Loading...
Loading...
Found 11,901 Skills
Use when auditing, trimming, or restructuring AI skill files to reduce context-window consumption. Trigger whenever a SKILL.md exceeds 120 lines, skills share duplicated content, AGENTS.md has large inline blocks, or the user asks to optimize, slim down, or reduce token usage of their skills.
Engineering operating model for teams where AI agents generate a large share of implementation output.
Azure cloud operations orchestration and Microsoft Agent Framework integration hub.
Tavily: web search optimized for AI agents, answer synthesis, domain filtering, depth control
View and manage configurations and skills for AI agent CLI tools (Claude Code, Opencode). Use when checking config files, listing or managing skills, viewing model settings, comparing configs across tools, or performing common config operations.
Integrate PICA into a LangChain/LangGraph Python application via MCP. Use when adding PICA tools to a LangChain agent, setting up PICA MCP with LangChain, or when the user mentions PICA with LangChain or LangGraph.
Create or update AgentSkills for CoWork-OSS. Use when designing, structuring, or packaging skills. Supports JSON format with requirements, installation specs, and metadata.
ALWAYS invoke this skill at the START of every session before doing any other work. This skill ensures the host project has agent governance rules (skill routing, pre-implementation protocol, issue tracking conventions) installed in its context file. It is idempotent — if rules are already present, it exits silently. Without this skill running first, other swain skills (swain-design, swain-do, swain-release) will not be routable.
Generate or update a README.md in French, oriented Product Owner, with Mermaid diagrams. Reviews and improves technical documentation in docs/. Also generates CLAUDE.md and AGENT.md if missing. Triggers on: create readme, update readme, generate readme, générer le readme, mettre à jour le readme, generate docs, update docs, /docs.
Orchestrate a specialized software development agent team. Receive user requests, classify task type, select the matching workflow, delegate each step to specialist agents via the Agent tool, and assemble the final output. Use when the user needs multi-step software development involving architecture, implementation, testing, security review, or code review. Also use for production incident investigation — when the user reports a live system issue, service outage, pod crash, data anomaly, or needs root cause analysis using kubectl, psql, argocd, or docker. Trigger this skill whenever a task involves more than one concern (e.g., "add a new endpoint" needs BA + Architect + Developer + QA + Security), when the user mentions team coordination, agent delegation, or when the work clearly benefits from multiple specialist perspectives rather than a single implementation pass.
Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance.
Builds sustained high agency through internalized standards, identity anchoring, cross-session learning, and self-recovery — all delivered in corporate PUA rhetoric. This is the evolution of PUA: same pressure culture, but with an internal engine that never burns out. Apply it to all tasks to maintain constant high agency. It is especially valuable for complex multi-step tasks, long debugging sessions, quality-sensitive deliverables, tasks requiring initiative and ownership, or whenever sustained motivation is critical. It can operate standalone or be stacked with PUA — when stacked, this skill's Recovery Protocol activates before PUA's L1 pressure takes effect. Trigger scenarios: start of any task, sustained work sessions, multi-turn problem-solving, or when you need the agent to think as an owner rather than a tool.