菜单
Entry point for professional skills — architecture, communication, process design, ethics, and leadership. Routes to the right skill based on what the user needs. Use this when the user's goal involves a professional discipline but they haven't named a specific skill.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build automation scripts and pipelines that use coding-agent CLIs (Claude Code, Codex, Gemini CLI, GitHub Copilot CLI) in headless/non-interactive mode as the AI engine, or delegate work to cloud agents (`gh agent-task`) that open pull requests asynchronously. Use this skill whenever the user wants to write a shell script, CI job, cron task, batch processor, webhook handler, or any automation that shells out to `claude`, `codex`, `gemini`, `copilot`, or `gh agent-task` — single-turn prompts, multi-turn agentic loops, parallel fan-out across files/folders, structured JSON outputs consumed by downstream tools, or cloud-delegated tasks that produce PRs. Trigger on phrases like "script that uses Claude", "automate with Claude Code", "headless Claude", "batch process files with an LLM", "pipeline with codex exec", "gemini -p", "copilot --autopilot", "gh agent-task create", "GitHub Action that calls Claude", "cron job to review PRs", "agent loop in bash", "dispatch an agent task to open a PR", "fleet-wide agent-tas
Apply causal inference whenever the user is interpreting metrics, debugging system behavior, reading A/B test results, or trying to understand whether an observed change was caused by an action or by something else. Triggers on phrases like "X caused Y", "since we deployed this, metrics changed", "the A/B test showed a lift", "why did this metric move?", "is this correlation or causation?", "we changed X and Y improved", "how do we know this worked?", "the data shows…", or any situation where conclusions are being drawn from observational data. Also trigger before any decision based on metric interpretation — confusing correlation with causation leads to interventions that don't work and misattribution of credit. Never assume causation without applying this skill.
Apply ethical reasoning whenever the user faces a decision, design, or action with moral implications — especially when someone could be harmed, rights could be violated, or values are in tension. Triggers on phrases like "is this the right thing to do?", "what are the ethical implications?", "who could this harm?", "should we build this?", "is this fair?", "what are our obligations?", "value trade-off", "responsible AI". Use proactively when reviewing any high-stakes decision, product design affecting vulnerable populations, or action where the beneficiaries and those bearing costs are different groups.
Apply execution-planning whenever the user has made a decision and needs to turn it into action — decomposing work, sequencing tasks, estimating timelines, and assigning ownership. Triggers on phrases like "how do we execute this?", "break this into tasks", "what's the project plan?", "create a roadmap", "what are the dependencies?", "who does what by when?", "how long will this take to build?". Use proactively after decision-synthesis or architecture-evaluation produces a committed decision that requires coordinated implementation.
Apply experimental-design whenever the user needs to test a hypothesis, validate an assumption, or determine whether something actually works. Triggers on phrases like "how do we test this?", "design an experiment", "what would prove this?", "set up an A/B test", "how do we validate this hypothesis?", "what's the right control?", "is this result significant?", "what sample size do we need?". Use proactively when decisions rest on untested assumptions — designing the test before collecting data prevents post-hoc rationalization.
Apply fairness auditing whenever the user describes a system, algorithm, policy, or process that allocates outcomes across groups and wants to know whether it is equitable. Triggers on phrases like "is this fair?", "disparate impact", "bias in the system", "does this discriminate?", "algorithmic fairness", "who's disadvantaged by this?", "equitable outcomes". Use proactively when reviewing any allocation mechanism, scoring system, or automated decision pipeline that affects people differently based on group membership.
| name | professional-orchestrator |
| description | Entry point for professional skills — architecture, communication, process design, ethics, and leadership. Routes to the right skill based on what the user needs. Use this when the user's goal involves a professional discipline but they haven't named a specific skill. |
Routes — does not reason. Match user intent to an entry point, then execute that skill's SKILL.md.
If ambiguous, ask one clarifying question.
| User wants to... | Start with | Then |
|---|---|---|
| Architecture & Engineering | ||
| Evaluate or choose between architectures | architecture-evaluation | → execution-planning |
| Debug a software failure systematically | debugging-methodology | → casual-inference if causal |
| Design or run an experiment | experimental-design | → casual-inference after results |
| Review code or a PR | code-review-amplifier | done |
| Find incremental improvements, tech debt, code hygiene | kaizen | → execution-planning or process-design |
| Understand why code is the way it is, audit undocumented fixes | kintsugi | → knowledge-architect or technical-writing |
| Planning & Execution | ||
| Break a decision into an action plan | execution-planning | done |
| Design or improve a workflow/process | process-design | → execution-planning |
| Build a financial model or business case | financial-modeling | → argument-craft |
| Writing & Communication | ||
| Write an RFC, design doc, ADR, runbook, postmortem, one-pager, announcement | technical-writing | → narrative-construction if storytelling |
| Summarize a document, article, transcript, meeting notes | summarizer | → technical-writing or argument-craft if needed |
| Structure a recommendation or argument | argument-craft | → technical-writing to write up |
| Tell a compelling story from analysis | narrative-construction | → presentation-craft if presenting |
| Create, structure, or improve a presentation/talk/pitch | presentation-craft | done |
| Prepare for a negotiation | negotiation-strategy | → difficult-conversations if high stakes |
| Navigate a difficult conversation | difficult-conversations | done |
| Design a meeting or workshop | facilitation-design | done |
| People & Organizations | ||
| Map stakeholder influence and blockers | stakeholder-power-mapping | → negotiation-strategy or difficult-conversations |
| Ramp up on a new domain | learning-strategy | → topic-explainer for specific concepts |
| Understand or learn a concept, technology, idea | topic-explainer | → technical-writing to document |
| Ethics & Fairness | ||
| Surface moral implications of a decision | ethical-reasoning | → fairness-auditing if systemic |
| Audit a system for equitable outcomes | fairness-auditing | → argument-craft to present |
| Determine causation vs correlation | casual-inference | done |
| Knowledge Management | ||
| Capture a decision, learning, or tribal knowledge | knowledge-architect | → technical-writing if formal doc needed |
| Set up or improve a team's knowledge system | knowledge-architect | done (produces architecture) |
| Someone is leaving / joining | knowledge-architect | detect mode for departures, audit for joiners |
| Meta | ||
| Scan all skills to find the right one(s) | skill-router | → matched skill(s) |
skills/[skill-name]/SKILL.mdDo NOT auto-execute. Propose:
Based on [what the skill produced], a natural next step would be:
→ [skill-name]: [1-sentence reason]
Want me to continue, or is this what you needed?
Multiple follow-ups → list as options. User chooses.
Architecture decision:
architecture-evaluation → argument-craft → execution-planning
Making and implementing a system design choice.
Building a business case:
financial-modeling → argument-craft → execution-planning
Numbers → narrative → action.
Navigating organizational resistance:
stakeholder-power-mapping → negotiation-strategy → difficult-conversations
People blocking progress; understand why and how to move them.
Process improvement:
process-design → execution-planning
Workflow is slow or broken.
Documenting a technical decision:
architecture-evaluation → technical-writing (ADR or RFC)
Architecture decision needs write-up.
Ethics review:
ethical-reasoning → fairness-auditing → argument-craft
Moral and equity analysis, then communication of findings.
| Skill | Purpose |
|---|---|
architecture-evaluation | Evaluate system design decisions, produce ADRs |
code-review-amplifier | Structured pre-scanning for human code reviewers |
debugging-methodology | Systematic debugging: reproduce, observe, hypothesize, isolate |
execution-planning | Decompose decisions into executable plans |
experimental-design | Design rigorous experiments to validate assumptions |
process-design | Design workflows using Lean and value stream analysis |
financial-modeling | Unit economics, cost-benefit, NPV/IRR, scenario modeling |
argument-craft | Structure recommendations into persuasive arguments |
narrative-construction | Turn analysis into compelling stories |
negotiation-strategy | Prepare for negotiations with BATNA, ZOPA, concession planning |
difficult-conversations | Navigate conflict, feedback, emotionally charged discussions |
facilitation-design | Design meetings and workshops that produce decisions |
stakeholder-power-mapping | Map influence networks and design engagement strategies |
ethical-reasoning | Surface moral implications using multiple ethical frameworks |
fairness-auditing | Audit systems for equitable outcomes across groups |
learning-strategy | Build structured plans for closing knowledge gaps |
casual-inference | Distinguish causation from correlation |
technical-writing | Write RFCs, design docs, ADRs, runbooks, postmortems, announcements |
topic-explainer | Explain concepts, technologies, ideas using the best style |
summarizer | Summarize documents, articles, transcripts, multi-source content |
presentation-craft | Presentation scripts: narrative arc, slide visuals, speaker notes |
kaizen | Continuous improvement audit: waste, unevenness, overburden |
kintsugi | Repair visibility audit: undocumented fixes, context gold |
skill-router | Exhaustive skill scan and composition planning |
knowledge-architect | Capture decisions, context, learnings; design team knowledge systems |