Loading...
Loading...
Found 28 Skills
Use when dealing with 2 or more tasks that can be performed independently, with no shared state or sequential dependencies
Use when an approved plan exists and needs execution, or when a hotfix/one-sentence scope needs direct TDD implementation — dispatches subagents per task, validates, reports
Track per-agent token usage and flag waste in parallel dispatch. Use after running parallel agents to evaluate cost vs value.
Use when user wants to find a note to publish as a blog post. Triggers on「选一篇笔记发博客」「note to blog」「写博客」「博客选题」. Scans Obsidian notes via Python script, evaluates blog-readiness, supports batch selection with fast/deep dual-track and parallel Agent dispatch.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task, reviews once per phase, loads phases just-in-time to minimize context usage
RED-GREEN-REFACTOR testing for agents: dispatch subagents with known inputs, capture verbatim outputs, verify against expectations. Use when creating, modifying, or validating agents and skills. Use for "test agent", "validate agent", "verify agent works", or pre-deployment checks. Do NOT use for feature requests, simple prompt edits without behavioral impact, or agents with no structured output to verify.
Raise một ISSUE đầy đủ bối cảnh vào ledger local (draft) để dev khác pull về xử lý ở BẤT KỲ đâu qua /fdk mà không đụng nhánh/dự án khác; TỰ mirror lên tracker remote nếu có (GitHub qua gh / GitLab qua glab / Gitea qua tea) — ledger là nguồn chân lý. Dùng cho feature-gap, tech-debt, foundation, câu hỏi kiến trúc (KHÁC orca-issue = sự cố/bug repro-first). Gồm template context + assign owner + dispatch agent. Trigger: 'raise issue', 'tạo issue', 'ghi issue', 'mở issue', 'log gap này', 'issue để dev khác làm', '/raise-issue'.
STOP — if you were dispatched as a subagent to execute a briefed task, this skill is not for you: it governs the dispatching orchestrator only, and the mode and path rules you need are already in your brief. Do the task you were briefed with instead. Use whenever the user asks to dispatch, launch, spawn, fan out, or delegate work to an agent, subagent, worker, or coding agent in a separate git worktree — phrasing like "dispatch a subagent", "launch an agent", "fan out subagents", "parallel agents", or "use a separate worktree to implement/fix/refactor/test/review X" — or whenever two or more workers must edit the same repository concurrently without colliding. Symptoms it prevents: worktrees created from the wrong base commit, workers accidentally editing the orchestrator checkout when an isolated worktree was intended (Mode D is the sanctioned single-writer exception), Edit/Write failing outside the agent CWD, colliding diffs, shared Docker/e2e infrastructure clobbered by concurrent test runs, merged worktrees left consuming disk, and force-removed worktrees losing uncommitted work.
Launch a task in a new Herdr tab after choosing the agent harness and model.
Concurrent investigation of independent failures. Use when multiple unrelated issues need parallel resolution.
Multi-source research synthesis — aggregate and compare 3+ sources or any source >5KB using sub-agent dispatch and SharedState
Use for the Team pipeline only on explicit request. Never infer from ordinary coding work. Runs QRSPI or a leading route.