how-to-customize
Explains how to customize design and implementation plans with project-specific guidance
A command is the one you type. It runs exactly when you ask it to, and never before.
8,043 commands across 583 plugins.
Explains how to customize design and implementation plans with project-specific guidance
Start collaborative design process with brainstorming and planning
Create implementation plan from design document
Verify a saved Brand Profile. Reports QA findings and a verdict (the role map lives in `PROFILE.md`; verify does not render a proof). Add `--accept` to mark a…
Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes…
Claude-orchestrated deep research — Antigravity (agy/Gemini) does the grounded web legwork; Claude plans, verifies the citations, and synthesizes.
Fetch the output of a finished background Antigravity (agy) job, then verify it.
Thoroughly review a GitHub pull request and submit structured feedback
- **Recommended model: Claude Opus 4.6** (`claude-opus-4-6`). Directed improvement requires understanding complex rubric feedback and generating precise,…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
Design exploration using parallel agents through a 7-phase process: topic analysis, memory context, divergent ideation (10+ ideas), feasibility filtering,…
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER…
Daily autonomous classifier for failing PRs across your repos. Runs /ci-debug headless against every open PR with red required checks, posts the verdict as a…
Refine an existing cli-anything-web CLI by recording additional traffic and expanding command coverage. Invokes the gap-analyzer skill as its first step, then…
Run tests for a cli-anything-web CLI and update TEST.md with results.
Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports per-category and per-tier results.
Read every resume file in `resumes/` (skip the README and `search_profile.md`). Extract:
`/jobs indeed-setup` is the standalone entry point for enabling Indeed discovery and optionally optimizing the user's Indeed profile. It can be run:
You are a job-search assistant. You manage the user's `job_tracker.csv` and drive LinkedIn through the Claude in Chrome extension.
Review and approve the agent's proposed updates to its own learned rules
Show everything the Obsidian Knowledge Agent can do, with every command and an example
Turn material into notes at the right altitude — a quick capture, a small collection, or a full build
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival…
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage:…
Run IJFW health check (files, MCP server, hooks, memory, caps, framing)
This command analyzes bank statement CSV files, corrects missing or incorrect categorizations, and generates comprehensive spending reports with visual…
Analyze data patterns and generate additional synthetic training data
Transcribe morning debrief audio and analyze for engineering ideas and priorities
Create a new git worktree for an agent to work in isolation.
Using the nano-agent mcp server, execute the following nano agents with their respective prompts, models, and providers then rank the results based on the…
- Pass the prompt into each nano-agent AS IS. Do not change the prompt in any way.
Type of issue to debug (runtime, test, build, memory, performance)
Target platform (docker, cloudflare, vercel, fly, railway)
Template to use (hono, next, nuxt, sveltekit, tanstack, basic)
Run prun: parallel delegation fan-out (Codex-primary, Opus coordinates)
Read and follow the skill definition. Look for it at `skills/readme-polish/SKILL.md` first, then `.claude/skills/readme-polish/SKILL.md`, then…
Add `^tr` IDs to untagged memory entries in managed files. This is safe to run multiple times - it only tags entries that don't already have IDs.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic