Reports per-plugin skill description token contributions to help reduce session startup budget. Use when /doctor shows skill descriptions dropped.
EnglishUse after completing a session to identify genuine learnings from mistakes, corrections, or rework - focuses only on patterns that were actually wrong, not things that worked correctly the first…
EnglishManual plugin-update check. Shows cached state by default; --refresh bypasses the 24h TTL; --dismiss hides the nudge until a newer release ships; --prompt spawns design-update-checker for a richer summary.
EnglishCreate a clean PR branch by filtering out .design/ and .planning/ commits. Code-review-ready branch for the design implementation work.
EnglishRetroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation…
EnglishSocratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase. Produces a SPEC.md with falsifiable requirements locked before implementation decisions begin.
EnglishInstalls a Claude Code skill from a curated source via one of three methods (sparse-clone, plugin marketplace, or npx antigravity filtered). Always asks for confirmation before any install. Creates .maxv-source.json in the skill folder for traceability. Used by orchestrate after discover-skill identifies missing components.
EnglishExtracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.
EnglishOwner-only — detects upstream drift of this plugin and applies the update via claude plugin update CLI (CC-native auto-update). The architectural equivalent of MaxVision's /maxvision:update for a Claude Code plugin (which is not an npm package). Non-owners get silent exit.
EnglishTrigger background monitors that watch the FTS5 catalog source file and the index staleness — opt-in replacement for the auto-start removed in v1.1.4. Invoked by /monitor.
EnglishManually install the maxvision statusline. Copies wrappers to ~/.claude/hooks/ (stable user-scope location) and writes the absolute path to ~/.claude/settings.json statusLine.command. Backs up any existing statusLine entry. The SessionStart auto-install hook normally handles this — use this command if you opted out via MAXVISIONSKIPAUTOSTATUSLINE=1 or want to force a fresh install.
EnglishEN: Triggered when user says "restore context", "continue", or similar in English. ZH: 当用户说中文"恢复上下文"、"恢复"、"接着"、"继续之前的工作"时触发。 IT: Si attiva quando l'utente dice "ripristina contesto", "continua" in italiano.
Uncertain
AGENT SKILLS ATLASIncludes Audit Budget, Context Save, Extract Learnings, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Audit Budget
Reports per-plugin skill description token contributions to help reduce session startup budget. Use when /doctor shows skill descriptions dropped.
Context Save
Save decision, bet, or learning to the context registry
Extract Learnings
Use after completing a session to identify genuine learnings from mistakes, corrections, or rework - focuses only on patterns that were actually wrong, not things that worked correctly the first time
Gdd Check Update
Manual plugin-update check. Shows cached state by default; --refresh bypasses the 24h TTL; --dismiss hides the nudge until a newer release ships; --prompt spawns design-update-checker for a richer summary.
Gdd PR Branch
Create a clean PR branch by filtering out .design/ and .planning/ commits. Code-review-ready branch for the design implementation work.
Gsd:eval Review
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
Gsd:secure Phase
Retroactively verify threat mitigations for a completed phase
Gsd:spec Phase
Socratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase. Produces a SPEC.md with falsifiable requirements locked before implementation decisions begin.
Gsd:validate Phase
Retroactively audit and fill Nyquist validation gaps for a completed phase
Install Skill
Installs a Claude Code skill from a curated source via one of three methods (sparse-clone, plugin marketplace, or npx antigravity filtered). Always asks for confirmation before any install. Creates .maxv-source.json in the skill folder for traceability. Used by orchestrate after discover-skill identifies missing components.
Keyword Extractor
Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.
Maxvision Update
Owner-only — detects upstream drift of this plugin and applies the update via claude plugin update CLI (CC-native auto-update). The architectural equivalent of MaxVision's /maxvision:update for a Claude Code plugin (which is not an npm package). Non-owners get silent exit.
Monitor Catalog
Trigger background monitors that watch the FTS5 catalog source file and the index staleness — opt-in replacement for the auto-start removed in v1.1.4. Invoked by /monitor.
Setup Statusline
Manually install the maxvision statusline. Copies wrappers to ~/.claude/hooks/ (stable user-scope location) and writes the absolute path to ~/.claude/settings.json statusLine.command. Backs up any existing statusLine entry. The SessionStart auto-install hook normally handles this — use this command if you opted out via MAXVISIONSKIPAUTOSTATUSLINE=1 or want to force a fresh install.
Context Restore
EN: Triggered when user says "restore context", "continue", or similar in English. ZH: 当用户说中文"恢复上下文"、"恢复"、"接着"、"继续之前的工作"时触发。 IT: Si attiva quando l'utente dice "ripristina contesto", "continua" in italiano.
Gsd:audit Fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
Gsd:ui Phase
Generate UI design contract (UI-SPEC.md) for frontend phases
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Audit Budget skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.