519 个 · 按相关度排序
Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request. The Lead is a provider-neutral orchestrator that makes decisions but never writes code, edits files, runs commands, or reviews its own work.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Energy Systems Engineer. Use when a task calls for Energy Systems Engineer judgment. Reasons from exergy, load duration curves, capacity factor, and grid boundary constraints through pinch analysis, hourly dispatch models (PLEXOS, HOMER Pro, SAM, PVsyst), spark-spread CHP screening, and IPMVP M&V while treating nameplate-vs-utilization confusion, average-vs-marginal grid emissions, unrealistic arbitrage spreads, and demand-charge ratchet resets as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces, explicit wrapped errors, context propagation) plus Cobra/Viper conventions where applicable. Use when a user has a Go spec to review, asks "is this spec ready?", or is about to implement from a written design. Distilled from spf13/go-skills and adapted to this repo's conventions.
中文简介正在准备中。当前显示原文说明。
Execute research tasks — checklist soft gate, phase dispatch with explicit thesis_dir, budget enforcement (halt + approval card on overrun), skill_pin recording (version_hash content-hashed per skill directory), [x] written on completion.
中文简介正在准备中。当前显示原文说明。
Scaffold and amend the L1 Investment Constitution — [ALL_CAPS] placeholder bootstrap, SemVer bump rules, Sync Impact Report, MINOR/MAJOR re-examination dispatch after the gate-5 budget confirm. Thesis creation stays refused until ratification (Q83).
中文简介正在准备中。当前显示原文说明。
Review and adapt MetaX attention backends, MLA, sparse indexers, cache layouts, and their kernel wrappers against a target vLLM revision and the actually installed MetaX component APIs. Verify dispatch, supported configurations, and GPU numerical behavior. Use for attention adaptations outside vllm_metax/patch/; do not apply monkey-patch headers or patch audit requirements.
中文简介正在准备中。当前显示原文说明。
Review and adapt vllm_metax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Verify registration, inherited state, weight layouts and actual backend selection. Use for registry compatibility work, not standalone attention algorithms or monkey patches.
中文简介正在准备中。当前显示原文说明。
Autonomously cut a Rove (`@sma1lboy/rove`) release end-to-end — detect the semver bump from pending changesets (flagging an upstream `minor` you didn't intend), run the release gates, dispatch the Changesets workflow (or run `scripts/release.sh` locally), then poll the GitHub Actions Release workflow with `gh` until npm publish completes, diagnosing CI failures (npm token, registry 404, lint, branch mismatch) instead of leaving them silent. Use when the user says "cut a release", "ship a version", "release Rove", "release rove", "发版", "release.sh", or "bump the version". Never force-pushes; always verifies the release landed on `main`.
中文简介正在准备中。当前显示原文说明。
Analyze an open-source project from What/Why perspective (not how-it's-implemented). Use when the user says "/analyze-oss", "분석해줘 이 오픈소스", "이 레포 뭐하는거야", "analyze this repo", "what does X do", "이거 왜 쓰는거야", "이 라이브러리 분석", provides a GitHub URL and wants understanding, or asks to deeply understand an OSS project's purpose, value, target users, and usage flow. Clones the repo to ~/opensource-analysis/<repo-name>/ (git pull if already exists), dispatches parallel subagents per analysis lens, then synthesizes a What/Why-focused report in chat. Supports optional user-specific follow-up questions.
中文简介正在准备中。当前显示原文说明。
Plan-driven orchestrator. Reads plan.json (from /blueprint) or requirements.md, then dispatches workers to build the system. Use when: "/execute", "execute", "plan 실행", "blueprint 실행"
中文简介正在准备中。当前显示原文说明。
Analyzes large tasks for independent subtasks that can be safely parallelized. Produces a DAG-based dispatch plan with dependency ordering and maximum parallelism. Use when a task has 5+ subtasks touching independent files, or the user asks to speed up or parallelize the work.
中文简介正在准备中。当前显示原文说明。
AgentFlow workflow skill. Use this skill when the user needs Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
中文简介正在准备中。当前显示原文说明。
DEPRECATED, renamed to orchestrating-chat-agents. Kept so existing imports of its scripts keep working; every module here loads the same module from orchestrating-chat-agents. Use orchestrating-chat-agents for parallel Claude calls over the API from claude.ai, and dispatching-subagents for fan-out in Claude Code.
中文简介正在准备中。当前显示原文说明。
Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use when reviewing tests, when a module gains a name-to-thing table, registry, enum, or dispatch map, before trusting a green suite as evidence a domain is covered, or when asked "is this test actually total", "does anything cover X", "what does this repo guarantee", "which invariants do we declare". Also for vacuous tests that pass over an empty collection, for a domain that has silently NARROWED (an enumeration cannot see that), and for recording the refutation that proves a claim can fail.
中文简介正在准备中。当前显示原文说明。
Use when deterministic runtime code needs to execute CommonGround worker lifecycle steps through the local `cg worker` command namespace, including claim acquisition, renewal, progress append, terminal finish, child dispatch, and suspend flows.
中文简介正在准备中。当前显示原文说明。
Use when a local agent needs to dispatch work to CommonGround, inspect turn or agent state, wait for a turn to close, or resume a suspended turn through the `cg` CLI instead of calling the CG HTTP API directly.
中文简介正在准备中。当前显示原文说明。
Verify the active host install, package, command ownership, enforcement, wrapper self-test, and active-dispatch coverage gap. Read-only.
中文简介正在准备中。当前显示原文说明。
Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.
中文简介正在准备中。当前显示原文说明。
The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.
中文简介正在准备中。当前显示原文说明。
OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.
中文简介正在准备中。当前显示原文说明。
Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.
中文简介正在准备中。当前显示原文说明。
The banned-primitive gate. Routed to when changed code hashes, signs, encrypts, derives keys, generates security-relevant randomness, configures TLS, or imports a crypto library. Rejects broken primitives, disabled TLS verification, and home-rolled crypto; the approved-primitive list lives in security-controls.md. The auth-crypto-reviewer agent is dispatched as the reviewer.
中文简介正在准备中。当前显示原文说明。
Feature auto-development — clarify requirements, generate spec, dispatch dev sub-agent to implement and merge into current branch
中文简介正在准备中。当前显示原文说明。
Use when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts".
中文简介正在准备中。当前显示原文说明。