Neeeophytee/finding-unknowns-skills
14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression evidence.
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 Neeeophytee/finding-unknowns-skills/skills ./rig-finding-unknowns-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 Neeeophytee/finding-unknowns-skills/skills/agent-interface-design .claude/skills/agent-interface-design $ npx degit Neeeophytee/finding-unknowns-skills/skills/assumption-test .claude/skills/assumption-test $ npx degit Neeeophytee/finding-unknowns-skills/skills/blindspot-pass .claude/skills/blindspot-pass $ npx degit Neeeophytee/finding-unknowns-skills/skills/brainstorm-prototypes .claude/skills/brainstorm-prototypes $ npx degit Neeeophytee/finding-unknowns-skills/skills/change-quiz .claude/skills/change-quiz $ npx degit Neeeophytee/finding-unknowns-skills/skills/context-audit .claude/skills/context-audit $ npx degit Neeeophytee/finding-unknowns-skills/skills/implementation-notes .claude/skills/implementation-notes $ npx degit Neeeophytee/finding-unknowns-skills/skills/implementation-plan .claude/skills/implementation-plan $ npx degit Neeeophytee/finding-unknowns-skills/skills/interview-me .claude/skills/interview-me $ npx degit Neeeophytee/finding-unknowns-skills/skills/pitch-packager .claude/skills/pitch-packager $ npx degit Neeeophytee/finding-unknowns-skills/skills/progressive-disclosure .claude/skills/progressive-disclosure $ npx degit Neeeophytee/finding-unknowns-skills/skills/reference-hunt .claude/skills/reference-hunt $ npx degit Neeeophytee/finding-unknowns-skills/skills/regression-proof .claude/skills/regression-proof $ npx degit Neeeophytee/finding-unknowns-skills/skills/test-blindspots .claude/skills/test-blindspots
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 (14)
Similar rigs
x24ken/claude-config
Claude Code user-level config (~/.claude): settings, skills, hooks
Pragmatist 209 tok ·
talhayme/claude-plugins
Claude Code plugins built around one idea: AI tooling should be measurable
Minimalist 257 tok ·
weellio/gander
Live NOC dashboard + control center for AI coding agents: pixel-art office floor, phone/Telegram/Slack alerts, cost guardrails, task queue with worktrees + test gate. Designed for Claude Code — other agent CLIs (Codex, Gemini, Grok, aider)
Pragmatist 2.2k tok ·
HourglassDigital/hgstack
The Claude Code stack we use to run an AI-native company. Skills, hooks, rules, and statuslines from 18 months of daily use at Hourglass. Conflict-aware installer never stomps your existing setup.
Pragmatist 821 tok ·