Loading...
Loading...
Found 831 Skills
设置 Claude Code hooks，在危险 git commands（push, reset --hard, clean, branch -D 等）执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Surfaces social-layer signals for crypto markets. Three capability groups: news (latest aggregated crypto news feed, filter articles by coin symbol, run full-text keyword searches, fetch a single article in full, and list available upstream platforms — blockbeats, odaily, theblock and similar — for use as filters); sentiment (rank coins by social mention volume over 1h / 4h / 24h, plus per-coin bullish/bearish/neutral counts with an optional time-bucketed trend); vibe (per-contract hotness score over 24h / 72h / 7d / 30d with timeline and sample KOLs per bucket, plus a TOP50 KOL leaderboard sortable by engagement, mentions, or impressions). Triggers: 'latest crypto news', 'BTC headlines', 'search news for X', 'is BTC bullish', 'hottest coins by chatter', 'who is tweeting about <token>', 'vibe score', 'first-mention KOL', and Chinese variants like '最新加密新闻', '搜索新闻', '市场情绪', '情绪排行', 'KOL榜', '热度走势'. Also handles x402/402 payment, quota, MARKET_API_*_OVER_QUOTA, and confirming:true notifications on social endpoints.
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
One book → a clear "Viewfinder" → a 2050 Library Borrow Card (PNG). The card includes the real book cover, author's avatar, and book information; the Viewfinder block fully, fluently, and clearly expresses the book's unique "way of seeing the world". The illustration block uses a hand-drawn explanatory style with white background and black ink, featuring the ink portrait of Ji Gang himself (created by cutting out his avatar), turning this set of ideas into a vivid, easily understandable scene. Light optical glass style, the card's accent color is dynamically extracted from the book cover, with adaptive width and height. Remember this "pair of eyes" after closing the book, and your reading won't be in vain. Use when user says '取景框卡', '图书馆卡', 'library card', '书卡', '铸书卡', '一本书一句话一张卡', '/ljg-library', or provides a book name and wants it distilled into one collectible card. NOT FOR book structure analysis (use ljg-book), pure text golden quotes (use ljg-card -b), infographics (use ljg-card -i), visual notes (use ljg-card -v).
Techniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer progress.
Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.
Convert Markdown documents into professional PDF whitepapers with Apple design style. Supports full Markdown syntax (code blocks, tables, blockquotes, lists, etc.). Automatically generates cover pages, table of contents, headers and footers. Use cases: Technical documents, whitepapers, tutorials, reports and other Markdown documents that require professional typesetting.
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
Template-based AI prompt engine with YAML templates, brand kit injection, input sanitization for security, and token-efficient context blocks.
Implement robust background job processing with dead letter queues, retries, and state machines. Use when building async workflows, scheduled tasks, or any work that shouldn't block the request/response cycle.
Execute written implementation plans: first read and critically review the plan, then implement in small batches (default 3 tasks), produce verification evidence per batch and pause for feedback; must stop immediately and ask for help when blocked/tests fail/plan unclear. Trigger words: execute plan, implement plan, batch execution, follow the plan.