Каталог навыков агентов

Compile a course module into the Andamio import format for publishing.

Compile .agents knowledge wiki.

Load the marketing assessment pipeline lessons, pitfalls, and quality checklist before generating or reviewing a client...

This skill should be used when the user asks to "分析编译效率", "分析编译时间", "查看头文件依赖", "保存编译命令", "提取编译命令", "生成编译脚本", "保存这个文件的编译命...

Guide for building CompCert, the formally verified C compiler, from source. This skill should be used when compiling, bu...

Build a structured intent spec through guided conversation, one decision at a time with a recommended answer for each. U...

Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when compiling lecture slides.

Compile a .tex with latexmk and report ranked errors with file:line attribution across \input'd files, plus a diff again...

Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "r...

レポートコンパイルエージェント - 分析結果のMarkdownファイルを統合HTMLレポートに変換。/compile-report [出力パス] で呼び出し。

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a...

Step-by-step CDD implementation workflow for scala-ts — change the type first, follow compiler errors, pin generated out...

Use when 解释或评估 CinderX 的 IR、优化 pass、指令调度与寄存器分配原理；指令规格用 isa-instruction-lookup。

Use whenever the user says "compile the design system", "build a design system", "build the brand system", "make me a to...

Compiles a comprehensive entry for a named entity by scanning ALL files, gathering every mention, and assembling a struc...

Produces and shrinks WGSL shaders. Converts GLSL (WebGL 1 and 2, Shadertoy mainImage code, Vulkan GLSL 450, compute shad...

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submi...

Surfaces what the agent would change and kept to itself — a decision it would make differently, effort it saw wasted, a...

Write a firm, effective complaint letter that gets a resolution. Use when asked to write a complaint letter, complain to...

Finalize a completed ticket: write 5-final.md, update 4-progress.md, commit.WHEN TO USE:- All required tests pass (via /...

Complete task: validate, document, review, commit, and merge to develop. Use when all implementation is done and ready t...

Browse, reserve, complete, and submit AgentPMT bounty jobs to earn credits using wallet-signed API calls. Use when the a...

Complete all tasks in order in the TODO.md file.

Complete checkpoint and finalize phase

AI 增强版 LaTeX 示例智能生成器，实现 AI 与硬编码的有机融合。AI 做"语义理解"（分析章节主题、推理资源相关性、生成连贯叙述），硬编码做"结构保护"（格式验证、哈希校验、访问控制）。用于用户要求"填充示例内容/生成示例/补充...

Mark an idea as completed when all its derived tasks are done. Note: Ideas are automatically closed when converted to ta...

You MUST validate that the implemented feature meets its goals and quality gates. This workflow is recursive: if follow-...

Implement a change end-to-end from a freeform prompt - settle the requirements, design the engineering approach and get...

Archive completed milestone and prepare for next version

Close a completed GitHub milestone and generate a completion summary. Use when a sprint or release is finished and needs...

Complete a project milestone

Provide complete, thorough responses Use when enforcing code quality standards. Quality category skill.

Finalize the current enhancement session — write the Sessions/E{n} retro note, tick the row in the master plan, update T...

This skill should be used when the user asks to "perform complex task", "implement advanced pattern", "handle multiple s...

A complete skill with all fields present for testing

A complete skill for E2E testing

A complete skill for E2E testing

A complete skill for E2E testing

Mark a rolling-wave slice done on explicit user authority, regardless of its current lifecycle status or missing impleme...

Interactive conversation to resolve [NEEDS CLARIFICATION] markers using /speckit.clarify command. Claude asks questions...

Complete the next task in the TODO.md file

Complete an in-progress task by running clean-code, staging, committing, and closing the bead. Use after /verify-task.

Achieves 100% test coverage with minimal redundancy through progressive test writing. Writes tests one-at-a-time with im...

> Compiler: skill-compiler/1.0.0

Finish a Magpie upgrade in one run. Checks this machine and this project against the installed version and shows one sho...

Status: Completed

Guide for using completers — TokenCompleter and MessageCompleter for text generation during RL rollouts and evaluation....

Use after verifying-layer-documentation to fix all gaps found. Reads gaps.md and adds missing documentation.

Use this skill when archiving a completed milestone, preparing for the next version, marking a milestone complete, shipp...

구현 완료 선언 전 검증하는 통합 프로세스.

This skill should be used when a reviewed task is ready to close, for example "close this task", "finish the task", "mar...

Completion Check: Verify Infrastructure Is Wired

Positive checklist for finishing a /create-module or /add-operation task. Use right before declaring done or opening a P...

Completion checklist - when is a task truly done

Ce skill doit être utilisé quand l'utilisateur demande à "compléter un cahier des charges", "remplir une offre de servic...

Hard discipline for verification and completion claims: do NOT claim tests passed, a fix works, or a task is complete wi...

Strictly audits a defined ChefFlow scope for completion, cohesion, wiring, and proof without expanding it. Use when the...

Validates agent claims against evidence trail. Use when verifying an agent has actually done what it claims — auto-fires...

Ralph Wiggum-style completion promise tracking for System 3 sessions. Use when starting a new session with user goals, w...

Prove completeness for non-trivial implementation, migration, translation, content, integration, and audit work by inven...

Produce the smallest user-facing report that preserves every material fact about a task outcome, by classifying the term...

Verifies that work is actually complete before it is claimed to be — running the checks, reading the output, and confirm...

Verifies a completion, fix, passing, compatibility, release, or readiness claim with fresh task-specific evidence mapped...

Verification system that ensures tasks are truly complete before marking them done, preventing premature completion clai...

Verifies implementation completion by running acceptance tests and triggers retry loop on failure.

Expert in complex functions, contour integration, residue theory, and conformal mappings

Refactor complex case statements and deeply nested code using appropriate strategies. Use this skill when you identify c...

Use when building a RAG pipeline that ingests PDFs, Excel, CSV, or images — especially when debugging silent data loss,...

Comprehensive toolkit for creating multi-tab Excel workbooks for startups and scale-ups. Use this skill when building fi...

复杂探索资产化 / Complex Exploration：当用户面对复杂、不确定、多轮迭代的产品策略、Roadmap、商业化定价、竞品定位、复杂 PRD 前置探索、项目复盘或方法论沉淀任务时使用。它先判断任务类型，暴露隐含假设，重构真正问...

A framework for building scalable products by designing for the most difficult use cases first rather than a traditional...

Configure with complex join helper operations. Auto-activating skill for Data Analytics. Triggers on: complex join helpe...

When implementing complex algorithms, mathematical formulas, or intricate business rules, add com... Use when documentin...

Use AgentPMT external API to run the Complex Math Tool tool with wallet signatures, credits purchase, or credits earned...

Use AgentPMT external API to run the Complex Mathematics Engine tool with wallet signatures, credits purchase, or credit...

此技能專注於 .NET 測試中的複雜物件比對場景，使用 AwesomeAssertions 的 BeEquivalentTo API 處理各種進階比對需求。

Orchestrates multi-file tasks by delegating to parallel sub-agents. Use when a task spans multiple files or components a...

Universal operational discipline for solo or small-team execution on complex multi-layer projects (research line + produ...

Multi-step reasoning patterns and frameworks for systematic problem solving. Activate for Chain-of-Thought, Tree-of-Thou...

Production patterns for managing complex application state in React without Redux, Zustand, or other state libraries. In...

Handle complex-valued tensors in PyTorch for astronomical imaging applications. This skill should be used when working w...

Complex skill for testing directory support with nested dirs, binary files, and multiple file types

Audits custom composite widgets—including comboboxes, listboxes, trees, treegrids, grids, menus, tablists, carousels, co...

Find focused refactor hotspots.

Code complexity guidelines to keep cyclomatic complexity below 6 using strategy patterns or dispatch tables. Use when wr...

Analyze Python package build complexity by inspecting PyPI metadata. Evaluates compilation requirements, dependencies, d...

Challenges over-engineering and identifies unnecessary complexity before implementation. Use when planning features, des...

AI-based complexity assessment for task analysis. Use when determining the appropriate workflow, phases, and validation...

Trigger: complexity, Big O, cyclomatic, nested loops, queries in loops. Evaluate control and algorithmic complexity wher...

Analyzes code complexity metrics and identifies areas that are too complex for developers to easily understand

Calculates a complexity score (1-50) from a user prompt. Analyzes keywords, scope indicators, quantity modifiers, and ne...

Corrective playbook for shipped code with bad complexity. Finds repeated work, nested scans, N+1 access, and wrong data...

Lower Big-O on existing code via a one-transformation-at-a-time playbook with verify-revert-stop. For new code use lemma...

Estimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementat...

Laravel guidance to keep cyclomatic complexity low; flatten control flow, extract helpers, and prefer table-driven/strat...