Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
47.966 de skill-uri din 2.309 depozite · actualizat acum 16 ore
6.165 de skill-uri
- Warmly API PatternsWYRE-AI/msp-claude-pluginsWarmly's remote MCP server: WorkOS AuthKit OAuth 2.0 + PKCE authentication, RFC 9728 protected-resource metadata, multi-organization scoping, the stateful Streamable HTTP session model, the three read-only visitor-intelligence tools and their fields, credit semantics, error codes, and rate-limit guidance.InginerieFără avertismente★ 52↓ —
- Clio API PatternsWYRE-AI/msp-claude-pluginsClio Manage MCP fundamentals: OAuth 2.0 Authorization Code connection via Conduit, region selection, the matters-as-hub data model, decision-tree tool navigation, pagination, and the deliberate v1 scope limits (no delete anywhere, documents metadata-only, communications/calendar/bills read-only).InginerieFără avertismente★ 52↓ —
- audit-projectOutlineDriven/outline-driven-developmentUse when the user says "audit my code", "find all the bugs", "review until clean", or "grill my changes". Not for remote, credential, or irreversible changes.InginerieFără avertismente★ 55↓ —
- settlement-agreement-review-andrew-birdlawve-ai/awesome-legal-skillsReviews or drafts the agreement that pays an employee to settle their claims — and flags the statutory conditions that decide whether it actually binds them. Works under s.203 ERA 1996 for England & Wales. Flags apparent s.203 condition gaps for a solicitor to confirm (writing, specific complaints, independent adviser, identification, insurance, statement of conditions), drafts the substantive terms (sum, tax characterisation, confidentiality, references, restrictive covenants, indemnities), and surfaces enforceability risks. Does not rule on validity and is not legal advice. Use when the user says 'review this settlement agreement', 'draft a settlement agreement', 'compromise agreement' (old term), or asks whether an agreement is binding.InginerieFără avertismente★ 913↓ —
- KPN API PatternsWYRE-AI/msp-claude-pluginsHow the KPN tool surface behaves through Conduit: the X-KPN-* credential headers and the two OAuth token realms (API Store vs Mobile Services Management), why a valid key can still fail with 401/403 (product entitlement), quota headers and 429 handling, the write-confirmation flow, and why failed MSM writes are never retried automatically.InginerieFără avertismente★ 52↓ —
- ai-audit-trail-larissa-meredith-flisterlawve-ai/awesome-legal-skillsThis skill builds a structured audit trail of an AI-assisted task: what the tool was asked to do, what materials it was given, what it produced, how the output was verified, and what was ultimately relied upon. It documents the workflow for supervision and later review without ruling on privilege or disclosure, so the record stays accurate rather than self-serving.InginerieFără avertismente★ 913↓ —
- google-chat-messagesjezweb/claude-skillsSend Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline. Use whenever the user wants to post to Google Chat from a script, build a chatbot reply, send a notification card, build a Google Chat webhook integration, or troubleshoot card / threading issues.InginerieFără avertismente★ 1,1 K↓ —
- disclosure-list-andrew-birdlawve-ai/awesome-legal-skillsWorks out which documents you have to hand over to the other side in a civil case in England & Wales, and builds the formal list. The part it gets right that trips people up is which disclosure regime applies — Practice Direction 57AD (the Disclosure Pilot, now permanent in the Business and Property Courts, with its Models A–E) or standard disclosure under CPR Part 31 everywhere else. It picks the regime, chooses a Model per issue, structures the Disclosure Review Document, and drafts the disclosure certificate for the party to sign personally. Built for litigation juniors, in-house counsel, and small teams without a precedent bank. Use when the user says 'disclosure list', 'PD 57AD', 'Model C', 'extended disclosure', 'List of Documents', 'N265', or needs to work out what must be disclosed.InginerieFără avertismente★ 913↓ —
- dwarf-expertOutlineDriven/outline-driven-developmentUse when inspecting, searching, verifying, or parsing DWARF debug info: DIEs, DW_TAG_/DW_AT_ entries, .debug_* sections, line tables, or llvm-dwarfdump/readelf output.InginerieFără avertismente★ 55↓ —
- Strix•功能级授权缺陷asdfgh1445/ctf-super-hubStrix 功能级授权缺陷测试手册,覆盖操作级权限失效、管理功能越权与 API 操作绕过;触发名:strix-broken-function-level-authorizationInginerieFără avertismente★ 842↓ —
- linkers-ltoOutlineDriven/outline-driven-developmentUse when choosing a linker, fixing link order or undefined symbol errors, enabling LTO or ThinLTO, or cutting dead code with --gc-sections. Not for inspecting the linked binary: use elf-inspection.InginerieFără avertismente★ 55↓ —
- type-drivenOutlineDriven/outline-driven-developmentUse when modeling a domain, encoding a state machine, hardening APIs, making invalid states unrepresentable, or parsing instead of validating. Not for TypeScript: use typescript-best-practices.InginerieFără avertismente★ 55↓ —
- axiom-modeOutlineDriven/outline-driven-developmentUse when the user requests axiom, axiom-mode, axiom-compact, formal-logic, or compact form. Not for changing code or remote state.InginerieFără avertismente★ 55↓ —
- tabular-review-lawvablelawve-ai/awesome-legal-skillsGuide to analyze multiple documents (PDF, DOCX) against user-defined columns and produce a structured Excel output with citations. Use when the user wants to: (1) Extract specific information from multiple documents into a table, (2) Compare clauses or provisions across contracts, (3) Create a document review matrix with source citations. Triggers on: 'tabular review', 'document matrix', 'extract from documents', 'compare across documents', 'review multiple contracts'.InginerieFără avertismente★ 913↓ —
- can-i-helpOutlineDriven/outline-driven-developmentUse when the user asks "where to help", "contribution opportunities", or "find a good first issue". Returns data-backed first steps. Not for PR review queues: use gh-review-requests.InginerieFără avertismente★ 55↓ —
- doc-reviewOutlineDriven/outline-driven-developmentUse when reviewing a prose plan, spec, PRD, requirements doc, design doc, or brainstorm, or invoking /doc-review. Not for collaborative drafting: use doc-coauthoring.InginerieFără avertismente★ 55↓ —
- sanitizersOutlineDriven/outline-driven-developmentUse when building, running, or interpreting ASan, UBSan, TSan, MSan, LSan, HWASan, or Miri for native or Rust code, including memory-corruption debugging, unsafe-code validation, and sanitizer CI wiring. Not for fuzz target setup: use fuzzing.InginerieFără avertismente★ 55↓ —
- resolveOutlineDriven/outline-driven-developmentUse when addressing review feedback in analyze or reception mode, or handling GitHub PR feedback in autonomous, interactive, or summary mode for a named PR target. Classifies, applies, replies, or summarizes comments.InginerieFără avertismente★ 55↓ —
- Icelandic Privacy Reviewlawve-ai/awesome-legal-skillsUse this skill when asked to review data protection or privacy compliance under Icelandic law and GDPR. Triggers on requests involving personal data processing, privacy policies, DPIA assessments, kennitala handling, Persónuvernd filings, or cross-border data transfers from Iceland.InginerieFără avertismente★ 913↓ —
- clay-to-deeplinegetaero-io/gtm-eng-skillsMove Clay tables, workflows and functions to Deepline Plays, and compare what the same run costs in Clay and in Deepline. Use for any Clay migration, Clay export or bookmarklet JSON, Clay CLI workspace, "convert this Clay table", Clay credit cost, or "is Deepline cheaper than Clay". Reads a Clay CLI export or a bookmarklet / clay-extract.py JSON file. Makes the Plays, proves formula parity on real rows, and prices both sides.InginerieFără avertismente★ 72↓ —
- deepline-feedbackgetaero-io/gtm-eng-skillsRetired. Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`. Kept only so installed CLIs that still list this skill keep syncing.InginerieFără avertismente★ 72↓ —
- update-project-docshoangsonww/Claude-Code-Agent-MonitorMANDATORY for every coding agent (Claude Code, Codex, or any other) — keep this repository's documentation in sync after any change to behavior, configuration, interfaces, events, schema, or features. Use automatically at the end of change-sets that alter an env var, event type, hook or state behavior, API, schema, WebSocket message, MCP tool, CLI command, or user-facing feature, and whenever the user asks to update documentation.InginerieFără avertismente★ 1,1 K↓ —
- proc-cliyazeed/proc-cliFinds, inspects and stops processes and ports with the proc CLI (macOS, Linux, Windows) under a safety protocol: preview, show the user, then act by PID. Use when a port is busy or in use (EADDRINUSE, "address already in use") and needs freeing, to see what listens on a port, runs from a directory or holds a file, to kill a process or stop, free a port, pause, resume or wait for one, to clean up the dev servers and headless browsers an agent started, or to look into a slow machine or a stuck process. Use it instead of lsof, ps, pgrep, pkill, killall, kill or netstat. A name can match processes of other projects and other agents, so anything the agent did not start needs a dry run and the user's approval first. Not for containers, system services or remote hosts.InginerieFără avertismente★ 64↓ —
- pitroom-reviewATASTECH/pitroomUse when completing a task, implementing a major feature, before merging, or whenever you want a second opinion on a diff, branch or pull request - a read-only Pitroom worker on another model reviews it against its requirements.InginerieFără avertismente★ 51↓ —