Productivity Skills

> Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

Generate and rank research ideas given a broad direction. Use when user says \"\u627eidea\", \"brainstorm ideas\", \"generate research ideas\", \"what can we work on\", or wants to explore a research area for publishable directions.

Generate and rank research ideas given a broad direction. Use when user says \"\u627eidea\", \"brainstorm ideas\", \"generate research ideas\", \"what can we work on\", or wants to explore a research area for publishable directions.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.

Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions. Invoke to create architecture diagrams, write Architecture Decision Records (ADRs), evaluate technology trade-offs, design component interactions, and plan for scalability. Use for system design, architecture review, microservices structuring, ADR authoring, scalability planning, and infrastructure pattern selection — distinct from code-level design patterns or database-only design tasks.

Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing Confluence pages with CQL, managing sprints and backlogs, setting up MCP server authentication, syncing documentation, or debugging Atlassian API integrations.

Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.

Builds security-focused full-stack web applications by implementing integrated frontend and backend components with layered security at every level. Covers the complete stack from database to UI, enforcing auth, input validation, output encoding, and parameterized queries across all layers. Use when implementing features across frontend and backend, building REST APIs with corresponding UI, connecting frontend components to backend endpoints, creating end-to-end data flows from database to UI, or implementing CRUD operations with UI forms. Distinct from frontend-only, backend-only, or API-only skills in that it simultaneously addresses all three perspectives—Frontend, Backend, and Security—within a single implementation workflow. Invoke for full-stack feature work, web app development, authenticated API routes with views, microservices, real-time features, monorepo architecture, or technology selection decisions.

Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models, and produces monitoring configurations and automation scripts for production systems. Use when defining SLIs/SLOs, managing error budgets, building reliable systems at scale, incident management, chaos engineering, toil reduction, or capacity planning.

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

MANDATORY: Use this skill for ANY and ALL tasks involving building Skia with GN, Ninja, or compiling any Skia tool. It is the authoritative source for Skia's build workflows and MUST be used whenever compilation is required.

Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

Use when launching anything that runs longer than a minute, anything that streams logs, anything you want to keep running while doing other work — or when terminal_exec auto-backgrounded on you and returned a job_id. Teaches the start→poll→wait pattern with terminal_job_logs offset bookkeeping, the `wait_until_exit=True` blocking-poll idiom, the truncated_bytes_dropped resumption signal, the merge_stderr decision, the SIGINT→SIGTERM→SIGKILL escalation ladder via terminal_job_manage, and the hard rule that jobs die when the terminal-tools server restarts. Read before calling terminal_job_start, or right after terminal_exec auto-backgrounded.

Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation, save this analysis, keep this insight, preserve this chat result.

Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions. This is a reasoning review, not a deterministic vault health check or repair workflow.

How to read and write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides, Keep, Forms, Apps Script, and Meet via the `gws` CLI (a community Google Workspace CLI, not an official Google product). `gws` wraps the Workspace REST APIs (pagination, retries, JSON parsing) and the agent shells out via `terminal`. Note that `gws` does NOT ship an OAuth client — an OAuth client or service account must be configured before interactive login will work (unless a pre-injected token is present). Use whenever the user asks for anything involving a Google Workspace surface.

Use when the user wants a recurring task done automatically on a schedule (daily/weekly/cron) that DOES WORK unattended — pull data and summarize, open a PR, post a digest — rather than just a time-based reminder ping, OR when the user wants to test/dry-run/"run now" a routine before scheduling it. Explains how to author a routine, test it once on demand, and schedule it to run in an isolated sandbox with only declared credentials, via the routine tool.

Architecture design and phased implementation planning for Bitwarden Android. Use when planning implementation, designing architecture, creating file inventories, or breaking features into phases. Triggered by "plan implementation", "architecture design", "implementation plan", "break this into phases", "what files do I need", "design the architecture".

> Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and vendor reviews to find policy drift, or direct query for a proposed new AI practice. Use when user says "policy sweep", "does our AI policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", or on a recurring schedule.

> Drafts board or committee meeting minutes in your house format. Auto-detects upcoming board and committee meetings from your calendar, asks for the agenda and any slides or pre-read materials, and produces a complete draft in the format learned from your seed minutes. Also handles written consents in lieu meeting", "committee minutes", "written consent", or calendar detection of an upcoming board or committee event.

> What's blocking close — maintain the closing checklist with status, critical findings and schedule builds, tracks status, surfaces what's blocking. Use when user says "closing checklist", "what's left to close", "checklist status", "add to the checklist", or on a scheduled status pull.

> Guided customization of your corporate practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, active modules (M&A / Board / Public Company / Entity Management), materiality thresholds, disclosure schedule format, consent precedents, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", or "customize".

> Read VDR documents and extract issues per house categories and materiality thresholds, producing findings in house memo format. Use when user says "review the data room", "extract issues from [folder]", "diligence review", "what's in the VDR", or points at VDR documents.

> Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start. Use when user says "integration", "post-close", "post-closing", "consents outstanding", "contract assignment", "integration status", or "what's left on the deal".

> Build the material contracts disclosure schedule from diligence findings, applying the purchase agreement's Material Contract definition and formatting per the agreement's schedule format. Use when user says "build the contracts schedule", "disclosure schedule", "schedule 3.X", "material contracts list", or when drafting disclosure schedules.

> Tabular review — one row per document, one column per data point, every cell cited to source. Built for M&A diligence ("review these 200 target contracts for change-of-control, assignment, and MAC clauses") but works for any batch review that needs a spreadsheet out the other end. Use when user says "tabular review", "review grid", "build a grid", "extract these fields from these contracts", "review these documents for X, Y, Z", "give me a spreadsheet of", "batch review", or points at a folder of documents and asks to compare them.

> Kick off international expansion planning for a new country — gathers intake, runs EOR vs. entity framing, drafts cross-functional questions, surfaces country-specific flags, and creates a persistent tracker. Use when someone says "we're hiring in [country]", "expansion to [country]", or "first hire in [country]".

> vs. entity decision framing, cross-functional triggers for tax/finance/HR, structured outside-counsel briefing requests, and a persistent gap tracker. Loaded by /expansion-kickoff and /expansion-update; not invoked directly.

> Open a new internal investigation matter — runs intake, generates the sources checklist, and creates the persistent investigation log. Use when a complaint or allegation comes in and the attorney needs to stand up a privileged investigation workspace.

> Check open leaves for deadline alerts and required decisions. Surfaces only the leaves that require an action and explains why — not a status board. Use weekly, or whenever the attorney needs to know which leaves have upcoming designation, certification, or exhaustion deadlines.

> Build or update a long-term bar prep (or exam prep) study plan — phases, subjects weighted by weakness, daily session schedule, adaptive to session history in study-plan.yaml. Use when the user says "build a study plan", "plan my bar prep", "schedule my studying", or "how should I study for [X]".

Draft a demand letter from a completed intake, gated on a privilege / FRE 408 / waiver / admission checklist, with a .docx output, post-send checklist, and an offer to create a matter. Use when the user says "draft the demand", "write the [type] letter", or has a finished demand intake ready to turn into a sendable draft.

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legal_hold fields in _log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

Triage a subpoena served on the company — classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar. Use when the user says "we got a subpoena", "served with a subpoena", or shares a subpoena, CID, or third-party document request to evaluate.

Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision (--decide CMT-ID).

Use markdown formatting when drafting content intended for external systems (GitHub issues/PRs, Jira tickets, wiki pages, design docs, etc.) so formatting is preserved when the user copies it. Load this skill before producing any draft the user will paste elsewhere.

Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow labels. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.

Assess, validate, and route community-filed issues for human disposition and roadmap placement. Takes a specific issue number or processes a confirmed batch of issues labeled state:triage-needed. Investigates reported behavior, separates objective findings from product decisions, and prepares validated issues for a human yes/no decision. Trigger keywords - triage issue, triage, assess issue, review incoming issue, triage issues.

Design and evaluate paid-ad experiments with hypotheses, randomization units, sample-size and duration assumptions, guardrails, platform experiment tools, analysis, and decision rules. Use for A/B test, split test, experiment design, hypothesis, statistical significance, sample size, test duration, or experiment readout.

在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。

在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。

当你有规格说明或需求用于多步骤任务时使用，在动手写代码之前

Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over asking clarifying questions when the user's tone is casual or playful rather than precision-seeking.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.