Loading...
Loading...
Found 3,748 Skills
Advanced memory operations reference. Basic patterns (profile loading, simple recall/remember) are in project instructions. Consult this skill for background writes, memory versioning, complex queries, edge cases, session scoping, retention management, type-safe results, proactive memory hints, GitHub access detection, and ops priority ordering.
Verify, download, and inspect build provenance attestations using the orbit CLI. Use this skill whenever the user asks about verifying attestations, checking provenance, inspecting Sigstore bundles, SLSA provenance, build provenance, verifying binaries, downloading attestation bundles, signer identity, in-toto attestations, or supply chain security. Trigger on phrases like 'verify attestation', 'check provenance', 'inspect bundle', 'build provenance', 'sigstore', 'SLSA', 'verify binary', 'attestation download', 'download bundle', 'check signer', 'inspect attestation', 'provenance verification', 'verify artifact', 'supply chain verification', 'check build origin', or any attestation-related task — even casual references like 'is this binary legit', 'who built this', 'where did this artifact come from', 'check the bundle', or 'show provenance'. The orbit CLI alias for attestation is `attest`.
Long-form writing skill for WeChat Official Account from Digital Life Khazix. It is used when users need to write WeChat Official Account articles, draft manuscripts, continue writing articles, or generate long articles based on materials. Trigger words include but are not limited to: write an article, draft a manuscript, help me write, continue writing, expand writing, WeChat Official Account article, long article, produce manuscript, write in my style. Even if the user only says "help me turn this into an article" or "write it in my style", it should be triggered as long as the context involves content creation and WeChat Official Account output. It is also applicable to scenarios where users send a PDF, brief, news link, voice-to-text content or any material and say "help me write an article". Do not use it for short content (Xiaohongshu posts, X (Twitter) posts, WeChat Moments posts) or pure title and abstract generation (use wechat-title skill for such scenarios).
This skill should be used when the user wants to "login to GitHub", "store an API key", "get authentication headers", "export credentials to the shell", "run a command with API keys injected", "register a custom OAuth provider", "manage tool tokens", or "authenticate to a third-party application". Also triggers for requests involving authenticating AI agents or securely storing/retrieving credentials using the authsome CLI.
Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.
Create and refine HEARTBEAT.md files for murmur — a CLI daemon that runs scheduled Claude prompts on a cron or interval schedule. Use this skill when the user wants to set up a recurring automated action (e.g., "monitor my GitHub issues", "check Hacker News for AI articles", "watch my endpoints", "send me a daily digest"). Guides the user through an interview, drafts the heartbeat prompt, tests it, and registers it with murmur's scheduler. Triggers: heartbeat, murmur, recurring task, scheduled action, cron, monitor, watch, automate, periodic check, scheduled prompt.
Use this skill when implementing encryption, hashing, TLS configuration, JWT tokens, or key management. Triggers on encryption, hashing, bcrypt, AES, RSA, TLS certificates, JWT signing, HMAC, key rotation, digital signatures, and any task requiring cryptographic implementation or protocol selection.
Source control and artifact exposure (.git, .svn, .hg, backups, .env). Use when recon finds VCS paths, 403 on hidden dirs, or backup/config leaks during authorized testing.
Share to the Starchild community in two independent ways — publish a running preview to a public URL, or open-source any project's code to the community GitHub repo. Also handles fork/install/browse.
Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.
Run Salesforce Code Analyzer to scan code for security, performance, best practice, and code style violations. Supports all engines (PMD, ESLint, CPD, RetireJS, Flow, SFGE, ApexGuru), targets (files, folders, git diff), categories, and severities. TRIGGER when: user says 'scan my code', 'check for security issues', 'run PMD/ESLint', 'find duplicates', 'analyze Flows', 'check vulnerable libraries', 'AppExchange review', 'lint my LWC', 'static analysis', 'code quality', or mentions engines/file types (.cls, .trigger, .js, .flow-meta.xml). DO NOT TRIGGER when: user wants to fix code without scanning, or asks about installation/configuration.
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.