Productivity AI Skills

BRD interview, 业务需求访谈。Use when: 需要将模糊的业务想法梳理成 BRD、"帮我梳理业务需求"、"老板说要做 XXX"、"这个需求不太清楚"、"写 BRD"。

Create an Obsidian-formatted markdown note documenting the current session topic. Use when the user says /note, 'save this to Obsidian', 'write a note about X', or asks to document a troubleshooting…

Research customer context across docs, tickets, CRM, email, and web sources with cited confidence.

Direct substantial repository work across Claude Code, Codex CLI, or Grok Build with a concise brief, parallel agents, evidence-based completion, and optional cross-CLI continuation. Use for project…

Build power-user interfaces: keyboard-first, information-dense, AI-present. Covers row patterns, keyboard layers, AI integration, liveness, nav chrome, color discipline, triage UX, visual impact…

Zoom Meeting SDK for React Native. Use when embedding Zoom meetings in React Native iOS/Android apps with @zoom/meetingsdk-react-native, JWT auth, join/start flows, platform setup, and native bridge…

GitHub Issue resolver skill that analyzes, triages, and proposes solutions for issues with full SDD integration Trigger terms: resolve issue, fix issue, github issue, issue triage, issue analysis,…

Developing for multicore systems in Zephyr RTOS. Covers Symmetric Multiprocessing (SMP), Asymmetric Multiprocessing (AMP) with OpenAMP/RPMsg, inter-processor communication (IPC) patterns, and Linkable…

Run the verify-plan checklist against YOUR OWN plan before finalizing it (before ExitPlanMode), with special emphasis on the consumer audit. Triggers on: 'audit yourself', 'self-audit', 'check your…

Load when a task needs anti-template frontend visual direction, design-read calibration, or pre-flight critique for landing pages, portfolios, marketing pages, or redesigns; do not load for…

Configure and adjust the job search strategy level. The agent interrogates the user, proposes a level, and saves it to DB. All flows respect it.

当用户需要校准画面色彩准确性、诊断'肤色不对'、或理解观众对色彩的心理预期时调用。核心 trigger：用户提到'肤色不对'、'天空颜色'、'色彩记忆'、'画面看起来不自然'。不适用于：用户讨论创意风格（用 look-development）。

Select optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to Superpowers

Clarify and rewrite quoted prompts while preserving the user's intent and natural prompting style. Use when the user invokes this skill with a prompt in quotation marks, asks to improve or strengthen…

Engine-absent safety and historical-field archive: field history, checkout/atomic safety, dispatch/QC invariants. Use only when the host has no CLI/engine (execution state = conversation tracking).

Production Intelligence Specialist

Identifies and refactors monolithic files (>2k lines) into modular, performance-safe component structures.

Manage JIRA issues, sprints, boards, and Confluence pages via CLI. Use when user needs to create/search/update JIRA tickets, manage sprints, or edit Confluence pages.

Help with OData service development in ABAP including OData V2 and V4 services via RAP service bindings, SEGW-based services, service definitions, service bindings, OData annotations, consumption of…

This skill should be used when the user asks to "query WRDS", "access Compustat", "get CRSP data", "pull Form 4 insider data", "query ISS compensation", "download SEC EDGAR filings", "get ExecuComp…

Direct game-math strategy, target setting, and validation governance across game modes. Use when aligning RTP/volatility goals, defining math sign-off criteria, reviewing simulation evidence, or…

Design, build, and verify practical dashboards for KPIs, trends, comparisons, status monitoring, filters, charts, and operational decisions.

Separate Splunk Enterprise entitlement lifecycle issues from measured license-capacity demand and produce an evidence-bounded, advisory-only plan grounded in current official Splunk documentation.

Read or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.

Audit an existing VictoriaMetrics vmanomaly configuration against runtime capabilities and real data. Use when reviewing model-data fit, scheduler cadence, persisted-state compatibility, cold start,…

设计和实施自动化工作流程，节省时间并实现独立创业者的规模化运营。适用于识别需要自动化的重复任务、跨工具构建工作流程、设置触发器和操作，或优化现有自动化流程。涵盖自动化机会识别、工作流程设计、工具选择（Zapier、Make、n8n）、测试和维护。触发词："automate"、"automation"、"workflow automation"、"save time"、"reduce manual…

Plan-first orchestration (ADR-004): comprehensive PLAN.md, sprint files with write-scope ownership, preflight checks, serialized integration, and the release sprint. Use for any non-trivial or…

Build and evaluate predictive sports models from user-provided modeling data. Use for binary outcome models, feature/model selection, chronological backtests, probability scoring, and comparison to…

Run Codex code review with Claude's independent double-check. Use when asked "codex review", "review my code with codex", or wants Codex to review code changes. For adversarial review use…

(alamops) Writes a decomposition-ready implementation plan to `docs/plans/<slug>.md` — objective, grounded context with file:line anchors, approach and rejected alternatives, a work breakdown where…

When the user wants a keyword SERP analysis with competitor comparison, target page gaps, or player-score interpretation. Also use before topic cluster or content brief work that needs SERP evidence.

Pre-submission validation for Google Play releases covering metadata, screenshots, bundle integrity, data safety, and policy compliance. Use when preparing a release to avoid rejections and catch…

Use when turning an alternative data source into model features and the event date differs from the date your fund actually received the data; enforces point-in-time lag mapping from knowledge date so…

Use when resizing or reformatting a CoDesign / CE.SDK design to a new size or aspect ratio (ig-post ↔ ig-square ↔ ig-story ↔ widescreen, or a custom W×H); when building the size/format editions of a…

Use when modeling, metering, attributing, billing, or controlling AI usage costs across tenants, plans, features, providers, and agent workloads.

Build orchestrator agents that manage multi-agent workflows, enforce SLAs, handle escalations, and maintain overall task completion

Planification stratégique du contenu {{COMPANY_NAME}} — calendrier éditorial, équilibre des piliers, idées de contenu, coordination cross-canal. À utiliser pour planifier, pas pour rédiger.

Review perceived performance in product UI. Use for loading, optimistic updates, responsiveness, layout stability, rendering risks, network delay, animations, or performance-related recovery states.

Compute the delta between the `DESIGN.md` baseline (from explore) and the `DESIGN-VERIFICATION.md` result (from verify), reporting per-category score delta, anti-pattern delta (resolved vs new),…

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Automate Atlassian tasks via Rube MCP (Composio). Always search tools first for current schemas.

Turns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story or issue link counts. Skip obvious,…

Capability-based multi-tool matrix for research, note-taking, document authoring, and publishing. Agents compose providers (CLI-Anything harnesses, public CLIs, Python libs, native binaries, cloud…

Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud…

Generates production-ready TypeScript CLIs via a 3-tier template system (manual arg parsing, Commander.js, oclif), each shipping full implementation, docs, package.json, strict config, JSON output,…

Guides repo-local skill creation and updates. Use when adding or editing .agents/skills, root AGENTS.md routing, SKILL.md frontmatter, description trigger quality, references layout, skill scripts, or…

Label a PR as ready for QA so the QA server picks it up automatically

Use this skill when the user asks MoviePilot to identify and organize a local or downloaded video/music file, season folder, recording, album directory, or mixed folder that automatic transfer did not…

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training…

Workspace file I/O expert. ALWAYS invoke this skill when you need to list workspaces, read or write files in a workspace on a remote node, or browse workspace directories. Use this for cross-node file…