Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
file-watcher
qdhenry
Chokidar-based file watcher that triggers claude -p on changes. Useful for automated AI reactions to file changes — design sync, code validation, config regeneration, etc.
grace-init
osovv
"Bootstrap GRACE framework structure for a new project. Use when starting a new project with GRACE methodology — creates docs/ directory, AGENTS.md, and XML templates for knowledge graph, requirements, technology, and development plan."
style-docs
thrashr888
Generate standardized project documentation using the 5-style system. Use when asked to create plans, specs, skills, RFCs, ADRs, or other project documentation. Ensures consistent, high-quality documentation across the codebase.
iterative-academic-writer
iamseungpil
Iteratively write academic documents (paper sections, research proposals, technical documents) with quality improvement loop. Uses academic-planner for structure design and academic-reviewer for quality evaluation. Ensures no hallucinations through fact verification.
plan-template
ReinaMacCredy
Scaffold a blank plan with required sections in .maestro/plans/. Use /plan-template <name> to create a new plan file.
work
ReinaMacCredy
"Execute a plan using Agent Teams, or work directly from a description. Spawns specialized teammates to implement tasks in parallel."
retro-analysis
mohitagw15856
Analyse sprint delivery data and produce a structured retrospective brief
project-development
guanyang
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 traditional approaches.
doc-coauthoring
guanyang
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
hwpx_writer
leedonwoo2827-ship-it
"마크다운 텍스트 또는 MD 파일을 proposal-styles.json 스타일이 적용된 HWPX 한글 문서로 변환하는 MCP 스킬."
llm-wiki
selmakcby
LLM tarafından sürekli inşa edilen ve güncellenen kalıcı, birikimli bir bilgi arşivi (persistent wiki) deseni. Standart RAG'ın aksine her sorguda bilgi yeniden keşfedilmez — ajan yeni kaynakları okur, mevcut wiki'ye entegre eder, varlık/kavram sayfalarını günceller, çelişkileri işaretler, çapraz-referansları korur. Herhangi bir alan için kullanılır: araştırma, kitap okuma, ürün geliştirme, takım bilgisi, kişisel gelişim, rekabet analizi, ders notları. Obsidian + LLM ajanı (Claude Code, Codex, vb.) ile çalışır. Kullanıcı kaynakları bulur, ajan tüm bookkeeping'i yapar.
plan-maestro
ReinaMacCredy
"Universal interview-driven planning for Claude Code, Codex, and Amp Code. Uses subagents only -- no Agent Teams required."
design
ReinaMacCredy
"Start interview-driven planning with Prometheus. Asks clarifying questions before generating implementation plan."
project-conventions
ReinaMacCredy
Discovers host project conventions from CLAUDE.md, package.json, linter configs, and other configuration files. Use when agents need to understand the target project's coding standards.
agents-md-improver
ericmjl
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
publish-to-google-docs
ericmjl
Quickly publish markdown notes to styled Google Docs using pandoc and a Word template. Use when creating Google Docs from markdown, applying branding to documents, or pushing content to Drive for sharing.
multi-model-meta-analysis
petekp
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.
handoff
petekp
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
op-session
sd0xdev
"Initialize 1Password CLI session for Claude Code. Use when: starting a session that needs 1Password secrets, op CLI keeps prompting biometric auth, setting up OP_SESSION token. Solves: Claude Code's no-TTY subprocess model triggers 1Password biometric auth on every op call. After running once, all subsequent op commands use the cached session token."
skill-vetter
app-incubator-xyz
"Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns."
Skill 创建指南
TencentBlueKing
指导如何创建符合渐进式披露架构的 skill 文档
codex-brainstorm
sd0xdev
"Adversarial brainstorming via Claude+Codex debate. Use when: exploring solutions, feasibility analysis, exhaustive enumeration. Not for: implementation (use feature-dev), architecture only (use codex-architect). Output: Nash equilibrium consensus + action items."
claude-health
sd0xdev
"Claude Code config health check. Use when: auditing .claude/ structure, checking naming, verifying hook setup. Not for: skill quality (use skill-health-check), code review (use codex-code-review). Output: health report + fix recommendations."
BKUI 组件属性速查表
TencentBlueKing
高频易错属性映射和避坑指南