Agent Claude Code
Principal-level software architect for architecture reviews, pre-implementation specification reviews, and spec-conformance verification. Use when the user asks to review architecture, evaluate design decisions, audit system boundaries, check for anti-patterns, evaluate whether a specification is ready to be…
Agent Claude Code
Translate a feature request, user prompt, or tracker reference into a rigorous technical specification the planning and implementation agents can build from without further clarification. Use when asked to specify, architect, design, write a spec, define requirements, draft an API contract, draft a schema change…
Agent Claude Code
Automated specification pipeline: specify -> review -> revise -> plan. Produces a complete, reviewed specification with an implementation plan in a single automated run. Intelligently routes based on input: drafts from a tracker reference or raw description, picks up an existing spec for review, or picks up an…
Agent Claude Code
Automated implementation pipeline: implement -> check findings -> test. Intelligently routes based on input: executes a plan, resolves a task tracker issue, or builds from a raw description. Detects spec deviations and halts before testing if the specification needs revision. Use when asked to run the full…
Agent Claude Code
Implement features, fix bugs, and write production code following architectural constraints and best practices in Go. Use when asked to build, code, implement, develop a feature, execute a plan, or write production code. Also use when the user mentions Go, Golang, or specific Go libraries or frameworks. Do NOT use for…
Agent Claude Code
Write concise, resilient, idiomatic Go tests using the stdlib testing package with table-driven patterns. Use when asked to test Go code, write Go tests, add Go test coverage, verify a Go module or package, lock a Go bug with a regression test, or after Go implementation changes need test coverage. Also use when the…
Agent Claude Code
Convert a technical specification, tracker reference, or feature request into a rigorous, atomic, step-by-step implementation plan the implementation agent can execute without further clarification. Use when asked to plan, break down work, create an implementation plan or checklist, outline steps from a spec, prepare…
Agent Claude Code
Detective-grade technical investigator. Use to explain, investigate, research, fact-check, or deep-dive into any technology, library, protocol, or technical claim. Triangulates sources, cites evidence, reports conflicts. Use when you need to understand something deeply enough to explain it, or when you need to find…
Agent Claude Code
Implement features, fix bugs, and write production code following architectural constraints and best practices in TypeScript. Use when asked to build, code, implement, develop a feature, execute a plan, or write production code. Also use when the user mentions TypeScript, TS, or specific TypeScript libraries or…
Agent Claude Code
Write concise, resilient, modern Unit, Component, and Hook tests using Vitest and React Testing Library for Next.js project. Use when asked to test, write tests, add coverage, verify a module, lock a bug with a regression test, or after implementation changes need test coverage. Also use when the user mentions Vitest…
Command Claude Code
Challenge a pull request with an independent second opinion from another model.
Command Claude Code
Run the full implementation pipeline - implement, check for spec deviations, and test - in a single automated step.
Command Claude Code
Commit staged changes, create or update a pull request.
Command Claude Code
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
Command Claude Code
Run the full specification pipeline - specify, review, revise, and plan - in a single automated step.
Command Claude Code
Forensic audit of an implementation against its authoritative specification.
Command Claude Code
Architectural review of a specification before implementation begins.
Skill Claude CodeCodex
Resolve reviewer comments on a pull request or pasted feedback using a six-step evidence-grounded protocol. Use when asked to resolve review feedback, address reviewer comments, process PR comments, triage review feedback, apply review suggestions, handle code review feedback, decide which review comments to accept or…
Skill Claude CodeCodex
Produce structured architectural comparison documents that evaluate two tools, technologies, or solutions against weighted criteria. Use when asked to compare tools, evaluate alternatives, write a technology assessment, create a build-vs-buy analysis, or produce a recommendation report. Also use when someone says…
Skill Claude CodeCodex
Create or validate project context files (AGENTS.md, CLAUDE.md, GEMINI.md). Use when bootstrapping a new project, initializing agent configuration, writing a context file, or when asked to create, review, audit, or validate an existing context file. Handles codebase archaeology, user interviews, golden-rule…
Skill Claude CodeCodex
Use when asked to create a pull request, open a PR, or submit changes for review. Handles branch verification, change analysis, title and description generation, and gh pr create. Do NOT use for committing, pushing without PR, or reviewing existing PRs.
Skill Claude CodeCodex
Explain technical concepts, mechanisms, and systems to a technically fluent reader who is unfamiliar with the specific topic. Use when asked to explain how something works, walk through an algorithm or protocol, write a deep-dive or onboarding article, answer 'what is X', 'why does X behave this way', 'how does X…
Skill Claude CodeCodex
Use when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits format, and project style matching. Do NOT use for pushing, creating PRs, or branch management beyond safety checks.
Skill Claude Code
Detect when a missing Agent Skill would have made the current task faster or more reliable, then scaffold a candidate SKILL.md for user review. Use after a non-trivial task when one of these signals fires: the same procedure repeated 3+ times, error recovery required inventing a workflow, the user corrected the…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: