Каталог навыков агентов

Globally retime a finished short by SPEED (default 1.25x) — the LAST step of the per-span edit chain. Video setpts + pit...

Use when Laravel/Pest test suites are slow, CI duration is growing, individual tests take seconds, or the user asks to s...

Finds the shortest path to done and takes it — no detours, no nice-to-haves; invoke via /speedrun when the only goal is...

Express-based REST API design patterns for the video rendering service. Use this when creating or modifying API endpoint...

Backward-compatible video template versioning and composition registry management. Use this when creating alternative vi...

TypeScript interface and type definitions for video data structures. Use this when defining types in src/lib/types.ts, c...

AWS SDK v3 S3 client operations for video uploads with credential management and error handling. Use this when uploading...

Accessibility guidelines for video content including contrast, timing, and readable typography. Use this when designing...

React component patterns for Remotion video compositions using frame-based rendering. Use this when creating or modifyin...

Inline React styling for Remotion video components using theme constants. Use this when styling video compositions, posi...

Fixed 1080x1920 pixel video format with percentage-based positioning. Use this when laying out video compositions, posit...

TypeScript and Remotion-specific coding style conventions for naming, formatting, and organization. Use this when writin...

Minimal, evergreen code commenting focused on why over what. Use this when adding comments to complex logic, frame calcu...

Project structure, git workflow, and environment configuration standards. Use this when organizing files, managing depen...

Express middleware and async error handling for video rendering operations. Use this when implementing try-catch blocks...

Defines the complete technical stack for the Cawpile video generation service. Use this when making technology choices,...

TypeScript-based input validation for API requests and video data structures. Use this when validating request bodies in...

Vitest-based test writing with mocking strategies for Remotion and AWS services. Use this when creating test files (__te...

Create, edit, and validate spell definitions (YAML/JSON) that compose connectors and step commands into end-to-end spell...

Check spelling in README files.

Schedule a moflo spell to run on the local machine via the moflo daemon (cron, interval, or one-time). Use when the user...

Meta-audit skill for spellbook development. Spawns parallel subagents to factcheck docs, optimize instructions, find tok...

Use when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific p...

USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use thi...

Analyze documentation, UI strings, comments, and user-facing text for spelling, grammar, clarity, and style. Scope: vali...

Show current Claude Code spend by project and branch via BudgetClaw

Execute one governed outbound payment through Runx Hosted with approval and provider readback.

When the user wants to analyze procurement spend, identify savings opportunities, or classify expenditures. Also use whe...

Forecast Claude Code spend to the end of the week or month from the daily session trend on the Agent Monitor dashboard —...

Shared step of the marketing playbooks (make-static-ads, research-market, run-paid-campaigns, work-with-creators): gets...

Gate any billable action (GPU pods/instances, paid APIs or tiers, cloud credits) behind a cost estimate, a live balance...

Analyze Pollinations revenue, pack purchases, and tier spending patterns. Query Polar for payment history and Tinybird f...

Generate a categorized spending breakdown with month-over-month trends.

Prüft Aufwendungsersatz und Spesenabrechnungen im Handelsvertretervertrag: gesetzlicher Aufwendungsersatzanspruch nach §...

SPH0645 is a digital MEMS microphone that outputs PDM (Pulse Density Modulation) audio via I2S interface. Convert PDM to...

Control Sphero Mini robot ball via Bluetooth Low Energy. Roll, change colors, read sensors, draw shapes, and play with c...

Generate comprehensive Python documentation with Sphinx. Covers autodoc for API extraction, Napoleon for Google/NumPy do...

コード変更、API変更、新機能追加時にSphinxドキュメントを自動更新します。公開APIやインターフェースの変更、新クラス・関数・モジュールの追加、アーキテクチャの重要な変更、ユーザーからの明示的なドキュメント更新依頼時に起動します。My...

Sphinx documentation system expertise for technical and API documentation. Configure projects, autodoc for Python APIs,...

Build, structure, and maintain technical documentation sites using Sphinx, reStructuredText (rST), MyST Markdown, and au...

Implement SPI full-duplex communication, clock polarities (CPOL/CPHA), chip select multiplexing, and DMA transfers.

This skill should be used when the user asks to "dump SPI flash", "read EEPROM through OpenOCD", "dump flash via MCU", "...

Verify Strong Parallelism Invariance (SPI) and GF(3) conservation for 3-way color streams with arbitrary precision.

Evaluates the semantic propositional content of image captions by transforming them into scene graphs that encode object...

>- Run automatic SPICE simulations on subcircuits detected from KiCad schematic analysis — validates filter frequencies,...

Spiceflow is a super simple, fast, and type-safe API and React Server Components framework for TypeScript. Works on Node...

Web crawling and scraping with analysis. Use for crawling websites, security scanning, and extracting information from w...

Generate Scrapy spiders with best practices when creating new spiders, crawlers, or implementing scraping patterns. Auto...

Weave authentication webs with patient precision. Spin the threads, connect the strands, secure the knots, and bind the...

SpiderFoot automated OSINT framework with 200+ modules for comprehensive target profiling. Use when: running automated O...

Design and document a spiff program with structured process, quality checks, and system integration

"Provides SPIFFE in Secure Product Identity Framework for Applications"

Spike an idea through experiential exploration, or propose what to spike next (frontier mode)

Implement N approaches as separate branches, then compare side-by-side. Removes "implementation effort" as a variable fr...

Bounded spike: web research plus local study to a verdict.

Build a small throwaway artifact that answers exactly one open design question, then move it off the working branch onto...

Throwaway experiments to validate feasibility before building.

Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.

Throwaway experiments to validate an idea before build.

Create a hypothesis-driven, time-boxed spike ticket (Hypothesis/Budget/Kill Criteria/Disposition). Exempt from AgDR + co...

Run an exploratory, non-production experiment to decide whether an idea deserves a project. Reproduce current behaviour...

Opens a throwaway spike of this project in its own git worktree, beside the project directory, with every hook off there...

Use for throwaway experiments that validate an idea before a real build.

Interrogate authority before planning a feature, refactor, migration, rewrite, backfill, event-sourcing design, dual-wri...

Close a spike via the disposition gate — `--promote` files a [Feature] follow-up, `--discard` writes a memo.

OI-3 spike harness — heavy consumer skill, BASELINE arm. Builds an incident post-mortem and sources the readability stan...

OI-3 spike harness — heavy consumer skill, FORKED arm. Builds an incident post-mortem and sources the readability standa...

OI-3 spike harness — heavy consumer skill, INLINE arm. Builds an incident post-mortem and sources the readability standa...

Frame a spike so its result is a decision, with the question, the cheapest experiment, a numeric exit criterion, the mea...

Guide for spike-driven development methodology. Use when starting new features, testing architecture patterns, integrati...

Run bounded spike work to test feasibility before committing to a normal implementation path. Use when Spec wants Builde...

OI-3 spike harness — the FORKED (context fork) readability-guidance variant. Same payload as the inline variant but decl...

OI-3 spike harness — the INLINE (non-forked) readability-guidance variant. Surfaces the shared readability standard into...

Internal harness probe for the OI-3 readability-guidance spike. Use only when explicitly told to invoke spike-probe. Ver...

分布式训练梯度尖刺 (Gradient Spike) 根因定位。基于梯度监控数据 (trend.db/CSV)、 msprobe dump 统计数据，三阶段渐进式从异常坐标定位逐层深入到算子级根因。 当用户明确指明分析梯度尖刺问题时使用此...

Spike Test Setup - Auto-activating skill for Performance Testing.Triggers on: spike test setup, spike test setupPart of...

Hypothesis-driven debugging methodology for TMNL. Progressive isolation (simple → complex), H1/H2/H3/H4 tagging, and Eff...

Builds a Canvas 2D knockout word whose traced outline is roughened and grown into hundreds of hand-drawn spikes, each a...

Package spike findings into a persistent project skill for future build conversations

SpikingMoE — spike-driven Transformer with LGN-inspired Mixture-of-Experts (MoE) for dynamic computation in SNNs

Delegate a task to a separate Claude Code session, optionally with its own worktree and Jira ticket. Use when asked to '...

Hand a side task found in the current thread to a new agent in its own Herdr worktree, with a brief that gives it the th...

Master the consultative sales methodology trusted by enterprise sales teams worldwide. Use Neil Rackham's research-backe...

This skill group covers the calculation and visualization of spin textures from

Backend engineer — APIs, system design, performance, distributed systems, and service scaffolding.

Backend engineer — APIs, system design, performance, distributed systems, and service scaffolding. Use when asked to "de...

Design and spec an API — endpoints, request/response shapes, error codes, auth pattern, pagination. Applies Stripe's con...

Find and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why...

Knowledge base from "Spinning Up in Deep RL" by Joshua Achiam (OpenAI, MIT-licensed). Use when applying Achiam's framewo...

PM-GATED, never EM-initiated. Fork a mid-session topic into a handoff.

Seed a new sibling repository out of the project you are standing in: triage what travels, write the new repo's sync wat...

Use when extracting a project into its own repo — a venture spinout (e.g. a product leaving its incubator repo) or a san...

Choose the right commercialisation pathway for a research result: spin-out (equity-based), licensing (royalty-based), or...

Use when creating, reviewing, or debugging SPIP CVT forms — canonical HTML wrappers, field/global errors, `charger`/`ver...

Use for SPIP translation/i18n work — creating, editing, or auditing language files (lang/prefix_XX.php, lang/paquet-pref...