Каталог навыков агентов

> Category: [Project | Development | Quality | Operations]

Show the state of terum-skills on this machine — team, clone, session hook, pending work, machine facts — and whether a...

cheat-on-skill 的陪跑进度 skill。用户问“今天该干嘛”“我现在做到哪了”“继续学”“打卡”“我卡住了”“下一步是什么”时触发。读取 .skill-state.json 的 active.progress 和 learni...

Atomically update task status across TODO.md and state.json. Invoke when task status changes.

用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估。

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake m...

Use when auditing Codex skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake mo...

Audit the installed skills and decide which to keep, improve, merge or retire. Use when taking stock of the skill librar...

Use when learned skills exceed 10 per location or need consolidation. 4-step stocktaking with character budget awareness...

Skill file structure, naming conventions, directory layout, and frontmatter requirements. Use when creating skill files...

Interview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, aut...

Find repeated manual work in Littlebird activity. Use to draft the next automation skill worth building. Read README.md...

Audit generic AGENTS.md, CLAUDE.md, and SKILL.md instructions for deterministic drift and model-era obsolescence candida...

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-inject...

Review a third-party skill or plugin before you install it: run skill-scan-gate on the folder, lock it with cc-plugin-lo...

当用户想检查、同步、发布或排查 Codex 技能同步器时使用。

Syncs .claude knowledge files with the codebase. Detects stale reference files (hook catalogs, type indexes, schema refe...

Sync a skill's content against the upstream library it covers — check whether the API descriptions, version references,...

Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, lis...

Maintains synchronization across model directories after modifying skills, agents, or prompts. Ensures consistency betwe...

Use when installing, copying, or checking local skills across agent harnesses. Treat ~/.agents/skills as the source of t...

Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.a...

Safely validate, publish, and track a local SKILL.md directory across GitHub, Awesome Codex Plugins, HOL Registry, skill...

Sync skills from `.claude/skills` and `.codex/skills` into `.gemini/skills`. Use when the user wants to import other age...

Compose multiple installed skills into one coordinated execution stack with ordered packets, minimal context load, and d...

Load when you struggled with something docs would have helped, when you're about to move on from a complex area you now...

Design the architecture for a multi-command skill system — the shared state schema, the command map, the router, and the...

Audit and optimize a skill system with evidence. Use for skill architecture, token or context waste, role and prompt bou...

AI-powered task management for structured, specification-driven development. Use this skill when you need to manage comp...

技能创建模板。复制此目录并修改 SKILL.md 即可创建新技能。请将所有 <占位符> 替换为实际内容。

Brief description of what this skill does

> 核心コンセプト: "{{CORECONCEPT}}"

Generate custom skill/command from template

Bootstrap a new standalone skill repo under gaia-research/ from the canonical template set at gaia-research/gaia-researc...

Copy-paste scaffold for creating a new Antigravity Agent Skill. Use when you want to author a skill folder that follows...

Brief description of what this skill enables. Include trigger keywords that should activate this skill. Triggers on keyw...

What this skill does. Use when user mentions "keyword1", "keyword2", or "keyword3". Keep under 1,024 characters and incl...

This skill should be used when the user asks to "specific action", "another action", or mentions "specific keyword". Pro...

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collecti...

<one-line description of what the skill does and when to use it>

One to three sentences describing what this skill does and the conditions under which an agent should activate it. Start...

Briefly describe what this skill does and when it should be used.

{{Brief tagline describing what this skill does}}.

Template for authoring a new data-engineering skill. Replace this text with a third-person summary of what the skill doe...

Template for creating new CodeHands skills. Copy this directory and fill in all sections. Use when authoring a new skill...

Example skill for XPR agents

[1-2 sentence description of what this skill does]. Triggers on [specific phrases/contexts that should activate this ski...

> 核心コンセプト: "{{CORECONCEPT}}"

Verifies that the skill system is working correctly.

Validate skill files for structural compliance and behavioral correctness. Four modes: static linter, spec, category rub...

Use when Codex skill files need structural, behavioral, category, or coverage validation.

Validate skill files for structural compliance and behavioral correctness. Three modes: static (linter), spec (behaviora...

AL App/Test project layout diagnosis for Business Central. Use when the main app compiles test sources, AL0297 appears o...

Complete testing environment setup and tool verification. Use at project start, when onboarding new developers, or when...

Test Claude Code skills in real-world scenarios to validate functionality, usability, and effectiveness. Task-based test...

The Skill Tester is a comprehensive meta-skill designed to validate, test, and score the quality of skills within the cl...

Validate and score Claude Code skill packages for quality, completeness, and best-practice compliance. Tests Python scri...

Skill Tester

Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural require...

Validate, test, and score the quality of skills within the claude-skills ecosystem. Comprehensive meta-skill: structure...

Test and validate agent skills against the Agent Skills Specification v1.0. Use before deploying skills to ensure spec c...

Skill Tester

Validates all CI skills in this repo. Checks Agent Skills spec compliance, gh-aw workflow compilation, permission correc...

AL test development patterns for Business Central. Use when creating test codeunits, writing Given/When/Then test proced...

Test Agent Skills from tests/skill_cases.yaml files. Use when validating whether a Skill triggers correctly, produces a...

Provides test cases and validation tools for skills. Use when creating tests for a new skill, adding regression tests af...

Test-Driven Development mindset and principles. Use when learning TDD, need to understand why test-first matters, facing...

Guide the selection and combination of testing tools based on environment, phase, and test type. This skill integrates m...

Comprehensive pre-PR testing using TestSprite MCP. Use before opening a pull request, after completing a task, or when f...

Implement semantic theories and Python/Z3 code with TDD. Invoke for Python-language implementation tasks.

Threat model agent skills, skillsets, and install paths. Use when Codex is asked to identify risks in a skill, define as...

Audit any Lattice SKILL.md for language compliance — removes rationale prose, converts soft language to imperatives, add...

Turn an existing pi skill into an isolated subagent and wire it into a project's implementation pipeline. Decides fitnes...

将现有 Skill、Prompt、SOP 或 Agent 操作说明拆解为可执行、可监控、可重试的 Workflow 规格；识别真实节点、共享子工作流、工具调用、状态、分支、循环、 提示词、数据契约和验收方式。适用于用户要求把一个 Skill...

Enable, disable, and manage Claude Code skills. Use when the user asks to enable/disable/toggle/manage skills, check ski...

Interactive guided tour of all available AI coding skills with live demos. Walks through headline capabilities, offers t...

Check and apply upstream updates to installed skills. Reads pending-updates.json generated by the cron checker, spawns h...

AL translation and localization for Business Central. Use when working with XLF files, NAB tools, or implementing multi-...

当需要系统性地提升在某个领域的能力以建立自信时调用此模型

Measure whether a skill's description triggers on the prompts it should and stays quiet on the ones it should not, using...

Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long...

Empirically test whether a lacquer skill needs an edit by mining real session transcripts for friction, proposing a boun...

Use this skill whenever the user wants to learn how to manually do what an existing Claude skill does, or when they want...

Implement Typst documents following a plan. Invoke for Typst-language implementation tasks.

Report the ultra crown rung, where the caller chooses convergence or exploration and a depth per gap.

Self-improvement protocol for Neo4j agents. Instructs agents to report skill updates needed.

Upgrade an existing Codex skill through a structured loop: inspect, compare, improve, validate, test, and finalize with...

Meta-skill for keeping all exceptd skills current — fires on new CVEs and CISA KEV listings, ATLAS updates, framework ch...

Apply improvements to Claude Code skills systematically. Workflow for planning updates, implementing changes, validating...

Updates skills during project work according to their contracts. Adds references, improves explanations, and refines exa...

Research-backed skill refresh workflow for updating existing skills with TDD checkpoints, memory-aware integration, and...

Self-assessment and auto-update for Claude Code's installed skills, CLAUDE.md files, and reference data. Audits for stal...

Upgrade any skill to v5 Hybrid format using decision theory + modal logic

Core skills system that manages loading and using other skills through progressive disclosure. Load at startup to enable...

Report how often each developer-os skill has fired in local Claude Code session history (calls in the last 30 days, last...