Loading...
Loading...
Found 9,772 Skills
This skill should be used when the user wants to review code, audit a diff, get a second opinion on changes, or run an adversarial review of files in the current working tree. Common triggers include "review this code", "audit this diff", "find issues in", "second opinion on this", "harsh review of", "adversarial review", and "security review of". Picks one or more reviewer personas (adversarial, security, architecture, performance). Reviews local files, `git diff`, or `git diff --staged` only — does not fetch external content. Runs in one of four modes: single-agent (one persona in the current agent), cross-model handoff (independent second opinion via another local AI CLI, with secret-shield preflight + prompt-shield wrap), multi-bg-agent (one persona per parallel background subagent), or agent-team (Claude Code Teams or equivalent on supporting agents). Skip when the user wants formatting fixes (use a linter) or refactoring patterns (use ts-best-practices or ts-best-practices-functional).
This skill should be used when Claude needs to build or reuse a reusable Make API-call shell by discovering the correct app-specific Make an API Call module, resolving or requesting the right connection, explicitly setting the scenario interface, running the scenario, and using that shell as the retrieval transport for email, CRM, tickets, and similar SaaS systems.
SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.
Fix a known bug in the Rock RMS codebase. Guides Claude through root cause analysis, minimal correct fix, and a release-note commit message. Use when the user says "fix this bug", "bugfix", "this is broken", "debug this", describes a bug with file paths or issue numbers, or pastes an error/stack trace with intent to fix. Also use when a bug is found by another skill (e.g. /review-conversion, /check) and the user wants it fixed. Do NOT use for: finding bugs (use /check or /review-conversion), adding features, or refactoring.
Cross-platform CLI tool for managing Claude Code, Codex, Gemini, OpenCode & OpenClaw providers, MCP servers, prompts, skills, and proxies.
Provides image recognition capabilities for non-multimodal models (such as pure text models like deepseek-v4-pro, GLM-5.1, mimo-v2.5-pro, etc.). This skill is automatically triggered when the main model cannot recognize images, when users send screenshots/design drafts/UI screenshots for analysis, or when users say 'Look at this image', 'Analyze this screenshot', 'What's wrong with this image'. It also applies to any scenario where users paste images but the current model does not support image input. Supports simultaneous recognition of multiple images, with primary-backup fallback achieved by configuring multiple image recognition models. It can also be manually triggered using the commands /skill:vision-support or /vision. Iron Rule: The models configured for this skill are only used for image content recognition and will never participate in main logical reasoning. Note: If the current model is itself a multimodal model (such as Claude Sonnet 4, GPT-4o, Gemini, etc. that can directly recognize images), do not use this skill; let the main model recognize directly.
Create lean-spec style GitHub issues as specs for human-AI aligned implementation on the current repo. Use when asked to "create a spec", "write a spec issue", "spec this feature", "spec this", or when planning work that needs a specification before implementation. Follows the lean-spec SDD methodology — small focused specs (<2000 tokens), intent over implementation, context economy. Creates GitHub issues with Overview, Design, Plan, Test, Alignment, and Notes sections. Repo-specific area taxonomy, sister-skill names, custom body sections (e.g. Provider impact / Schema impact / Reach), and additional principles are overlaid by the consumer repo's CLAUDE.md and its `*-dev-process` / `*-pre-push` / `*-pr-lifecycle` sister skills — read those first when the repo isn't obvious.
Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skill-auditor); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads subagents/pm-skill-auditor.md and executes the system prompt inline. Returns a layered audit report (full findings + Status Summary prose + Status YAML envelope per master plan D26) with cross-cutting findings graded P0/P1/P2/P3 plus aggregate counter audit and validator results table.
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.
A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).
Use when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before syncing or publishing.
Run an ordered sequence of pm-skills against one input via the pm-workflow-orchestrator sub-agent, pausing for go/no-go and stopping on a failed or empty step. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skills:pm-workflow-orchestrator, which delegates each step through the Skill tool); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads agents/pm-workflow-orchestrator.md and walks the loop inline after a tool-capability pre-flight. Explicit invocation only; never fires proactively. EXPERIMENTAL on all non-Claude clients and on the native path until smoke-tested; run --dry-run first.