Deterministic git operations with state verification for skill-creator managed repos. Use when managing repos, branches, worktrees, or contribution workflows.

Foundational measurements and relationships. The axioms of the system — numbers, distance, angles, and the geometry of seeing.

Periodic phenomena and frequency analysis. How repetition creates structure — from simple oscillation to Fourier decomposition.

Passive Sensing, Threat Assessment, and Coordinated Signaling for Agent Systems.

Use trace-mcp apply_codemod for any bulk mechanical change instead of repeated Edit calls. Activate whenever the same edit pattern would be applied 2+ times, across one file or many.

>-

Defense-in-depth security for AI-assisted development. Pre-commit secret scanning (Gitleaks + native fallback), repo-wide pattern detection, token lifecycle management, and AI agent safety rules. Prevents secret leaks at every stage: write → commit → push → deploy. Use BEFORE any git push or deploy, or when setting up new projects.

Pre-production security audit and vulnerability scanning. Run Snyk + Aikido dependency scans, OWASP analysis, and set up automated GitHub security checks with Jules. Use when asked to 'run security check', 'security audit', 'kiểm tra bảo mật', 'vulnerability scan', 'Snyk', 'OWASP', or before open-sourcing / commercializing a project.

Start the CM Workflow to execute your objective from idea to production code.

Use when running ANY terminal command - enforces clear progress logging, output reading, and error-stop behavior so terminal processes are never left unchecked

Route conversation content to the right files mid-session. Use after a decision, update, correction, or new datum lands in conversation. Lightweight capture, session continues after.

You are the **Chair** — John Carmack's philosophy made operational. You coordinate a council of domain experts, each running as an independent subagent via the `Task` tool. Your job is to understand t

Elasticsearch 集群管理

Kubernetes Deployment 管理

Kubernetes Pod 管理与调试

Prevents the most common AI failure: rushing to execute before understanding what's actually needed.

Use when starting feature work that needs isolation or before executing implementation plans — creates isolated git worktrees

Use when about to claim work is complete, fixed, or passing — run verification commands and confirm output before any success claims; evidence before assertions always

Run Cogny marketing analysis tasks — fetch scheduled tasks, analyze ad accounts via MCP, report findings

>-

Execute a hunt phase with parallel telemetry work, query logging, receipt generation, and optional wave targeting

abra-flexibee

acelle-mail

aci-payon

addsearch

adobe-acrobat-sign

ai21-labs

aircall

alegra

aleph-alpha

altera-payroll

alternative-payments

amadeus

amazon-cognito

amazon-ecs

amazon-eks

amazon-location-service

amazon-polly

amazon-ses

amlbot

ansible

appointo

aqilla

asana

assembla

astronaut

awesome-support

aws-s3

axis-lms

backblaze