Use when proving, rejecting, or deleting backend adjustment registry entries with real LLM evidence and independent disabled-adjustment worktrees.
EnglishToken-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.
EnglishGenerate a full agento PR status report — 6-point green checks, zero-touch rate, display inline, and post to Slack ai-slack-test.
EnglishUse Claude Code to control Google Antigravity IDE on macOS via Peekaboo. Explicitly supports targeting either the Agent Manager window or the Editor window (worktree/editor titles), plus auto routing. Covers workspaces, conversations, Knowledge/Browser/Settings panels, keyboard shortcuts, model selection, planning modes, artifacts, and menu bar. Trigger when the user asks to automate, click, send messages to, or interact with the Antigravity app, or to choose Manager vs Editor.
EnglishRead ~/.hermes/agent-orchestrator.yaml BEFORE declaring an --agent value unsupported. Lists plugin shorthands (wafer, minimax, agy).
EnglishOverride the model an ao spawn worker uses (e.g. force claude-sonnet-4-6 instead of the project default of wafer.ai/GLM-5.1) WITHOUT mutating ~/.hermes/agent-orchestrator.yaml. Use when the user asks for "claude sonnet with AO", "spawn AO with X model", "AO worker but not GLM", or any one-shot model swap. Also use as the canonical reference whenever someone tries to find a --model flag on ao spawn and is surprised it doesn't exist.
EnglishUse when spawning, steering, or auditing Agent Orchestrator workers, especially when the user specifies exact AO parameters such as codex, runtime, project, claim-pr, or PR targets.
EnglishUse whenever running an AO spawn. Honors exact --agent/--runtime/--project/--claim-pr; verifies session metadata; never silently substitutes a different worker.
EnglishUse BEFORE bulk/iterative AO spawns (>3). Hard cap 20 active workers; spawn ≤5 at a time; never use loadavg as the gate.
EnglishChecklist for dispatching AO workers — python venv, commit discipline, branch drift, and post-push CodeRabbit…
EnglishAudit automation job runs, logs, PR processing metrics, and AI-authored remote commits.
EnglishUse BEFORE running any automation loop. Requires stating the observable success output (PR, fixed test, push); rejects prediction-only loops.
EnglishAlways check ~/.bashrc for credentials, API keys, passwords, and configuration values before asking…
EnglishStandardize br bead follow-ups for PR reviews and code reviews so each bead includes exact implementation instructions, API/function signatures, and acceptance criteria.
EnglishGuide and workflow for Browser Testing with OCR Validation. Use when you need Browser Testing with OCR Validation.
EnglishGuide and workflow for Chrome Superpowers - localhost:3000 Usage. Use when you need Chrome Superpowers - localhost:3000 Usage.
EnglishGuide and workflow for Chrome Superpowers MCP - Reference Guide. Use when you need Chrome Superpowers MCP - Reference Guide.
EnglishUse Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution. Trigger when the user asks to make agents do Claude computer-use behavior, desktop/browser UI control, click/type/scroll automation, or iterative visual task execution in Claude Code.
EnglishGuide and workflow for Claude Code Schema Validation & Testing. Use when you need Claude Code Schema Validation & Testing.
EnglishMaintain Claude Code settings, hooks, and agent config formats; use when editing or validating settings.json or hooks.
EnglishUse when dispatching work through the Hermes gateway with /claw, especially when the task may resolve slash commands or hand off into AO worker orchestration.
EnglishUse when debugging unauthorized/fallback errors. Flags redacted placeholders (e.g. OPENCLAWREDACTED) as invalid tokens; checks env overrides first.
EnglishSecurely guide teammates through cloud configuration, secrets management, and incident…
English
AGENT SKILLS ATLASIncludes Adjustment Proof, Agento Report, Antigravity Computer Use, 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
Adjustment Proof
Use when proving, rejecting, or deleting backend adjustment registry entries with real LLM evidence and independent disabled-adjustment worktrees.
Advice
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.
Agento Report
Generate a full agento PR status report — 6-point green checks, zero-touch rate, display inline, and post to Slack ai-slack-test.
Antigravity Computer Use
Use Claude Code to control Google Antigravity IDE on macOS via Peekaboo. Explicitly supports targeting either the Agent Manager window or the Editor window (worktree/editor titles), plus auto routing. Covers workspaces, conversations, Knowledge/Browser/Settings panels, keyboard shortcuts, model selection, planning modes, artifacts, and menu bar. Trigger when the user asks to automate, click, send messages to, or interact with the Antigravity app, or to choose Manager vs Editor.
Ao Agent Shorthands
Read ~/.hermes/agent-orchestrator.yaml BEFORE declaring an --agent value unsupported. Lists plugin shorthands (wafer, minimax, agy).
Ao Model Override
Override the model an ao spawn worker uses (e.g. force claude-sonnet-4-6 instead of the project default of wafer.ai/GLM-5.1) WITHOUT mutating ~/.hermes/agent-orchestrator.yaml. Use when the user asks for "claude sonnet with AO", "spawn AO with X model", "AO worker but not GLM", or any one-shot model swap. Also use as the canonical reference whenever someone tries to find a --model flag on ao spawn and is surprised it doesn't exist.
Ao Operator Discipline
Use when spawning, steering, or auditing Agent Orchestrator workers, especially when the user specifies exact AO parameters such as codex, runtime, project, claim-pr, or PR targets.
Ao Parameter Fidelity
Use whenever running an AO spawn. Honors exact --agent/--runtime/--project/--claim-pr; verifies session metadata; never silently substitutes a different worker.
Ao Spawn Safety
Use BEFORE bulk/iterative AO spawns (>3). Hard cap 20 active workers; spawn ≤5 at a time; never use loadavg as the gate.
Ao Worker Dispatch
Checklist for dispatching AO workers — python venv, commit discipline, branch drift, and post-push CodeRabbit verification
Automation Audit
Audit automation job runs, logs, PR processing metrics, and AI-authored remote commits.
Automation Output Verification
Use BEFORE running any automation loop. Requires stating the observable success output (PR, fixed test, push); rejects prediction-only loops.
Auton
Diagnose why the automation system is not autonomously driving PRs to green and merge.
Bashrc Credential Guard
Always check ~/.bashrc for credentials, API keys, passwords, and configuration values before asking user
Bead Followup Templates
Standardize br bead follow-ups for PR reviews and code reviews so each bead includes exact implementation instructions, API/function signatures, and acceptance criteria.
Browser Testing Ocr Validation
Guide and workflow for Browser Testing with OCR Validation. Use when you need Browser Testing with OCR Validation.
Chrome Localhost3000 Usage
Guide and workflow for Chrome Superpowers - localhost:3000 Usage. Use when you need Chrome Superpowers - localhost:3000 Usage.
Chrome Superpowers Reference
Guide and workflow for Chrome Superpowers MCP - Reference Guide. Use when you need Chrome Superpowers MCP - Reference Guide.
Claude Code Computer Use
Use Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution. Trigger when the user asks to make agents do Claude computer-use behavior, desktop/browser UI control, click/type/scroll automation, or iterative visual task execution in Claude Code.
Claude Code Schema Validation
Guide and workflow for Claude Code Schema Validation & Testing. Use when you need Claude Code Schema Validation & Testing.
Claude Code Settings Maintenance
Maintain Claude Code settings, hooks, and agent config formats; use when editing or validating settings.json or hooks.
Claw Dispatch
Use when dispatching work through the Hermes gateway with /claw, especially when the task may resolve slash commands or hand off into AO worker orchestration.
CLI Secrets
Use when debugging unauthorized/fallback errors. Flags redacted placeholders (e.g. OPENCLAWREDACTED) as invalid tokens; checks env overrides first.
Cloud Ops Credential Guard
Securely guide teammates through cloud configuration, secrets management, and incident triage
Showing 24 of 133 skills. Use the list’s page controls above to explore the rest.
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 Adjustment Proof 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.