Loading...
Loading...
Found 2,174 Skills
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.
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring observability from day 1, and adding entropy-control checks plus CI automation for reliable autonomous runs.
This skill should be used when the user asks to "implement a plan", "execute implementation", "build from plan", "implement feature", or needs to orchestrate execution of an implementation plan with specialized engineering agents.
P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Evaluate agents and skills for quality, completeness, and standards compliance using a 6-step rubric: Identify, Structural, Content, Code, Integration, Report. Use when auditing agents/skills, checking quality after creation or update, or reviewing collection health. Triggers: "evaluate", "audit", "check quality", "review agent", "score skill". Do NOT use for creating or modifying agents/skills — only for read-only assessment and scoring.
Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.
Generate AGENTS.md file and docs/ knowledge base skeleton in the project root directory, and establish a document governance system for agent-first repositories. Manually triggered, writes the template after checking for existence.
Strategic operating manual — direction-setting, resource allocation, focus, metrics, and scaling stages for autonomous agents treating themselves as CEO of a one-entity company.
HODLMM volatility risk monitor — reads Bitflow HODLMM pool state, computes current-state volatility proxy from bin distribution, scores regime (calm/elevated/crisis), and emits position-sizing or liquidity-pull signals for LP agents. Read-only; no wallet required.
Integration patterns for the GitHub Accessibility Scanner Action (github/accessibility-scanner). Teaches agents how to detect scanner presence, parse scanner-created issues, correlate findings with local scans, and track Copilot-assigned fix status.
Orchestrates multi-agent AI systems with task delegation, agent communication, shared memory, and workflow coordination. Use when users request "multi-agent system", "agent orchestration", "AI agents", "agent coordination", or "autonomous agents".