Loading...
Loading...
Found 3,064 Skills
Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs"
Shared references and cross-cutting rules used by all Infrahub skills. Contains GraphQL query syntax, .infrahub.yml configuration format, and common rules for git integration, display label caching, and Python environment setup. DO NOT TRIGGER directly — loaded automatically by other Infrahub skills when they need shared references.
Gets, checks, and verifies the current UTC date and time for unambiguous temporal reference. Use when starting tasks, verifying temporal context, ensuring date awareness before time-sensitive operations, or when incorrect date assumptions are detected.
Generate Triton operator requirement documents suitable for Ascend NPU. Used when users need to design new Triton operators, write operator requirement documents, or perform operator performance optimization design.
Guides users through documenting business flows step-by-step in EventCatalog. Use when user asks to "document a flow", "map a business process", "create a flow diagram", "walk through a process", "document an end-to-end flow", or "map out how something works in my architecture".
Regenerate docs/INDEX.md using docs/prompts/PROMPT-INDEX.md with a preflight plan, direct execution, validation, and post-action review (explicit-only).
Compiles and extracts session knowledge into a living, interconnected LLM-Wiki. Instead of writing isolated logs, it identifies key entities, updates cross-referenced topic files in docs/knowledgelib/, and maintains an index and chronological log. Use this to ensure persistent, compounding project knowledge.
Organize reusable programming patterns, library usages, and technical techniques that address "This is the correct way to do such tasks" into a prescriptive reference library, which can be retrieved and reused on demand during feature-design and issue-analyze phases. There are three types: pattern (design patterns, programming idioms), library (usage and pitfalls of a specific library/framework), technique (specific operation skills / command recipes). Trigger scenarios: when users say "Record a trick", "This usage is worth noting", "tricks", "Record library usage", or when valuable techniques worth documenting and archiving are discovered during feature-design / issue-analyze phases and actively pushed. For how to distinguish it from learning / decisions / explore, refer to the root skill of `easysdd`.
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
Fetch up-to-date third-party API/SDK docs via chub before writing or reviewing integration code — so method names, payload fields, and auth headers are always sourced from live docs, not stale training data. Don't use for first-party project docs, generic programming questions, or when the user only wants a conceptual answer rather than integration code.
Onboard a new repository or a repository with scattered documents into the CodeStable system. Two paths are automatically determined: the empty repository path (no spec-type documents or codestable/ directory in the repository) builds the skeleton from scratch; the migration path (the repository already has scattered documents or partial codestable/ structure) first generates an audit report + migration mapping plan, which is finalized after user confirmation one by one. This skill only does two things: "build the skeleton" and "organize existing documents". Once the skeleton is built, all sub-workflows can run directly. Trigger scenarios: Users say "Use CodeStable in this project", "Build CodeStable structure", "Initialize CodeStable", "Migrate to CodeStable".