Каталог навыков агентов

Select the most consequential unresolved decision, present a compact set of viable options and a recommendation, then re...

Level and optimize construction resource allocation across project schedule. Balance labor, equipment usage, and avoid o...

Top-level memory- and resource-safety code review for modern C/C++ (C++17), including Node.js native addons (node-addon-...

Respond to incoming code review comments on a PR you authored. Fetches every unresolved comment across all channels, inl...

Restate durable execution for fault-tolerant services and workflows. Triggers on restate, durable, ctx.run, ctx.sleep, a...

Resume work after a crash or new session with safety constraints

Inspect, verify, transactionally restore, and audit a Codex migration package on a new computer. Use when the user has t...

Change the style/genre of an existing song while keeping its original melody and structure, using ACE-Step 1.5 "cover" m...

Track manuscript resubmission deadlines and automatically generate phase-appropriate task breakdowns for academic resear...

Resume an interrupted AgenTeam run with verify-first strategy.

Tailor resumes to job descriptions using verified achievements from your lexicon - never fabricates, always traceable to...

Resume the BOD/Agency Council kickoff workflow in a new chat session — restores context from memory, summarizes prior st...

Auto-invoke after task completion to generate powerful resume bullet points from completed work.

Set up a resume workspace, suggest focused job-description matches, and develop evidence-backed project bullets. Use for...

Resume a paused background mission. The mission will resume executing on its original schedule. Use when the user wants...

Resume structure, achievement bullet formulas, ATS optimization, and job-targeted tailoring for software engineers. Use...

Scores an inbound application against the role's written rubric with supporting quotes as evidence, writes a structured...

Resume a previous session by reading pipeline state and presenting current status

Resume paused work

Resume any interrupted work session — brainstorm, requirements, proposal, epic, or implementation. Scans for incomplete...

Guided pass over recent Bigweld conversations to surface repeated patterns and propose memory or CLAUDE.md updates after...

Explicit retrospective of a coding session with evidence-backed suggestions for future work.

Capture a session learning.

Look back at recent factory runs from any machine — the run records and lessons on the factory-memory branch, the issues...

Session retrospective and codebase pattern discovery, with subcommands retro (default), which extracts corrections and p...

Fill an unfilled auto-retrospective skeleton for a date, or list the skeletons still pending. Use when you say `retro fi...

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros...

Scan retro.md files across all skills, resolve open issues, and update retro entries.

Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. fo...

Analyze completed tasks to improve the Ralph system

Facilitate evidence-based project or periodic retrospectives one question at a time. 用于项目结束、停止，或周/月/季度复盘，区分事件、结果、解释、贡献和下...

Learning from failures and successes, post-mortems, continuous improvement

After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when...

Structured retrospective after completing a delivery increment or diamond. Captures learning for continuous improvement.

Review all work completed across an epic. Phase 4 Implementation

Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'sprint review', 'close ou...

Post-interaction retrospective analysis — use after completing a significant task, conversation, or phase to extract les...

Turn completed session records into verified follow-up candidates.

Facilitate productive team retrospectives with structured formats and actionable improvement outcomes

Retrospective facilitation and organizational learning for project teams. Covers retrospective formats (Start/Stop/Conti...

Identify repeated patterns in Exorex projects and turn them into reusable, documented, versioned assets. Use when Codex...

Designs, hardens and audits the system around an agent that runs on its own — bot, scheduled task, routine, automation —...

Paces a Claude subscription's usage — how fast to spend this week, what can still run at N% weekly, whether planned work...

Design and document a revenue model with structured process, quality checks, and system integration

Local wrapper around the upstream Anthropic skill. Use for iOS reverse engineering, Frida dynamic instrumentation, Objec...

Orchestrate the full reverse engineering pipeline: Extract provisional spec from existing code, refine through dialogue...

Review a task by updating last_reviewed_at timestamp. Recomputes derived status and flags any hash mismatches without ch...

Use this skill when all MVP module CDDs need a cross-document review for dependency, ownership, formula, scenario, and d...

Review a CI workflow change for trigger, permission, command, secret-reference, artifact, and release-impact evidence wi...

Review implementation for maintainability, evolvability, anti-slop, and human complexity; emit `M#` findings and durable...

Review implementation fidelity against `PLAN.md` and `AMENDMENTS.md`; emit `PS#` findings and validation-fact gaps into...

Find a code spec's Halt risks before a run: a reader that never wrote the tickets checks every one against the spec, the...

Use when the user asks to review finished uncommitted work, commit it and push it in one run. Not for planning or implem...

覆奏机制，尚书省汇总完毕提交时触发，门下省事后审查执行结果是否忠于原旨

Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-ba...

Comprehensive pre-release review pipeline. Runs /review-health, /review-arch, /review-security, /review-perf, /review-a1...

PR作成後に自律的に実行する必要があるフロースキルです。 Trigger: review, pr created, pr open

Inside a drive, when it must reach the person, write them a brief they can act on: what we understood, what we built, an...

Review a branch, diff, commit range, or pull request with a findings-first code review workflow. Use when the task is to...

Load and review the complete JSON state for a workflow project before task work. Use when the user asks to review projec...

Load this skill when looking back over a period of work in a repo: what shipped, how work flowed, and the issues the his...

Routes ambiguous review or planning to one leaf workflow. Do not use for a clear code, security, UI, architecture, or mi...

Author your live personality, revise the disposition you want to inhabit, or restore an earlier version.

Use when a learner needs a structured review session prioritizing high-value topics by recency, error history, and upcom...

When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes. Al...

RevOps workflow skill. Use this skill when the user needs Design and improve revenue operations, lead lifecycle rules, s...

When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes. Al...

Create or review revenue operations deliverables with traceable assumptions, decision criteria, ownership, and risk cont...

Update old notes with new connections. The backward pass that /reflect doesn't do. Revisit existing notes that predate n...

Show RFC details or update RFC status through lifecycle

Automate Rhino modeling through RhinoCommon, work with Grasshopper data trees, and configure Rhino.Compute workflows.

Self-contained parallel generator — invoke directly, do not decompose. Generates 3-10 app variations in parallel for com...

Rifts is the umbrella workflow: Speedrift (drift + contracts) plus optional Specrift (spec/doc drift) and optional UXrif...

Risk Assessment Creator - Auto-activating skill for Enterprise Workflows.Triggers on: risk assessment creator, risk asse...

"Assess risk of bias in research studies for systematic reviews. Use when: (1) Conducting systematic reviews, (2) Evalua...

User-invoked DevRites menu and router; no args renders the menu, a verb dispatches to the matching `rite-<verb>` skill.

Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autono...

Converge intent and live code. Use when resuming a half-built feature, after `/rite-adopt` drift, or live code may have...

Review recurring cross-feature evidence and propose durable project guidance.

Observe one GitHub PR and CI state without mutating code, Git, threads, checks, or shared state. Safe for native host sc...

Use for Roblox Open Cloud: API keys, OAuth 2.0, webhooks, scopes, token lifecycle, DataStore or messaging access from ou...

Persist player data in Roblox with DataStoreService: GetDataStore, GetAsync/ SetAsync/UpdateAsync/IncrementAsync wrapped...

筛选和验证机器人应用场景。Use for scenario discovery, workflow analysis, task decomposition, ODD, automation boundary, human interven...

Designs and implements minimal, high-value metrics for RobustMQ services and dashboards. Use when the user asks to add m...

Analyze and produce a roi analysis with structured process, quality checks, and system integration

Redesign a job role that AI now does a large part of — deliberately, instead of quietly expecting the same headcount to...

Rootly's incident-response automation model: the trigger / condition / action structure, the full catalog of trigger, ac...

朝会（standup）を実行し、出力を workspace に保存する

RouterOS packet capture and TZSP streaming for protocol debugging. Use when: capturing packets on RouterOS, setting up /...

Suggests relevant cron routines based on user context, goals, and observed patterns

Interview-style setup for Claude Cowork Scheduled Tasks. Turns your recurring tasks into ready-to-paste automation promp...

Resilience and retry patterns for reliable RPA automation.

Create detailed session retrospective with AI Diary and Honest Feedback. Use when user types 'rrr' or when ending a sign...

Covers the environmental footprint of research computing: measuring and reporting energy use and carbon emissions of com...

Covers end-to-end computational reproducibility: making a project's results regenerable with one command, determinism an...