
Jump to queryKey hook
React Native device QA
Expand TS aliases to shapes
Find unfinished code litter
Pursue a single strongly-desired objective autonomously to verifiable completion. Auto-derives 3-5 verifiable success criteria, suppresses sub-skill interruptions (auto-selects recommended options), logs concerns to GitHub/Linear/file instead of blocking on the user, and runs an adversarial review gate before declaring achievement. Use when the user invokes `/goal <objective>`, `/goal clear`, `/goal` (no args), or describes wanting Codex-style `/goal` pursuit-mode behavior.
Hypothesis-driven root-cause fix
--- name: strip-skill-descriptions description: --- # Strip Skill Descriptions Empty the `description:` field of every `SKILL.md` under `~/.claude/skills/` to reclaim always-loaded preamble context. ## When to Invoke Trigger when ALL of these signals are present: 1. User reports skill descriptions consuming meaningful preamble context (e.g. `/context` shows Skills using >5% of the window). 2. User explicitly authorizes deletion (e.g. "全削除", "set to 0 chars", "strip them all"). 3. User confi
macOS app stack
Five-phase implementation workflow
Chrome cookies to Playwright
React core deep-dive JP
Git worktree with env copy
Build Claude Code hooks
Architecture plan architect
Deep code explainer
Publish skill to registry
Load session from memory
Save session to memory
Research before coding
Next.js component tree
Vague idea to approved plan
Codex context breakdown
Create or list tracker issues
iOS Simulator QA
Casual lunch chat
Interactive code mentor
Electron black-box QA
CLI black-box QA
Multi-tool cited research
Cited research briefs
Daily coding habit prompts JP
Terminal UI black-box QA
Sync Pencil pen and code
Copy last agent reply
Inspect skill ecosystem
Review diff for quality
Top-app UI inspiration
CodeRabbit PR loop
Trace code flow
Bulk issue fix
GIF analyzer
Exhaustive browser scenario QA
Deep newsletter summary
Multi-agent parallel review
EN practice
Screenshot UI defect lint
Line-by-line diff trace
Vague idea via search to plan
Electron release ship
Coordinate drag-drop QA
Brand TS types
Pursue a single strongly-desired objective autonomously to verifiable completion. Auto-derives 3-5 verifiable success criteria, suppresses sub-skill interruptions (auto-selects recommended options), logs concerns to GitHub/Linear/file instead of blocking on the user, and runs an adversarial review gate before declaring achievement. Use when the user invokes `/auto <objective>`, `/auto clear`, `/auto` (no args), or describes wanting Codex-style `/goal` pursuit-mode behavior.
Smart git operations
Deep JS hacker news JP
Code to screen capture
Trace React prop drilling
Parallel QA agent team
SaaS UX gap audit
Refactor branches to ts-pattern
Debug Claude Code plugins
Sync docs and memory
Secure pnpm GitHub Actions CI
Reveal agent system prompt