Menu
SkillsMP a collecté 25 skills depuis ucsandman/claude-skills. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 25 skills collectés sur 25.
Fill a repo's .env from the machine's credential stores without ever reading or printing a secret value. Use when the user says "/secrets", "fill in the .env", "get the keys", "wire up the credentials", "pull the secrets from offlocal", or when launch.py / a…
Langue du texte source : anglais
Use when finished work needs to go out — the user says "ship it", "update docs commit and push", "commit and push", or asks "anything else we need to update?" before a release or at the end of a work session.
Langue du texte source : anglais
Use before writing a new skill, before saying no skill exists for something, or whenever Wes asks "do I have a skill for X" / "is there a skill that…". Also use when a task sounds like it needs a capability that might already be installed (spreadsheets, PDFs,…
Langue du texte source : anglais
Use when a product is about to go public and needs its final pre-launch pass — the user says "final pass", "preflight", "launch check", "is this ready to go live", or is sweeping several repos before a launch day. Run from the product's repo, one run per repo.
Langue du texte source : anglais
Use when driving the user's iPhone with sidetap or the phone-claude harness, before the first tap and whenever a tap lands on the wrong element, a scroll overshoots, an app search returns an unexpected action name, a capability seems missing, or a send is…
Langue du texte source : anglais
Nightly/weekly reflection loop for Claude Code — append dated entries to rotating reflection topics, promote durable insights up the ladder (memory → CLAUDE.md → SOUL.md), build one real artifact at the workbench, render an HTML digest. Use when invoked as…
Langue du texte source : anglais
Multi-agent adversarial code review — parallel read-only finders across focused dimensions, then every finding is independently verified by a skeptic that defaults to REFUTED. Use when the user asks for an adversarial review, a deep/thorough review of recent…
Langue du texte source : anglais
Use when the user wants music, voiceover, narration, or a soundtrack added to a video asset, OR wants standalone generated audio for any purpose (e.g. "/audio-track", "add music to the launch video", "narrate the demo", "make a 30 second music sting",…
Langue du texte source : anglais
Use before modifying unfamiliar or high-stakes code — when the user invokes /blindspot, inherits a module or codebase, asks "what am I missing?", or is about to change auth, billing, data migration, or concurrency code they didn't write. Not for routine…
Langue du texte source : anglais
Use when you need to see or inspect the Windows desktop — Wes asks "what's on my screen", pastes or offers a screenshot, mentions a native app, dialog, installer or window that is not a browser or a phone, or asks you to check/read/screenshot something…
Langue du texte source : anglais
Use when a task involves heavy implementation, debugging, test fixing, refactoring, or multi-file edits that Codex could execute, or when orchestrating Claude + Codex together in a session.
Langue du texte source : anglais
Read-only health check of the local Claude Code harness — verifies every hook target file exists, finds orphaned hook scripts, flags enabled plugins with missing cache dirs, and counts backup/state-file cruft. Use when hooks misbehave, after editing…
Langue du texte source : anglais
Use before implementing any non-trivial feature or change — when the user invokes /interview, when a spec has multiple plausible interpretations, when a request is vague ("make it better", "add auth"), or before committing to an architecture. Not for trivial…
Langue du texte source : anglais
Use when the user wants a full launch video / hero video / 30-90s product announcement composing demo footage, logo, and copy (e.g. "/launch-video", "make the launch video for DashClaw").
Langue du texte source : anglais
Use when the user wants a logo reveal / logo animation / brand intro video for any product (e.g. "/logo-reveal", "make a logo reveal for DashClaw", "animated logo for the landing page").
Langue du texte source : anglais
Use when the user wants the complete marketing asset suite for a product in one run — "/marketing", "build all the marketing assets", "generate everything for the launch", "all the animations and brand assets for X". Not for a single asset (use that asset's…
Langue du texte source : anglais
Use when generating any brand video, animation, image, or audio asset (logo reveal, social clip, product demo, launch video, OG image, README GIF, music, voiceover) for any product/repo, or when working inside C:\Projects\animations. Required background for…
Langue du texte source : anglais
Use when the user wants OG images, link-preview assets, animated OG loops, README GIFs, or social-card exports for any product (e.g. "/og-assets", "make an OG image and README gif").
Langue du texte source : anglais
Use when the user asks to text or message someone from their iPhone, read or check something on their phone, or control their iPhone — e.g. "text my dad ...", "send this to Mom", "summarize this and text it to X", "what's on my phone", "open <app> on my…
Langue du texte source : anglais
Use when the user wants a product demo video / screen recording with zooms and cursor / dashboard walkthrough clip for any product (e.g. "/product-demo", "record a demo of the app", "Screen-Studio style demo").
Langue du texte source : anglais
Ship a product end to end — render marketing assets with the animations studio, then run the launch-engine flow with videos attached to X and LinkedIn posts. Run from the product's repo.
Langue du texte source : anglais
Use when the user wants a short social media video / feature announcement clip / X-LinkedIn-TikTok teaser for any product (e.g. "/social-clip", "make a clip announcing the new dashboard").
Langue du texte source : anglais
Fan a task out to the Claude Code + OpenClaw (MoltFire) team. Use when the user types /team <task> or asks to "have both agents" / "the team" handle something. Classifies who leads, delegates over CLI, logs every exchange to the team ledger, reports back here.
Langue du texte source : anglais
Use when Wes asks to rewrite or translate pasted text into his own casual voice, especially with "/wes", "make this sound like me", "make this sound like Wes", "translate this into my voice", or drafting comments, posts, replies, and messages he will…
Langue du texte source : anglais
Use when a session is ending — the user says "wrap up", "get to a good stopping point", is near a rate limit or context limit, wants to compact safely, or asks for handoff notes / a resume prompt.
Langue du texte source : anglais