N coordinated agents on shared task list using Claude Code implicit agent teams
原文语言:英语
菜单
SkillsMP 已收集 Yeachan-Heo/oh-my-claudecode 中的 43 个 Skill。打开任一 Skill 可查看来源和详情。
复制这段 Prompt,发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Yeachan-Heo/oh-my-claudecode.已展示 40 / 43 个已收集 Skill。
N coordinated agents on shared task list using Claude Code implicit agent teams
原文语言:英语
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions…
原文语言:英语
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
原文语言:英语
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates…
原文语言:英语
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language…
原文语言:英语
Shipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a pasted chat log or verbal problem report into a five-section intent.md through numbered batch questioning with a completion gate, walk it through tracker review with…
原文语言:英语
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at…
原文语言:英语
Writing-time discipline for the prose an agent speaks to a human (replies, reports, pointers): a protected core never rewritten (code, commands, paths, errors, negators, numbers), filler dies, no narration, auto-clarity where terse misleads
原文语言:英语
Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidates and hands them to the captain; it never refactors on its…
原文语言:英语
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one…
原文语言:英语
Deep codebase initialization with hierarchical AGENTS.md documentation
原文语言:英语
Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state
原文语言:英语
Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.
原文语言:英语
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the…
原文语言:英语
Diagnose and fix oh-my-claudecode installation issues
原文语言:英语
Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
原文语言:英语
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away
原文语言:英语
Full autonomous execution from idea to working code
原文语言:英语
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery
原文语言:英语
Carry an approved task through to working, verified code
原文语言:英语
Configure HUD display options (layout, presets, display elements)
原文语言:英语
Strategic planning with optional interview workflow
原文语言:英语
Self-referential loop until task completion with configurable verification reviewer
原文语言:英语
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
原文语言:英语
Autonomous evolutionary code improvement engine with tournament selection
原文语言:英语
Turn a repeatable workflow from the current session into a reusable OMC skill draft
原文语言:英语
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session
原文语言:英语
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
原文语言:英语
Investigate an open question and return grounded, sourced findings
原文语言:英语
Evaluate finished work for defects, risk, and simplification before it ships
原文语言:英语
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
原文语言:英语
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
原文语言:英语
Configure notification integrations (Telegram, Discord, Slack) via natural language
原文语言:英语
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
原文语言:英语
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
原文语言:英语
Manage local skills - list, add, remove, search, edit, setup wizard
原文语言:英语
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
原文语言:英语
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release
原文语言:英语
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
原文语言:英语
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs
原文语言:英语