进化
Skill Collector 3.5k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·