Loading...
Loading...
Found 8,144 Skills
Extract and structure fuzzy product ideas into validated problem statements, target users, and jobs-to-be-done. Use when a user has a raw idea, concept, or solution in mind but hasn't clearly articulated the problem, target user, or assumptions. This skill helps users communicate context to coding agents more effectively, reducing iteration cycles and "that's not what I meant" moments.
Use after the final approved execution scope is complete, or when the user asks whether a feature is done, ready to ship, safe to merge, or needs a quality check. Runs the post-execution quality gate: specialist review, artifact verification, and human UAT against locked decisions and the final exit state. Use for prompts like "review this feature", "is this done?", "can we ship this?", "double-check the implementation", or "run UAT".
Use whenever a beo session is starting, resuming, recovering from interruption, checking status, deciding what to do next, or when the correct beo skill is not obvious. This is the default bootstrap and routing entry point for the beo pipeline. Use first for prompts like "continue", "resume", "what's next?", "status?", "pick this back up", "where are we?", or any new feature request where the current phase is unclear.
Use before any non-instant feature work, refactor, behavior change, or requirements-shaping conversation where user intent is not yet locked. Extracts and confirms the decisions that planning will depend on, especially when the user knows what they want but has not fully thought through edge cases, scope boundaries, or expected behavior. Output is CONTEXT.md.
Use after exploring completes or whenever a feature already has locked requirements and now needs research, synthesis, phase definition, story mapping, and executable task beads. Use for prompts like "plan this", "break this into tasks", "decompose this work", "map the stories", "research and plan", or "turn this into beads" before implementation begins.
Use when an approved epic is ready for implementation and the next current-phase bead should be executed directly in single-worker mode or by a single worker inside a swarm. Use for prompts like "implement this bead", "do the work", "run the worker", "start implementing", "execute the next task", or whenever approved current-phase work needs to move from plan into verified implementation one task at a time.
Use after planning completes and before any implementation begins. Verifies that the current phase contract, story map, and bead graph are structurally sound, execution-ready, and aligned with locked decisions. Use for prompts like "validate the plan", "is this ready to build?", "check the bead graph", "verify execution readiness", or whenever there is doubt about whether the current phase is safe to execute.
Use the emergent-thinking CLI to persist project-local requirements, plans, decisions, and thought trails across Codex or Claude Code sessions.
Discover Harbor capabilities, inspect capability details, and explain grant or secret blockers before execution. Use when asked what Harbor can do, list capabilities, inspect a capability, check whether a capability exists, or find the next safe Harbor action.
Fetches issue context, auto-detects task type, maps to branch prefix, presents brief.
Review a PR and submit suggestions as comments, along with an optional approval/request for changes.
Use when starting any conversation, receiving a new task, or when uncertain which skill applies - establishes how to find and use all 64 toolkit skills, requiring Skill tool invocation before ANY response including clarifying questions