Каталог навыков агентов

Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review pass...

Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code rev...

Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requi...

Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.

Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specificati...

Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heat...

Track deep work sessions and productivity metrics.

Search, inspect, and progressively read open-access academic papers with the deepxiv CLI. Use when the user wants arXiv...

Turn a selected Radar defect cluster into a bounded discovery specification using existing ATE, fuzz, oracle and replay...

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, cr...

Generate a structured user story map to visualize workflows, user goals, and release slices.

Schedule instructions to run ONCE at a later time in the current session, via a one-shot in-session cron job (CronCreate...

Choose who does a piece of work, and on which model. Claude agents review and judge; OpenCode implements and reviews cod...

A built-in agent for delegating subtasks, orchestrating parallel workflows, and managing multi-agent execution.

Delegate bounded independent subtasks to available subagents while preventing file overlap, missing context, and unverif...

Delegate clear, simple, bounded work to a subagent model from the user's ordered candidate list while the main session k...

Delegate an independent coding or review task to Codex CLI with a narrow brief, isolated worktree, bounded permissions,...

Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.

Help users delegate effectively. Use when someone is struggling to let go of tasks, deciding what to delegate, building...

Helps users delegate tasks, break them into steps, set deadlines, and track progress via routines and memory.

Delegate so the work comes back right the first time — the brief that transfers outcome, context, and constraints (not j...

Decide whether to spawn a subagent, and on which model tier and reasoning effort. Use when planning a fan-out, choosing...

Guidelines for safely deleting dictionary entries while properly updating indexes and cross-references.

Deliberate practice as a rigorous training method distinct from ordinary repetition. Covers Ericsson's four conditions (...

Coordinate a development task from a stronger brief through implementation and verification, with optional adversarial C...

Turns raw captures, dictated braindumps in a deliverable’s inbox/, or recent macwhspr dictation-log entries into propose...

Pre-delivery acceptance checklist and reusable mini-prompts for common tasks. Use when (1) Preparing to mark story as De...

Execute an approved Markdown task packet through a bounded loop: validate it against the repository, implement it, run t...

Break large scopes into coherent increments without losing the complete product vision.

Delivery manifests, QA reports, user feedback interpretation, patch writing, reward calculation, and training-loop updat...

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

Rebuild and publish the unityctl demo page hosted at https://dirtybitgames.github.io/unityctl/. Use when asked to update...

Builds departmental or company budgets on a driver basis: collects top-down targets, bottom-up department requests and e...

Use when a task involves reviewing dependency update alerts or Dependabot pull requests for compatibility, security, and...

Laravel guidance to remove unneeded Composer packages and assets to improve boot time, memory, and security surface

Analyze task dependencies including finding blocked tasks, checking dependency chains, and identifying bottlenecks. Use...

Extract a thesis's dependency fingerprint — the external variables its bull case actually rests on (key customers, suppl...

Deploy a backend branch via GitHub Actions. Use when user says "deploy", "lanza el pipeline", "despliega", or "/deploy"....

AI PR intake and multi-agent governance for deployless repositories. Use when a repo has high-volume bot or agent PRs, p...

Single-mainline governance for deployless repositories. Use after a deployless audit when a repo needs trunk-based branc...

Deployment workflow for Astro sites on Cloudflare Pages + GitHub. Staging → Production flow. Use before first deploy.

Write dept-state.md and member-roster.md at end of department session. Department-operations parallel of /save-state.

当手上有一份已经写好的推导、要逐步核验时使用。每一步查四件事：代数是否等价、量纲是否一致、符号有没有翻错、以及这一步用的定律在此处适用条件是否仍然成立——变质量、非惯性系、准静态假设中途被悄悄破坏是高频翻车点。scripts/check_d...

Phase sizing, scope boundaries, and anti-patterns. Load when evaluating whether a phase is well-formed or needs splittin...

Phase directory layout, naming conventions, and required files. Load when creating or navigating phase directories.

Required sections and format for phase.md. Load when defining phase intent, scope, and acceptance criteria.

Plan-Build-Review cycle and agent handoffs. Load when transitioning between agents or understanding workflow progression...

Mandatory files agents must read before acting. Load when starting agent work to ensure prerequisites are met.

Structure and sections for review.md. Load when creating review scaffolds or recording review findings.

Ticket system overview, schema, and workflows

Core Ushabti concepts and development lifecycle. Load when starting any Ushabti workflow or orienting to the framework.

When intent or consequential choices are unclear — resolve goals, boundaries, contracts, and an approved direction befor...

TRIGGER when: asked to write or refine a technical design, PRD, specification, implementation plan, or task list, or res...

Design or review multi-agent delegation, handoff, review, voting, fan-out, shared-artifact, and event contracts. Use whe...

Route and coordinate an end-to-end design-award workflow across winner research, evidence-based evaluation, award matchi...

Sizes a single simply-supported beam in steel, wood, or reinforced concrete for a known span, tributary load, and deflec...

Compare 2-3 materially different child-level contract/interface shapes and write the chosen direction into `CONTRACT_DEC...

Use when the user asks to make or compare a codebase architecture decision involving module boundaries, ownership, inter...

Checks a single axially loaded, braced column against the capacity your standard's values produce, with every step of th...

Design cycle count programs from inventory classes, risk, count capacity, accuracy history, and review cadence.

Design a recurring workflow for human, deterministic automation, and optional agent work by modeling triggers, state, de...

Sizes a duct segment from an airflow and the limits you set: area from the velocity limit you state, rectangular dimensi...

Checks a single isolated spread footing: bearing pressure under your loads against the allowable bearing value your geot...

Evidence-driven agent skills for design award research, evaluation, matching, entry preparation, and submission checks a...

Design logistics barcode and scan-flow concepts for process steps, identifiers, labels, validation points, exceptions, a...

Design a Zoom MCP workflow for Claude. Use when deciding whether Zoom MCP fits a task, when planning tool-based AI workf...

End-to-end media pipeline automation — from AI generation through optimization to social publishing. Covers workflow des...

Ensure that ideas become designs, designs are reviewed, and

Manage NV oOS Pro Schedules — create, update, delete, list, dry-run, view run history, and plan schedules from workflows...

Manage the NV oOS Pro Toolkit Project Management system — projects, tasks, events, sprints, task plans, task templates,...

Reviews a CDD for completeness, internal consistency, implementability, and adherence to project design standards. Suppo...

Compare 2-3 materially different initiative decompositions in `SPLIT_OPTIONS.md` when task boundaries or sequencing are...

Checks one stair flight item by item: width, headroom, riser, tread, uniformity, nosing, landing, vertical rise between...

Use this skill when authoring or retrofitting the CDD for one module listed in design/cdd/module-index.md, including dep...

Plan and run safe data backfills and replays — idempotent reprocessing of historical windows, partition-by-partition exe...

Designs risk-based functional test plans, manual test cases, regression slices, and automation handoff packs from requir...

Use when designing systems with explicit states, transitions, or multi-step flows. Triggers: "design a workflow", "state...

Move pointer, drag, type and click in a permitted local desktop session.

destination-trip-planning — Research a specific destination/attraction, gather pricing/logistics, and build a themed tri...

Detecta entidades nomeadas (personagens, locais, organizacoes) em textos ficcionais em portugues usando modelos NER fine...

Detection engineering skill for writing, testing, and tuning Sigma, YARA, YARA-L, Suricata, Snort, Zeek, KQL, SPL, EQL,...

Plans and records bounded defensive tests of whether preventive controls, telemetry, and detections remain effective acr...

Use this skill when designing mine-rs deterministic tools, JSON schemas, VFS artifacts, task tools, subagents, verifier...

Use this skill when the operator needs Detsky Mir data — prices and availability for kids' and baby goods, toys, strolle...

Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, o...

기능 개발을 위한 아키텍처 설계 문서를 작성한다. AI가 기술 옵션 분석과 트레이드오프를 제시하고, 사용자가 기술 판단과 시스템 영향을 평가하여 결정한다. 사용 시점: "아키텍처 설계해줘", "기술 구조 잡아줘",...

This skill should be used when the user asks to 'pause work', 'hand off session', 'save progress', 'create handoff', or...

AI DevKit · Orchestrator for structured SDLC phase skills. Use when the user wants to run the full lifecycle or choose t...

기능 개발을 위한 PRD(제품 요구사항 문서) 및 디자인 문서를 작성한다. AI가 초안을 작성하고 사용자가 우선순위와 요구사항을 결정하는 협업 방식으로 진행한다. 사용 시점: "PRD 작성해줘", "기획서 만들어줘"...

4단계 개발 프로세스를 순차적으로 실행하는 오케스트레이터. PRD → 아키텍처 → 구현 스펙 → 테스트 케이스 순서로 진행한다. 각 단계에서 AI가 초안을 작성하고 사용자가 검증/확정하는 협업 방식으로 진행한다. 사...

Manage long development sessions with structured progress tracking. Creates SESSION.md files for multi-session handoff,...

기능 개발을 위한 상세 구현 스펙 문서를 작성한다. AI가 상세 스펙 초안과 인수 조건을 작성하고, 사용자가 도메인 규칙과 엣지 케이스를 검증한다. 사용 시점: "구현 스펙 작성해줘", "상세 스펙 만들어줘", "A...

Read a story file and implement it. Loads the full context (story, CDD requirement, ADR guidelines, control manifest), r...

Plan sprints and backlogs in an AI-Driven Development workflow. Define features (backlogs), organize sprints as cumulati...

Development Workflow Skill