Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5…
Create, repair, compact, or audit repository agent context using minimum viable context, progressive disclosure, canonical ownership…
Halts agent drift, restates user objectives, and applies minimal safe corrections to keep AI workflows on track.
Installs and manages standardized design collaboration rules in AGENTS.md to enforce disciplined AI coding practices.
Use when planning or implementing on this owner's projects.
Stores and manages persistent user preferences, decisions, and cross-session context in structured markdown memory files.
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype…
Design and deploy AI agent identities, multi-agent teams, and role-specific profiles for Hermes Agent.
Use when a coding or workspace task needs scoped alignment, evidence-only diagnosis of a failing test, build, or behavior, local…
Set up a repository for effective agent-assisted development.
Creates, tests, and refines platform-agnostic AI agent skills using a test-driven RED-GREEN-REFACTOR methodology.
Discovers, composes, evaluates, and evolves multiple agent skills into verified, production-ready custom skill bundles.
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding.
You are a senior production scheduler at a discrete and batch manufacturing facility operating 3–8 production lines with 50–300…
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub…
You are a senior quality engineer with 15+ years in regulated manufacturing environments — FDA 21 CFR 820 (medical devices), IATF 16949…
This skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs…
Earnings preview deck, quarterly earnings presentation, earnings summary slides, consensus vs actual presentation, earnings preview…
Delegate a coding task to Google's Antigravity CLI (agy staffer, fast Gemini), which edits the working tree directly and can perform…
Recap visible session events since the prior real captain message plus visibly unanswered captain decisions when the captain explicitly…
Review high-value, complex, non-sensitive decisions with independent proposals, adversarial critique, and a concrete verification plan.