Навыки: Разработка

Use when the request mentions `.lando.yml`, `lando rebuild` or a fixture runner and you need a contract-compliant exampl...

Use when the request mentions `.lando.yml`, `lando rebuild` or a fixture runner and you need a contract-compliant exampl...

Use this skill when the user wants to extract stay points, dwell events, OD endpoints, or meaningful stops from GPS, che...

Split a class that holds too many responsibilities into two focused classes.

Extract clinical entities from synthetic or already de-identified text with OpenMed and map them into deterministic FHIR...

Use when adding new error messages to React, or seeing "unknown error code" warnings.

Pull a code fragment into a named method to improve readability and enable reuse.

지역 변수가 서로 얽혀 Extract Method가 불가능한 거대 메서드를 별도 클래스(Method Object)로 추출. "긴 메서드를 클래스로", "지역 변수 때문에 추출 불가", "method object",...

Download GitHub repos as clean source code (no .git history) to WORKDIR. Use when cloning repos for analysis or modifica...

Give a name to a complex expression by assigning it to a well-named variable.

Extract verifiable correctness properties from ONE component artifact — a spec, the source code, or a verification harne...

Extracts ASCII and Unicode strings from a binary and classifies them into investigative categories: URLs, IPs, file path...

Extracts and interprets a Cobalt Strike Beacon configuration: decoding the encoded config block, recovering C2 servers,...

Extracts file structure (functions, classes, exports) efficiently without reading entire files, using ast-grep, Dart/Flu...

Extract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylog...

Use when user pastes a screenshot / image. Extract text, layout, intent — don't just describe pixels.

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR b...

Multi-agent coordination, spatial memory, and swarm navigation. Connect to an Eywa room so your agents share memory, cla...

Entry point for ezorm repo skills. Use to pick the right skill based on task (write YAML vs generate code, and mongo vs...

Reconstructed reference notes on US FAA approval guidance for airborne software and airborne electronic hardware, built...

Knowledge base from FAA-HDBK-006D (2020), the FAA's System Reliability, Maintainability, and Availability (RMA) Handbook...

Pull fresh follow-up call notes from a dedicated Telegram group into the CRM layer of a vault. Incremental and idempoten...

戦略選定Agent - 本質分析を受けて具体的な選択肢を提示する

Summon Claude Fable 5 (Mythos-class, xenos daimon) for long-horizon tasks. Handles model override, cost awareness, and t...

Claude Fable 5 (claude-fable-5) protocol — selection, prompting, effort tuning, token discipline. Trigger when working w...

This skill should be used when the user asks for a "Fable second opinion", wants to "check a plan before committing", ne...

Debug like Fable 5 — systematic root cause analysis with natural reasoning flow. Use this skill when you encounter an er...

Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fre...

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications,...

Emulates the reasoning habits of Claude Fable 5 — plan before executing, self-refutation, iterative verification until i...

An advanced, autonomous AI agent skill designed to execute complex, multi-step, and long-horizon tasks with high reliabi...

Фейбл руки-агенты — ручной режим оркестрации, где Fable не пишет код, а пишет спеки в тела GH issues и раздаёт готовые з...

Use when implementing any change in existing code — when tempted to clean up nearby code, add unrequested validation or...

Comprehensive, rubric-driven, whole-repository code audit that ends in a prioritized improvement plan with an executive...

Escape a failure loop — when two or more attempts to fix the same problem have failed, stop patching and re-derive the d...

A harness that makes Opus (or any Claude model) behave like Fable — it enforces seeing a task through to the end, with e...

Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY pr...

一键替换服装面料。版式图 + 面料图 → 换上新面料的样衣图，垂坠与光泽随材质变。当用户说「换面料」「换材质」「试布料」「面料上身」「同款不同料」时使用。

Provide a simplified interface to a complex subsystem.

Facebook integration for AI agents via ClawLink — browser login, no API key setup. Connect Facebook through ClawLink's h...

Facebook评论分析工具。输入帖子链接即可获取评论数据，支持分页浏览、对评论进行情感分析（积极/负面/需求/竞品），生成精美HTML报告。当用户需要查看Facebook帖子评论、分析评论舆情、了解用户反馈时使用。触发词：Facebook...

使用 sau CLI 登录 Facebook 个人主页，立即发布视频或图文，查询原作品、移至垃圾箱或永久删除。

Migrate a Jakarta Faces project from one version to another (e.g. JSF 2.3 to Faces 4.1)

AI Face Swap - Swap face in video, deepfake face replacement, face swap for portraits. Use from command line. Supports l...

Run a claim-by-claim fact-check pass on a draft article, script, or report before publication. Use when asked to fact-ch...

Verify the accuracy of claims and statements by extracting individual assertions, identifying authoritative sources, cro...

Answer economic and financial data questions with FactIQ data: US and international indicators, trade, markets, earnings...

Coding factory — transforms a spec into a reviewed PR via BUILD → INSPECT pipeline with adversarial review. Use when you...