From ai-permission-hook
This skill should be used when the user asks to "clear permission cache", "reset permission hook cache", "clear cached decisions", "permission hook inconsistent behavior", or needs to wipe cached LLM permission decisions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-permission-hook:clear-cacheThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Clear the cached LLM permission decisions stored at `~/.claude/permission-hook/cache/approval_cache.json`.
Clear the cached LLM permission decisions stored at ~/.claude/permission-hook/cache/approval_cache.json.
Read ~/.claude/permission-hook/cache/approval_cache.json and report:
Write an empty object {} to the cache file.
Report how many entries were cleared. Note that pattern-matched instant decisions (fast allow and deny) are unaffected — only cached LLM evaluations are cleared, forcing fresh LLM queries for ambiguous commands.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub thenemal/thenemal-cc-marketplace --plugin ai-permission-hook