Loading...
Loading...
Found 6,423 Skills
Load groove workflow context into the conversation. Run at the start of every session.
Autonomous SDLC router. Takes a job, classifies complexity, executes the appropriate lev-* workflow (from trivial fix to full epic), and returns "done" with runnable instructions. One shot to full auto: spec/bd/poc/impl. Subagent returns completion artifact. Triggers: "sidequest", "side quest", "just do it", "autonomous", "one shot"
Skill Map Viewer. Scans all installed skills and renders a visual overview — you can check the name, version, description, and category at a glance. This tool is triggered when the user says 'skills', '技能', '技能地图', 'skill map', '我有哪些技能', '看看技能', '列出技能', 'list skills'. It also activates when the user asks about available or installed skills.
Check and install prerequisites for Cyrus — Node.js, jq, gh CLI, and the cyrus-ai npm package.
Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.
Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
Analyze a company's published content to extract their brand voice, writing style, and tone guidelines. Reads 10-20 of their best content pieces and produces a brand voice profile covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona. Useful before writing outreach, content, or campaigns that should match a client's existing voice.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for AI-agent, prompt-injection, MCP or toolchain, cloud, container, CI/CD, and supply-chain challenges. Use when the user asks to analyze prompt-to-tool flows, retrieval poisoning, mounted secrets, deployment drift, runtime-vs-manifest mismatches, registry provenance, or CI-produced artifacts under sandbox assumptions. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Use when starting work on a new or unfamiliar project, when encountering unexpected patterns, when user corrects your assumptions, or when explicitly invoked via /learn - auto-discovers and remembers project context through structured codebase analysis
Use this skill when the user wants to transform an existing image into a new generated result, such as replacing models, changing poses, swapping backgrounds, generating scenes, expanding image edges, removing backgrounds, or creating virtual try-on images. Use it for image-editing and image-generation tasks where a source image and text instructions need to be turned into one or more final images.
Autonomous evolutionary code improvement engine with tournament selection
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.