Menu
SkillsMP a collecté 20 skills depuis Marve10s/melete. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 20 skills collectés sur 20.
Write reports, plans, audits, explainers, and comparisons for the user as rich single-file HTML instead of markdown. Use whenever producing a report, implementation plan, audit result, research summary, PR walkthrough, or design exploration addressed to the…
Langue du texte source : anglais
Generate or edit raster images by calling the ChatGPT/Codex Responses image_generation tool directly with local Codex or OpenClaw OAuth credentials, then save decoded image files for OpenClaw and other agent workflows.
Langue du texte source : anglais
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
Langue du texte source : anglais
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via write-a-skill + unslop, optionally pulling…
Langue du texte source : anglais
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove…
Langue du texte source : anglais
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing,…
Langue du texte source : anglais
Prepares the user's concise, spoken work update for recurring Tuesday and Thursday evening meetings. Use when the user asks for a meeting update, boss update, or summary of what they completed since the previous meeting.
Langue du texte source : anglais
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints. Use when asked to clean up, strip, or check comments, and before filing a PR in a repository whose rules forbid narration comments.
Langue du texte source : anglais
When the user wants to write a social media post for LinkedIn, Twitter/X, Threads, or Bluesky. Also use when the user mentions 'write a post,' 'draft a post,' 'LinkedIn post,' 'tweet,' 'Threads post,' 'Bluesky post,' 'social media post,' 'help me write,' or…
Langue du texte source : anglais
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working…
Langue du texte source : anglais
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect, or at the end of a session in which the user corrected the agent more than once.
Langue du texte source : anglais
Create engaging content for social media platforms: X posts and threads, LinkedIn, Threads, Instagram, Facebook. Includes writing styles, AI-avoidance patterns, hooks catalog, and macOS Notes integration. Use when drafting social media posts, writing thread…
Langue du texte source : anglais
Selects the model, harness, and workflow for delegated work, and defines the bounded review cycle. Use when reviewing a PR, diff, or plan, when asked for sub-agents, multi-model work, or an independent second opinion, and before starting any agent team,…
Langue du texte source : anglais
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat,…
Langue du texte source : anglais
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Langue du texte source : anglais
Owns a pull request until CI is green and review threads are cleared. Use whenever the user asks to babysit, fully babysit, monitor, or watch a PR or several PRs, however hedged ("I think we might babysit it", "can we babysit all 3 PRs?"). Any babysit…
Langue du texte source : anglais
Thread-scoped toggle that runs the original Caveman terse-prose rules and Ponytail minimal-code rules together. Supports Ponytail intensity levels: lite, full (default), and ultra. Use only when the user explicitly invokes $cavetail or /cavetail, or…
Langue du texte source : anglais
Find and delete stale worktrees, build artifacts, caches, and dead branches safely, with an inventory-first protocol and freed-space report. Use when asked to clean up, free disk space, remove stale worktrees or artifacts, when a repo or machine "is huge", or…
Langue du texte source : anglais
Applies Effect-first TypeScript architecture for errors, asynchronous workflows, runtime schemas, services, Layers, logging, tests, and Effect Atom. Use when writing or reviewing code in any project that uses Effect, Effect-TS, @effect packages, Effect…
Langue du texte source : anglais
Commits and pushes the current in-scope work and opens a ready-for-review pull request with an outcome-focused title and explanation. Use for any request that the work should end in a PR, however hedged — "file the PR", "I think we might file a PR", "we can…
Langue du texte source : anglais