70 skills · sorted by relevance
Architectural review workflow. Analyzes codebase organization via noun analysis and produces a target blueprint. Advisory only — does not implement changes. Always offers to cut tickets for the planned work; orchestrators receive the proposal and apply their own autonomy judgment to approve / edit / decline.
The English summary is being prepared. Showing the original description.
Full-lifecycle project workflow. Takes batched tickets, implements via /implement-batch, runs smoke tests, then executes a comprehensive quality pipeline (refactor, review-arch, review-test, tidy-docs, review-release). Maximizes autonomy with andon cord escape.
The English summary is being prepared. Showing the original description.
自主任务执行系统 - 让 从被动 Abby变主动
The English summary is being prepared. Showing the original description.
Launch Marcus multi-agent experiments with independent CLI agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent agent CLI processes that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill. The Marcus MCP server is agent-agnostic; this skill supports both Anthropic's claude CLI and OpenAI's codex CLI as agent harnesses (selected via --harness).
The English summary is being prepared. Showing the original description.
Launch Marcus multi-agent experiments with independent CLI agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent agent CLI processes that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill. The Marcus MCP server is agent-agnostic; this skill supports Anthropic's claude CLI, OpenAI's codex CLI, and Google's gemini CLI as agent harnesses (selected via --harness).
The English summary is being prepared. Showing the original description.
Launch Marcus multi-agent experiments with independent Claude agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent Claude CLI agents that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill.
The English summary is being prepared. Showing the original description.
Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.
The English summary is being prepared. Showing the original description.
当用户需要做重大决策、团队存在群体思维、或想将决策权下放到一线时触发此技能。帮助建立知情指挥决策模型，让最有信息的人做最终决定。
The English summary is being prepared. Showing the original description.
当用户正在微观管理团队、想从命令控制型转向自主团队、或作为创始人成为决策瓶颈时触发此技能。帮助用情景管理替代控制管理。
The English summary is being prepared. Showing the original description.
GStack plan-tune method for calibrating how many questions to ask, autonomy level, stop conditions, and decision style for a workstream or user preference.
The English summary is being prepared. Showing the original description.
Use when an autonomous agent run needs a plan before execution — decomposing the goal, setting explicit boundaries and stop conditions, and defining what the agent may decide alone versus escalate.
The English summary is being prepared. Showing the original description.
Use when executing a previously agreed autonomous agent plan — running the steps within declared boundaries, checkpointing progress, and escalating when a stop condition is hit.
The English summary is being prepared. Showing the original description.
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.
The English summary is being prepared. Showing the original description.
Abbruchbedingung für autonome Loops: So weit wie möglich selbständig weiterarbeiten UND einen Loop erst beenden, wenn belegt ist, dass keine autonom ausführbare Aufgabe mehr vorliegt. Der bloße Eindruck "nichts mehr zu tun" reicht NICHT — er löst eine vierstufige Prüfkette aus (think/decide, _CONTROL/_DECISIONS, Gardener/USMC, decision-avatar/BYUM), die zuerst neue Aufgaben GEWINNEN muss, bevor der Loop enden darf. Jeder Kettenschritt meldet found/empty/unavailable statt eines binären Ergebnisses — "exhausted" gilt nur, wenn ALLE Quellen tatsächlich befragbar waren; ist mindestens eine Quelle unavailable, meldet der Skill "blind" statt "exhausted" und behauptet nichts Ungeprüftes. Nutze diesen Skill bei /work-autonomous, /waafap, "arbeite autonom weiter bis nichts mehr zu tun ist", als Goal-Bedingung innerhalb eines /loop, oder wenn geprüft werden soll, ob wirklich keine autonome Arbeit mehr übrig ist, bevor ein Loop/eine Session beendet wird.
The English summary is being prepared. Showing the original description.
Einmaliger Tasksolver+Writer+Maintainer-Durchlauf fuer den Projektordner, in dem die Session gerade sowieso gearbeitet hat (inkl. Unterordner) — kein systemweiter Sweep. Loest offene triviale/autonome Register-Punkte, aktualisiert Dokumentation auf den gemessenen Ist-Stand (im Projekt UND in der Root der Pipeline, in der das Projekt liegt) und raeumt Strays/Temp- Dateien nach dem Papierkorb-Prinzip weg. Nutze diesen Skill bei /tidy-up, "raeum das Projekt auf", "mach hier sauber bevor wir weitermachen", am Ende einer Arbeitssitzung an einem Projekt, oder als faellige autonome Aufgabe innerhalb von /work-autonomous + /goal.
The English summary is being prepared. Showing the original description.
Experimental workflow for configuring an autonomous software delivery factory. Use when choosing feedback sources, schedules, worktree behavior, autonomy gates, or drafting proposed host automations for report-only review.
The English summary is being prepared. Showing the original description.
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.
The English summary is being prepared. Showing the original description.
Run multiple Reforge-guided section-refactor lanes in parallel, each in its own worktree/branch off origin/main, with a score-blind adversarial review panel gating every commit, one draft PR per section. Use when the user wants to reduce Reforge surface/internal score across several sections at once via architecturally-correct deletions (dead surface, entity-leak removal, cross-section consumers moved onto the public contract) — not by relocation, parameter bags, or accessibility-dodging. Wraps the per-lane process in .codex/skills/humans-refactor. Triggers: 'refactor swarm', 'parallel section refactors', 'run reforge refactor on Users/Tickets/...', 'burn down surface score across sections'. Has an intensity dial (light|standard|deep) and a workflow|solo execution mode to trade token burn against autonomy per unit of output.
The English summary is being prepared. Showing the original description.
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.
The English summary is being prepared. Showing the original description.
Frame multi-agent designs through explicit environment, autonomy, information, coordination, commitment, incentive, and verification assumptions. NOT for endorsing multi-agent architecture without need or claiming runtime correctness from conceptual methods.
The English summary is being prepared. Showing the original description.
Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle detection, or any "when / how long ago / how long did that take" question. Required for autonomous, parallel, or long-running agents.
The English summary is being prepared. Showing the original description.
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.
The English summary is being prepared. Showing the original description.