Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
memory-manage
catlog22
Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory manage", "update claude", "update memory", "generate docs", "更新记忆", "生成文档".
ccw-cli-tools
catlog22
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
team-tech-debt
catlog22
Unified team skill for tech debt identification and cleanup. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team tech-debt", "tech debt cleanup", "技术债务".
deepsearch-service
Lin-A1
基于 LLM 的深度迭代搜索与推理服务。擅长处理复杂问题，通过自动分解查询、多轮迭代检索、信息评估与验证，最终生成全面且结构化的深度分析报告。
pan-peer-review
eltmon
"Workflow: spawn an independent adversarial reviewer on a different model to verify or refute your own findings. EXPENSIVE — invoke only when the operator explicitly asks for a peer/second-opinion review."
implementing-as-tachikoma
sumik5
Operates as Tachikoma Agent (Implementation Worker) performing actual code implementation. Use when receiving task assignments from Claude Code for implementation work, test creation, or documentation. Adapts to frontend, backend, or testing roles based on task assignment.
pan-memory
eltmon
"pan memory <subcommand> — search and inspect Overdeck memory observations, status, reset markers, summaries, and health"
starlight-si
frankxai
Codex-native Starlight Intelligence /si router for choosing local agent lanes, building handoff packets, and running explicit read-only fanout or council dispatch across Codex, Claude, Grok, Antigravity, OpenCode, DeepAgent, and image tools. Use when prompts mention /si, the installed /si prompt shortcut, mobile alias si:, starlight si, route, dispatch, fanout, council, which agent/tool, local CLI lanes, or Starlight multi-agent orchestration.
real-mecha
ShinChven
Converts 2D/anime mecha art into photorealistic 3D/real-world visualizations with high-fidelity material textures.
savethetokens
Redclawww
Reduce Claude Code token burn with proactive compacting, task-scoped sessions, checkpoint files, tiered docs, and relevance-based context pruning. Use when a user explicitly asks to reduce context usage/cost, run token benchmarks, or optimize CLAUDE.md. Do not use to expand product scope or skip correctness checks.
photo-restoration
ShinChven
Restores vintage and blurry photos to high-definition 8k images while preserving identity.
agent-task-splitter
WenyuChiou
Use when the user asks to split a goal across Claude, Codex, or Gemini (gemini requests are rerouted - lane deprecated); plan a multi-agent run; break work into parallel agent tasks; or decompose a large task that needs bounded context handoffs. This is the generic multi-agent task splitter — writes .coord/plan.yml (a DAG) plus per-agent task files. NOT for research-domain routing that touches .research/, .paper/, or Zotero/Obsidian/NotebookLM ingest pipelines — for those, use research-hub-multi-ai instead (different artifact .coord/multi_ai_plan.md, research-hub-aware reconciliation).
baoyu-danger-gemini-web
xuanxuan1983
Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.
skill-forge
WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.
task-define
osdlc
Interactively drive a single task document toward the implementation-ready contract (solutions/ontological/lib/model/entities/task/implementation-ready.md). Walks the user through filling missing or thin sections via AskUserQuestion, edits the body, and commits. Leaves readiness_verified_at to /sdlc:task-ensure-ready; callers should invoke task-ensure-ready after this skill returns to verify the result.
solo-founder-gtm
chadboyda
"When the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions 'solo founder,' 'one-person startup,' 'solopreneur,' 'bootstrapped,' 'no team,' 'AI agents as team,' 'scaling without hiring,' 'founder-led sales,' 'lean GTM,' 'one-person company,' or 'no employees.' This skill covers the complete solo founder GTM playbook from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire."
status
IgorGanapolsky
Show the latest Codex bridge artifact metadata from Claude Code. Use when the user asks whether the bridge already ran, what mode it used, or where the result was saved.
setup
IgorGanapolsky
Validate that the Codex bridge plugin is ready inside Claude Code. Use when the user asks to install, configure, or sanity-check Codex review from Claude.
adversarial-review
IgorGanapolsky
Run a skeptical Codex review from Claude Code that hunts for hidden regressions, unsafe assumptions, and release risk. Use before merges, deploys, migrations, or other risky changes.
second-pass
IgorGanapolsky
Hand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.
thumbgate-feedback
IgorGanapolsky
Capture thumbs up/down feedback into structured memories and prevention rules. Require one sentence of why before claiming memory promotion. Use when user gives explicit quality signals about agent work (e.g. "that worked", "that failed", "thumbs up/down"). Do NOT use for general questions, code generation, file operations, or any task that is not explicit feedback on prior agent output.
skill-evolve
OrangeViolin
用演进式方法论改进任何 skill 的质量。当用户说"改进这个 skill"、"这个 skill 效果不好"、"优化 skill"、"skill 不够好"、"迭代 skill"、"skill-evolve"、"/evolve"时触发。也适用于用户拿着一个 skill 的输出结果说"不满意"、"有问题"、"效果差"的场景。不要等用户明确说"演进"——只要他们在讨论一个 skill 的质量问题，就应该启用。
excalidraw-diagrams
robtaylor
Creates Excalidraw diagrams programmatically. Use when the user wants flowcharts, architecture diagrams, system designs, or any visual diagram instead of ASCII art. Outputs .excalidraw files that can be opened directly in Excalidraw or VS Code with the Excalidraw extension.
interminai
mstsirkin
Control interactive terminal applications like vim, git rebase -i, git add -i, git add -p, apt, rclone config, sudo, w3m, and TUI apps. Can also supervise another CLI LLM (cursor-agent, codex, etc.) - approve or reject its actions by pressing y/n at confirmation prompts. Use when you need to interact with applications that require keyboard input, show prompts, menus, or have full-screen interfaces. Also use when commands fail or hang with errors like "Input is not a terminal" or "Output is not a terminal". Better than application specific hacks such as GIT_SEQUENCE_EDITOR or bypassing interactivity through file use.