메뉴
이 저장소의 skills
SkillsMP는 tomevault-io/skills-registry에서 17,125개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
tomevault-io/skills-registry수집된 skill 17,125개 중 40개를 표시합니다.
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent…
원문 언어: 영어
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent…
원문 언어: 영어
Use when working with a comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
원문 언어: 영어
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or…
원문 언어: 영어
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending…
원문 언어: 영어
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent…
원문 언어: 영어
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent…
원문 언어: 영어
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes,…
원문 언어: 영어
Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides. Use when this capability is needed.
원문 언어: 영어
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and…
원문 언어: 영어
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection. Use when this capability is needed.
원문 언어: 영어
This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces. Use…
원문 언어: 영어
Creates properly formatted Git commits following conventional commit standards for the MCPSpy project. Use when asked to commit changes, stage files, or manage git workflows. Has access to git status, diff, checkout, add, and commit commands.
원문 언어: 영어
Creates well-structured GitHub issues for the MCPSpy project using the gh CLI tool. Use when asked to create issues, report bugs, or document features. Follows conventional naming with feat/chore/fix prefixes and maintains appropriate detail levels.
원문 언어: 영어
Handles all Golang testing tasks including running tests, writing new tests, and fixing test failures. Follows MCPSpy testing conventions with require for critical assertions and assert for non-critical ones.
원문 언어: 영어
Detects ESLint configuration and available commands in a repository. Returns structured JSON output designed for consumption by the quality-gates-linter agent. Checks for ESLint config files, extracts lint commands from package.json, Makefile, and CLAUDE.md,…
원문 언어: 영어
Create git worktrees in .worktrees/ for working on different branches without touching current working directory. Use this when the user needs to switch to another branch for quick fixes or temporary work while preserving uncommitted changes in their current…
원문 언어: 영어
Remove git worktrees from .worktrees/ directory and clean up all traces. Use this when the user wants to delete a worktree they no longer need, with interactive selection if no worktree name is provided. Use when this capability is needed.
원문 언어: 영어
Detects Prettier configuration and formats code. This skill should be used for final cosmetic formatting before commits, after all logic and type fixes have been verified. Returns structured JSON with detection and format results. Use when this capability is…
원문 언어: 영어
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when this capability is…
원문 언어: 영어
Detects TypeScript configuration and available compilation commands in a repository. Returns structured JSON output designed for consumption by the quality-gates-compilation agent. Checks for tsconfig.json, extracts compile commands from package.json,…
원문 언어: 영어
Convert acceptance criteria into a concrete validation/test plan. Use when Codex should turn backlog/spec acceptance criteria into unit/integration/e2e test ideas and update the task/spec validation section with relevant commands. Use when this capability is…
원문 언어: 영어
Write architecture decision records (ADR) in `logics/architecture`. Use when Codex identifies a non-trivial decision (trade-offs, alternatives) and should create a concise ADR document with context and consequences. Use when this capability is needed.
원문 언어: 영어
Groom and promote a Logics request into a backlog item. Use when a request is clear enough to define scope, acceptance criteria, and priority, and Codex should create `logics/backlog/*.md` aligned with the Logics format. Use when this capability is needed.
원문 언어: 영어
Bootstrap the Logics directory structure in a new repository (create `logics/architecture`, `logics/product`, `logics/request`, `logics/backlog`, `logics/tasks`, `logics/specs`, `logics/external`) and add `.gitkeep` files for empty folders so the structure…
원문 언어: 영어
Curate user-facing project changelog entries from Logics release notes or completed tasks. Use when Codex should turn `logics/RELEASE_NOTES.md` into a cleaner project-level `logics/CHANGELOG.md` and remove internal references/noise. Use when this capability…
원문 언어: 영어
Detect the repository's likely stack/framework (heuristics) and generate an adapted code-structure review (large files, folder hygiene, suggested module/component boundaries) as a Markdown report. Use when Codex needs to check whether code is overly…
원문 언어: 영어
Ask clarifying questions with suggested defaults to raise Understanding/Confidence above 90% for Logics request/backlog/task docs, and to strengthen product or architecture companion docs with a clarified `# Clarifications` section plus optional status…
원문 언어: 영어
>- Use when this capability is needed.
원문 언어: 영어
Validate and repair Logics request/backlog/task/product/architecture docs (structure, indicators, and cross‑references) without deleting existing metadata. Use when Codex should audit `logics/request`, `logics/backlog`, `logics/tasks`, `logics/product`, or…
원문 언어: 영어
Lint and validate the Logics Markdown conventions. Use when Codex should verify filenames, top headings, and required indicators across `logics/request`, `logics/backlog`, `logics/tasks`, `logics/product`, and `logics/architecture`, and report…
원문 언어: 영어
Detect potential duplicates across Logics documents. Use when Codex should scan titles and content of requests/backlog/tasks/specs/product briefs/architecture docs to find similar items and propose merge, split, or de-duplication. Use when this capability is…
원문 언어: 영어
Estimate effort and complexity for Logics backlog items and tasks. Use when Codex should propose a rough estimate (S/M/L or points), identify unknowns/risks, and recommend splitting work. Use when this capability is needed.
원문 언어: 영어
>- Use when this capability is needed.
원문 언어: 영어
Run a global review of the repository's Logics workflow and documents, then propose concrete optimizations/improvements (hygiene, placeholders, stale indicators, missing links, progress distribution) as a Markdown report. Use when Codex needs to audit…
원문 언어: 영어
Generate a consolidated index of Logics documents. Use when Codex should build or refresh `logics/INDEX.md` summarizing requests, backlog items, and tasks with titles and progress. Use when this capability is needed.
원문 언어: 영어
Install and configure the Chrome DevTools MCP server (chrome-devtools-mcp) in projects and control Chrome via MCP for UI automation, debugging, network/console inspection, and performance tracing. Use when wiring MCP clients (Codex, Claude, Cursor, VS Code,…
원문 언어: 영어
Install, configure, and use a Figma MCP server to connect MCP clients to Figma (search files, read nodes, export assets). Use when wiring MCP clients to Figma. Use when this capability is needed.
원문 언어: 영어
Install, configure, and use a Linear MCP server to connect MCP clients to Linear (query issues, projects, cycles). Use when wiring MCP clients to Linear. Use when this capability is needed.
원문 언어: 영어
Install, configure, and use the Notion MCP server to connect MCP clients to Notion (read/query/update pages and databases). Use when wiring MCP clients to Notion. Use when this capability is needed.
원문 언어: 영어