Каталог навыков агентов

Cadre RenooLab spécialisé pour qualifier le métier, rechercher réellement des professionnels via le MCP et comparer prof...

Audit, write, or revise renovate.json. Use when adding Renovate, troubleshooting unexpected (or missing) update PRs, har...

Configure Renovate Bot for automated dependency updates. Keep packages secure and up-to-date with customizable rules, gr...

Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates...

Generate Renovate configuration for automated dependency updates. Triggers on "create renovate config", "generate renova...

Add or extend Renovate with a seven-day minimum release age and immutable updates: lock files and integrity hashes, GitH...

Turn a renovation idea into a realistic scope, budget, and sequence before you hire anyone — so you go in informed inste...

Respond to a rent increase strategically — check its validity first, price your alternatives honestly, then negotiate wi...

Model rent-vs-buy honestly — year-by-year net position for both paths including the assumption everyone drops (the rente...

Write a standout rental application / cover letter to a landlord or letting agent. Use when asked to write a rental appl...

Query MBIE/Tenancy Services NZ rental bond and market-rent statistics, including quarterly/monthly bonded-tenancy counts...

Track rental income, expenses, ROI, and cap rate per property.

Know your position as a tenant when a fire, flood, storm or other disaster damages your rented home: whether rent is sti...

去 AI 味：让文案、图像、视频等交付物读起来、看起来像具体的人为具体受众认真做的。用户嫌内容“AI 味重”“像模板”“不像人写的”，要求润色或本地化文案、重画或替换生成素材、清理噪点、制作宣传图与截图、剪预告片、清理生成来源标记，或 od...

Query Renzo crypto liquid restaking protocol — DeFi vault yields, TVL, ezETH exchange rates, EigenLayer operators, suppo...

Provides the only correct mechanism for operating Reolink network cameras locally — the installed `reolink-cli` binary p...

Reopen completed increments, tasks, or user stories when issues are discovered. Validates WIP limits, creates audit trai...

Reopens, one terminal tab each, the Claude Code sessions that were running before the terminal, the IDE or the computer...

Realign a drifted listing into a logical order under one stated principle, moving items and rewording nothing. Use on a...

Use when asked to reorder a drifted listing under one stated principle, moving items only and rewording nothing. Not for...

Reorganize project documentation with bilingual (English/Japanese) structure. Use when asked to "reorganize docs", "upda...

Generate coaching notes for a manager preparing a 1:1 with a rep, covering activity, engagement quality, conversion effi...

Leader's prep on a single rep before a 1:1 - their pipeline, recent activity, what they've been working on per chat and...

Найти ЖИВЫЕ чужие треды (GitHub issues/discussions) по темам, где у нас есть РЕАЛЬНЫЙ боевой опыт и артефакты, и ответит...

Diagnose and repair Operator memory load failures.

Use when paired-end reads need to be reordered so mates appear consecutively, or when preparing BAM files for featureCou...

Repair a relationship after an argument — reconnect, own your part, and rebuild trust — instead of the cold silence that...

Implement regenerative recovery using triage, scaffolding, and progressive rebuild. Covers damage assessment, wound clas...

Get a landlord to actually fix things — the repair request that creates a record, the escalation ladder from reminder to...

Automated geometry repair using RasFixit and quality validation using RasCheck. Handles blocked obstructions, generates...

信号塔修复 - Stella尝试修复或建造信号发射装置,希望联系地球或发送求救信号

Classifies ComfyUI prompt/execution errors and plans a minimal partial rerun. Use whenever a submit_prompt result contai...

Reviews a customer's post-first-purchase flow, reorder prompts, replenishment timing, second-purchase incentives, and pi...

Any component rendered many times — cards, list rows, table cells, nav items, tiles, KPI widgets, feed entries — is a fi...

Detects recurring workflows across repository history, task notes, issue records, prompts, and project documentation, th...

Run repeatedly apply skill.

Invariant set repelling nearby trajectories

Create publication-quality visualizations of immune repertoire data including circos plots, clone tracking, diversity pl...

Proofreads and tightens supplied text while preserving meaning and voice. Use only when the user explicitly asks to reph...

Interactive REPL programming environments reference. Covers IPython magic commands, ptpython, Jupyter console for Python...

Expert skill for building interactive REPLs with rich editing and evaluation features

Run and maintain the REPL PTY-based end-to-end test after code changes. Use when implementation is complete and you need...

Imported skill replace from anthropic

แทนที่เนื้อหาในไฟล์หรือโค้ดด้วย regex หรือ AST-based patterns

Replace a type-switch or repeated type-checks with polymorphism so each subclass handles its own behaviour.

타입·상태별로 반복되는 switch/if-else 분기를 다형성(인터페이스 + 구현 클래스)으로 치환. "switch를 다형성으로", "타입 분기를 클래스로", "strategy 패턴", "/replace-condi...

명령형 for/while 루프를 Stream API/Collection Pipeline으로 변환하여 데이터 흐름 의도 명확화. "스트림으로 바꿔", "루프를 파이프라인으로", "for문 stream", "/repla...

Replace a bare numeric or string literal with a named symbolic constant.

说明这个 Skill 做什么、何时使用，以及必要的排除边界。

임시 변수를 메서드 호출(query)로 치환하여 중복 제거·추출 용이성 확보. "임시 변수 메서드로", "temp 제거", "지역 변수를 쿼리로", "/replace-temp-with-query" 요청 시 사용. 단...

Replace a local variable that caches an expression with a method call so the expression becomes reusable.

State what the skill does and the concrete requests that should trigger it; include a meaningful boundary when a nearby...

Describe what the skill does and the concrete user requests that should trigger it.

Use when REPLACE_WITH_A_PRECISE_TRIGGER. REPLACE_WITH_THE_BEHAVIORAL_CONTRACT.

Replace sentence-by-sentence revised or paraphrased text back into an original paper or document while preserving the or...

Compiles a Visual Intent Object into a ComfyUI background-replacement prompt JSON by driving the inpaint template with a...

Provides intuitive find & replace CLI with JavaScript regex and string-literal mode. Use this skill when performing text...

Iterative deep planning with critiques and alternatives. Use when facing complex design decisions requiring thorough ana...

Iterative deep planning with critiques and alternatives. Use when facing complex design decisions, cross-platform change...

Replay fuzzer divergences to reproduce bugs, find root cause by comparing Ivy AST interpreter vs Boa bytecode execution

Validate every rule change on deterministic replay fixtures through the same code path as live paper before it may touch...

Replay blackbox sensor data to flight controller (SITL or HITL)

This skill should be used when the user asks to "debug", "create test script", "analyze replay report", "why isn't my ga...

Reproduces any match deterministically from rules version, seed and action log, and locates the first divergence, illega...

Rebuild the graph or re-process archived events with just replay — re-produces events from the S3 archive back onto the...

Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mist...

Practice trading in TradingView replay mode — step through historical bars, take trades, track P&L. Use when the user wa...

Replays a CARLA .log recorded by the recorder — the whole run or a time window, at any speed, following a chosen actor,...

Use when independently verifying a supplied PoC against fresh live before/after deployments.

A menu-bar share lane for turning game clips, screenshots, and quick notes into send-ready handoffs without Finder hoppi...

Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model...

Analyze Sentry session replays to surface UX patterns, pain points, and user journeys for a given product area. Use when...

Prove the simulation is deterministic by re-running a seeded scenario and diffing its order log and world-state hash aga...

Orbit Wars の対戦ログをブラウザで再生するスキル。ローカルの self-play ログ (data/lake/selfplay) と Kaggle スクレイピング済みエピソード (data/lake/kaggle_episodes...

This skill should be used when the user asks about "replayability", "roguelike design", "roguelite", "meta-progression",...

Use when you need to record or inspect an agent browser run in Replay, test a local app with the host agent browser usin...

When the user wants to design or optimize replenishment strategies, determine replenishment policies, or improve invento...

Same-design migration — re-platform a site to AEM Edge Delivery (or any clean front end) keeping its current design near...

Clean-room app cloning pipeline in eleven parts: reverse-engineer an app into a recon map, plan the stack and schema, re...

Plans the stack, database schema and API for an app clone, from the recon map replica-recon wrote. Picks boring, managed...

Plan the stack, schema, API and build order for a replica from its recon map or supplied requirements. Use for replica a...

Builds the backend of an app clone: auth, database migrations and access rules, payments with Stripe, email, background...

Build auth, database, test payments and official integrations for a replica. Use when a replica needs a real backend or...

Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle ch...

Name and rebrand a replica with original identity, check contrast and scan for old brand traces. Use for replica naming,...

Rebuilds an app screen by screen from the recon map: app shell first, then the core flow as a vertical slice, then every...

Implement a replica from its recon map and architecture, starting with a working core flow. Use for building replica scr...

Scans this computer read-only and reports which Replica Crew target types it can build today (web, desktop, android, gam...

Redige a replica do autor e cobre as providencias preliminares (CPC 350-353): manifestacao sobre as preliminares e os do...

Single entry point for cloning apps and websites in Claude Code or Codex. Picks the mode (product, faithful, study) and...

Ships an app clone live on the user's own domain: a preflight gate (tests green, parity must-haves done, rebrand sweep c...

Prepare replica deployment, verify tests, required feature parity and branding, then publish within the user-authorized...

Rebuilds an app's design system for a clone: colour roles, type scale, spacing, radius, shadows and every component with...

Create design tokens and component specs for a replica with original assets; check contrast. Use for replica design syst...

Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, co...

Measure replica feature parity and screenshot layout differences using local Python tools. Use to compare a replica to i...