Каталог навыков агентов

Revise a draft's substance against critique findings or a brief — structural and argumentative changes with a change log...

This skill should be used when the user asks to 'revise writing', 'fix review issues', 'polish draft', 'apply review fee...

Route writing requests to the correct installed workflow. Use when a request could mean natural prose, technical documen...

Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior. Use when adding safety guardra...

Extract and manage writing rules (style, structure, persona, publisher, custom) (project)

仅当使用者明确说"使用规则写作"、"按规则写"、"用写作规则"或等价表达时启用。启用后按十五条规则写中文：禁破折号、禁"不是A，是B"、打破三点式、删句首冗余连接词、杜绝强行升华、长短句交替且不用嵌套从句、只在文末收束、保留适当不确定性、必...

Create, inspect or update Hookify project rules for inputs, tool calls and completion checks.

Use when writing operational documentation - runbooks, setup guides, release procedures, migration guides, deprecation g...

Writes new science files following academic prose standards: third-person voice, present tense for laws, in-universe ter...

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Internal skill for creating PRECIS.md, OUTLINE.md, and ACTIVE_WORKFLOW.md. Called after brainstorm sources are gathered.

Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate...

Writing, exploit ： 将原始素材逐段塑形为一篇文章。

Writing, exploit — shape raw material into an article, paragraph by paragraph.

Shape raw material into an article, paragraph by paragraph. Use when beats are ready and the user wants to write.

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Use when the user wants to turn a pile of fragments into a polished article, shape raw material paragraph by paragraph,...

Shape a file of raw material into an article through a conversational session — candidate openings, paragraph by paragra...

Collaborative writing: shape raw material into an article, paragraph by paragraph.

Chooses the final structure for a public-facing article, guide, or docs page from fragments and beats. Use when turning...

Use this before writing any shell scripts - establishes fish shell syntax, gum integration patterns, and script organiza...

Writes production-ready shell and automation scripts (Bash .sh and PowerShell .ps1) with a mandatory adversarial audit g...

Converts hunt findings into portable Sigma detection rules: choosing the right logsource, expressing robust selection/fi...

Defines how to create, structure, and document agent skills, including required metadata, directory layout, and best pra...

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

Use when creating, updating, or improving agent skills.

Create new godot:* skills — use when adding a new skill to the godot plugin.

Use when creating a new forge-skill, editing an existing skill, when planning to contribute to forge-skills, when a sess...

Creates and refines agent skills using TDD methodology with pressure testing and rationalization detection. Use when cre...

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when creating new skill files, editing existing SKILL.md files, or reviewing skills before deployment — covers struc...

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to proce...

Writing skills IS Test-Driven Development applied to process documentation.

Helps author concise, discoverable skills using TDD-style testing. Use when creating, editing, or verifying skills befor...

Use when creating/editing/verifying skills or `AGENTS.md` agent-instruction docs, especially when routing, trigger wordi...

How to properly create and structure Claude Code skills in this project. Use when adding a new skill, restructuring exis...

Use when checking, testing, or reviewing existing skills for trigger accuracy, environment compatibility, or deployment...

writing-skills

Use when creating a new skill, editing an existing skill, or writing the agent/command that wraps one.

当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用

Use when creating new skills, editing existing ones, or verifying skill quality before deployment.

Use when writing a new SKILL.md, revising an existing skill's instructions, or converting a repeated workflow into a reu...

TDD for process documentation - test with subagents before writing, iterate until bulletproof

Use when creating a new skill. Meta-skill with template + anti-patterns.

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills...

use when touching skill

Guidance for creating new Claude Code skills following best practices

Reference for writing and editing skills so they run predictably — invocation choice, information hierarchy, leading wor...

Create Agent Skills for Claude. Use when asked to write, create, or design a skill, skillsheet, or SKILL.md file. Provid...

Use when creating, editing, or verifying agent skills before deployment. Emphasizes test-driven skill writing and tight...

Create and maintain AI agent skills for this project. Use when creating new skills, reviewing existing skills, or decidi...

Use when creating reusable process documentation. Apply TDD: baseline without skill → document failures → write skill →...

Use when a new skill has to be created (or an existing skill revised) for this framework, applies the single template, c...

Creates or improves an Agent Skill by defining a precise trigger boundary, concise procedural instructions, progressive-...

Use when creating a new skill, editing an existing skill, or verifying skills work before deployment

Guide for authoring new CodeHands skills. Use when creating a new skill, improving an existing skill, or contributing to...

Use before you change a file in skills/ or .agents/skills/, or an AGENTS.md file.

当你要创建新 skill、重写已有 skill，或把稳定 workflow 提炼为可复用 skill 时使用。

Create, edit, split, merge, port, or validate agent skills and SKILL.md packages. Use for skill architecture, trigger de...

Create, update, or validate Chakra UI slot components for styling integration

Generate a script for a dreaded social scenario — declining, asking for an extension, following up, setting a boundary —...

Use when creating implementation specification documents - ALWAYS required in Phase 2 regardless of bridge weight, presc...

Complete spec workflow - generates Run ID, creates isolated worktree, brainstorms requirements, writes lean spec documen...

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC...

Creates feature specifications capturing requirements and acceptance criteria. Use when writing specs, documenting featu...

Write technical specifications from feature requests, prompts, or tracker references. Use when asked to specify, archite...

Help users write effective specs and design documents. Use when someone is creating technical specs, feature specs, desi...

Create a build-ready spec + design doc pack (low-fi diagram, user flows/states, prototype brief, acceptance criteria) fo...

Use when writing or adding tests for Spring Boot code at a service's edges: HTTP clients that call other services (WireM...

AI 패턴 제거, 전지적 저자 시점, 체계적 인용을 통한 고품질 한국어 글쓰기 표준. 금지 어휘, 문장 종결 규칙, 어휘 다양화 전략을 정의한다. 콘텐츠를 작성하거나 검토하거나 품질을 검증할 때 사용한다.

Create, update, or validate Storybook stories with comprehensive play functions

Generates a WRITING.md file with YAML tokens for prose consistency — voice, tense, forbidden words, citation format, equ...

Writing guidelines for clear, economical prose. Reference this skill when creating or enhancing note content.

Writing style guide for prose content - program descriptions, technique pages, blog posts, and any user-facing text. Use...

Core writing standards for all Skill Stack content. Invoke automatically for any writing task. Combines anti-AI patterns...

Structural pattern analysis for writing-mode review. Performs paragraph-level decomposition and pattern aggregation. Inv...

Writing style guide for Jason Warren. Use this skill whenever writing prose, reports, documentation, or any substantive...

Human writing standards to eliminate AI-generated text patterns. This skill should be used for any copywriting, marketin...

The writing-craft skill — style and tone as applied technique: rhythm, specificity, tone modulation, and the edit passes...

Writes and validates Suricata/Snort IDS rules for network-based malware detection, covering rule anatomy, content/pcre m...

Provides SVC naming conventions, comment style, code structure order, and reset patterns. Triggers when writing or modif...

Svelte 5 syntax reference. Use when writing ANY Svelte component. Svelte 5 uses runes ($state, $derived, $effect, $props...

Paragraph-level structural blueprint for 12-page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provide...

Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Prov...

Write clear, intentional documents with minimal patchy phrasing and strong structural discipline.

Provides svc_unit.sv testbench framework, macros (TEST_CLK_NS, CHECK_EQ, etc.), and template. Triggers when creating or...

Architectural planning and ADR creation. Use when evaluating feasibility, making technology choices, or defining system...

Guides technical documentation and report writing. Applies the 7 Cs principle (Clear, Concise, Correct, Coherent, Concre...

Creates timestamped technical analysis and debugging reports following a standardized structure. Use when documenting co...

Writes technical prose (READMEs, ADRs, code comments) in the project's established human voice. Use when creating or edi...

Creates risk-based test plans and strategies. Use when planning testing, defining test scope, or documenting QA approach...

Write Vitest unit tests and browser mode component tests for TypeScript projects. Use when asked to write tests, create...

Use when writing or reviewing tests in any language, or diagnosing a suite that is slow, brittle, or hard to read. Trigg...

Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before...

How Ascribe's tests are laid out, where a new test of each kind goes, which fixture helpers to build it from, and what k...