Productivity

Run the full pre-PR checklist (make check, secret scan, docs, diff review) before opening or updating a pull request. Use before creating a PR or when asked if work is ready.

Use when an open-ended task should be raised from task-level to outcome-level, when results must be verified by something other than the model that produced them, or when a crew of tool-bearing subagents is needed. Compiles the request into <invariant + falsifiable verifier + environment manifest>, runs an outside-judge ladder with per-claim verdicts, and makes subagents do the work rather than role-play it. Skip for tight specs with fixed acceptance criteria, trivial tasks, or crunch situations - adding harder goals there only adds risk.

把杂乱的会议记录、语音转录文字整理成结构化会议纪要。当用户发来会议记录、聊天记录或转录文本并说"整理成纪要"时使用。

Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an index README. Use when the user says 'record this decision' or 'ADR this', chooses between frameworks or databases, discusses trade-offs, or asks why the codebase is shaped this way.

>- Use this when choosing a tool, library, framework, CLI, MCP server, or agent skill for a task: first look in the user's own GitHub stars and in official vendor skill catalogs, then recommend well-known, actively maintained options with reasons.

Analyzes Android apps to identify key user workflows for AppFunctions such as creating a note, playing media, or sending an automated or AI agent triggered message, voice commands, or system shortcuts, without needing to open the app UI. Generates Kotlin code to expose these workflows to the Android system, allowing agents to discover and execute them on-device. Also refines KDoc documentation to ensure AI agents correctly understand and use the provided functionality.

Scan a Go project structure and generate/update README.md with package overviews, dependencies, and usage notes.

Commit workflow that runs doc-gen first, stages only needed files (asking for confirmation on uncertain ones), suggests a message from the actual diff, commits, shows a summary, and asks about pushing.

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

Update project documentation (CLAUDE.md + .llmdocs/). Use after significant work to keep docs in sync.

Builds the project and pushes a release to the staging host.

Create diagrams as self-contained HTML files with inline SVG that make visual arguments, then screenshot and lint them in a render-validate loop until clean. Use when the user wants to visualize a workflow, architecture, system, process, or concept as a diagram they can open in a browser, embed, or share.

Builds the project and pushes a release to the staging host.

Run the Gate 1 deterministic static check on task bundles before development starts and follow the Gate 2 review checklist. Use when task contracts exist under tasks/ and you need to verify blast radius, diff budget, declared-file topology, traceability anchors, spec anchor coverage, inherited ADRs, machine-checkable acceptance criteria, and DAG acyclicity. Do not use for code execution, CI pipeline construction, AST/complexity checks, or test audits (owned by quality-engineering).

Run a bounded brownfield change (bugfix, small feature, behavior tweak) against an existing spec or codebase: proposal -> one task bundle -> dev/QA -> converge -> archive. Use when an existing spec or codebase needs an incremental change (bugfix, small feature, behavior tweak) and a full PRD is overkill. Do not use for greenfield requirements (use prd-generator), architecture decisions (use spec-generator), or pure task slicing (use task-decomposition).

Fold confirmed implementation deviations back into the technical spec after a task reaches QA_PASSED, archive the task bundle and close the change proposal. Use when a task bundle records a checked QA_PASSED verdict and its 02-dev-workspace.md deviation log is ready to be written back. Do not use while implementation or QA is still running, and do not use to invent spec content.

Implement, fix, or refactor project code with a cooperative token-budgeted workflow that stops before optional builds, tests, runs, linting, formatting, generation, dependency work, or documentation. Use for ordinary software changes in any language or framework. Do not use when the user's primary request is to perform one of those validation or maintenance actions.

Implement one planned task bundle as the Dev role: read the contract, change only touch_files, run the machine-checkable DoD, fill 02-dev-workspace.md and hand off to QA. Use when a task contract exists and you are assigned implementation. Do not use for planning, task slicing, architecture, or QA verification.

Consolidates multiple fragmented OpenSpec capability folders under openspec/specs/ into a single main feature spec, through a staged/approved workflow. Use this whenever the user says openspec/specs/ is cluttered, has too many similar or overlapping capability folders, asks to merge/consolidate/combine specs, wants to clean up specs split across several separate change archives (e.g. specs/user-show/, specs/user-detail/ that should really be one specs/user-management/), or asks to check/apply a pending merged spec under openspec/specs/.merged-specs/. Do NOT use this for a normal single /opsx:archive of one change — only for merging several already-archived, already-existing spec folders together.

Talk to Agent Office, the live pixel-art office where the user watches their coding agents work, through the agentoffice MCP tools (office_status, office_peers, office_shout, office_celebrate, office_flip). Use when starting a substantial task (set a status), before editing files in a repo other agents may be working in (check peers to avoid edit collisions), on a real milestone (shout), when tests go green after a fix (celebrate), or when a failure is truly maddening (flip, once per task). Only applies when the agentoffice tools are available.

>- 结绳（Tiecode/结绳 IDE）插件开发完整指南。涵盖插件 API （com.rapid.api.* / studio-api.jar）、program.json 扩展点、.rmx 打包、 以及各种功能的实现方式：代码补全（TextMate + LanguageEngine + LSP）、 文件树（PSObject/ExpansionCase/CreationOption/OpeningOption）、 运行配置（RunConfiguration/TaskRunConfiguration）、 新建文件选择方式、工程模板（BaseTemplate）、编译任务（BaseTask/ToolchainService）、 工具链、语言高亮、菜单、设置页等。当用户要开发、修改、学习或排查结绳插件、 结绳IDE插件、.rmx 插件、Tiecode 插件、go/scala/kotlin/linux/aar 等语言工程插件时使用。

>- Put Amazon Bedrock AgentCore infrastructure behind a plan-only CI gate. Generates a GitHub Actions workflow that, on pull requests touching the infrastructure, runs the static AgentCore review (`ACR0xx`), `terraform fmt -check`, `init`, `validate`, a saved `plan` (Terraform or Terragrunt) with a read-only OIDC role, `show -json`, and the plan policy (`CI0xx`: no delete or replace of memories, gateways, credential providers, workload identities, user pools or tables without an explicit per-address allowance; no `*` on `*`; no gateway with `authorizer_type = NONE`; pinned MCP revisions), then uploads the plan JSON. Nothing in it applies. The plugin's stdlib-only library is vendored into `ci/agentcore/` so the job needs nothing from the plugin, and action pins are reused from the repository's own SHA-pinned workflows. `policy_check.py` also runs locally on any saved plan. Use when asked to "add CI for the AgentCore Terraform", "gate the plan", "block destructive changes", "policy check the plan", "plan on ...

Stand up and run a LinkedIn employee advocacy program for a marketing or sales team. Covers 14-day launch playbook, brand-guideline governance, per-post time budget, cadence benchmarks, and team ROI (reach, engagement, pipeline). Triggers on \"employee advocacy\", \"get the team posting\", \"scale LinkedIn across team\", \"advocacy ROI\". Not for planning one person's own calendar (use linkedin-content-planner).

>- SOLID C++ / ESP32 firmware guardrails: file/class size, no nested classes, strict DI at composition roots, no UNIT_TEST / test ifdefs in production headers (and avoid them in .cpp), no hardcoded secrets, one type per public header, public API /// comments, dual-core radio pinning (PRO_CPU 0 / APP_CPU 1), FreeRTOS-safe patterns. Use when editing ESP-IDF, Arduino-ESP32, PlatformIO firmware, or ESP-NOW / BLE / Wi-Fi tasks.