Loading...
Loading...
Found 512 Skills
Conduct deep research using OpenAI's deep research models via API. Use when the user asks for comprehensive analysis, company research, person research, or product research requiring web-sourced citations.
Evaluate every produced output (code, report, plan, data, API response) against type-specific quality criteria, score 1-10, make accept/reject decisions, and provide actionable improvement suggestions. Triggers on "evaluate", "check", "review", "quality control", "is this good enough", "score it", or before passing output to the next step in an agentic workflow.
Designs album concepts, tracklist architecture, and thematic planning through 7 structured phases. Use when planning a new album or reworking an existing album concept.
Create, improve, and audit AI agent skills. Applies 14 proven structural patterns, scores quality with deterministic audit, manages full lifecycle. Use when building, refactoring, or reviewing skills. NOT for agents, MCP servers, or running existing skills.
Synthesize unstructured thinking into a structured, actionable plan. Use when user provides stream-of-consciousness thoughts, scattered notes, or a brain dump and needs them organized into a coherent plan with goals, actions, and priorities. Trigger phrases: "synthesize", "organize my thoughts", "turn this into a plan", "make sense of this", "structure this", "formalize these notes", "what should I do with all this".
Manage tasks using the fine CLI. Use this skill whenever the user asks to create, view, update, or work with tasks, project requirements, feature specs, or work tracking through markdown files. Also use it when the user mentions "fine" in the context of project management, or asks about task status, step progress, or wants to break work into tracked steps.
The project's all-seeing guide. Sentinel MUST activate before Claude takes any action that modifies, creates, or deletes anything in the project. It understands the codebase, architecture, brand, design system, business model, deployment pipeline, testing strategy, and every convention. Trigger on: action requests (build, fix, add, change, update, refactor, implement, create, remove, delete, migrate, deploy, integrate, improve, configure, install, bump, upgrade, debug, troubleshoot, move, rename); casual requests (can you, I need to, let's, go ahead and, help me, we need to); status reports (X is broken/failing, there's a bug); project questions (how does X work here, where would I add, walk me through); planning (scope this, break this down, write a spec). Do NOT trigger on general knowledge, blog posts, interview prep, or tech comparisons for other projects. Key test: does this need THIS project's context? If yes, trigger. Sentinel guides Claude, it does not execute. No task is too small.
Guides the agent through authoring and validating agent skills. Use when creating new skill directories, tightening skill metadata, extracting supporting references, or preparing skillgrade evals. Do not use for general app documentation, generic README editing, or non-agentic library code.
Research how to implement a phase (standalone - usually use COMMAND PREFIX plan-phase instead)
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Decompose requirements into structured task lists and build a task management system for long-running Agents (based on the Anthropic Effective harnesses methodology). Automatically trigger when users need to manage multi-session development tasks, track feature completion progress, or request "task decomposition", "task management", or "project planning".
Track per-agent token usage and flag waste in parallel dispatch. Use after running parallel agents to evaluate cost vs value.