category · coding
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
/architectureExplore user intent, requirements, and design space before writing any code. Surfaces constraints, alternatives, and tradeoffs. Must run before any creative work — features, components, new functionality, or behavior modifications. Prevents building the wrong thing.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
/claude-apiRemove dead code, unused imports, commented-out blocks, and resolved TODOs. Behavior-preserving: no logic changes, only deletion of unreachable or inert code.
/cleanupReview code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
/code-reviewGenerate a conventional-commit message from the staged diff and commit. Reads the diff, analyzes the change, picks the right Conventional Commits prefix (feat/fix/refactor/chore/docs/test/ci), and commits with a descriptive message.
/commitFive-phase systematic debugging (reproduce → isolate → root cause → fix-with-regression-test → verify). Use when the user reports a bug, hits an error or failing test, or wants methodical investigation. Invocable as /debug, /debug "<symptom>", /debug --error <log>, /debug --test <test-name>.
/debugGenerate Mermaid diagrams (flowchart / sequence / state / class / ER / gantt) from code or systems.
/diagramRead-only code explainer with audience-tuned depth (non-technical / junior / practitioner / senior) and path:line citations. Never modifies files.
/explainGuides completion of a development branch: verify all tests pass, run the adversarial self-pass, open PR, wait for CI green, merge. Presents structured options for merge, PR, or cleanup. Use when implementation is complete.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
/mcp-builderOpen a GitHub pull request with a body generated from the branch's commits. Derives title and summary from commit history.
/prBehavior-preserving refactor with test gates and the bug-report-separately rule. Tests must be green before and after. Bugs found during refactor are reported separately, not fixed inline.
/refactorRepository structure tool — monorepo or polyrepo migration in either direction, preserving git history.
/repoWrite correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.
/sql-queriesDesign systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.
/system-design[Deprecated — use skill/debug instead] Five-phase debugging protocol: reproduce → isolate → root cause → fix with regression test → verify. Use when encountering any bug, test failure, or unexpected behavior. Never proposes a fix before root cause is confirmed. Enforces the 3-cycle local cap and 5-cycle total cap to prevent thrashing.
Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.
/tech-debtRun repo tests via project.yaml's tooling.test_command and report failures with path:line citations.
/testDesign test strategies and test plans. Trigger with "how should we test", "test strategy for", "write tests for", "test plan", "what tests do we need", or when the user needs help with testing approaches, coverage, or test architecture.
/testing-strategyEnsure an isolated workspace exists for feature work via git worktrees. Creates a worktree at the canonical location before any implementation. Single-repo work: <repo>/.worktrees/<name>/. Cross-repo or persistent: ~/.ai/worktrees/<name>/. Use at the start of any non-trivial feature or before executing implementation plans.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
/web-artifacts-builderToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
/webapp-testingProduce a Conventional Commits message from a staged diff or change description. Enforces Code.md §11.2: correct type prefix, 72-char subject line, imperative mood, body explaining why not what, one logical change per commit.
A refactor must not change observable behavior. If you discover a bug, file it separately — do not bundle the fix into the refactor.
Five-phase systematic debugging voice. Reproduce → isolate → root cause → fix with regression test → verify. Refuses symptom-fixes.
A coding assistant that prioritises factual accuracy over fluency. Verifies every symbol, function signature, and API against the version in use. Cites sources for non-obvious claims. Refuses to fabricate library methods or configuration keys. Surfaces uncertainty rather than guessing.
Five-phase systematic debugger. Reproduce → isolate → root cause → fix with regression test → verify.
Implements application code within the development pod after planning and test-contract definition.
Behavior-preserving refactor agent. If it finds a bug, it files it separately — never bundles a fix into a refactor.
Expertise covers component boundaries, trust boundaries, service interactions, data flows, failure modes, scalability, and long-term structural integrity.
Expertise covers programming languages, software design patterns, algorithms, data structures, testing, debugging, CI/CD, version control, API design, and software architecture. Outside: hardware engineering, civil engineering, and non-software disciplines.
Remove a file. Destructive. Requires explicit user approval.
file_deleteTargeted string replacement in a file. Requires a prior read of the same file.
file_editCreate or overwrite a file. Side-effecting.
file_writePer-line authorship for a file.
git_blameShow changes between commits, branches, or working tree. Read-only.
git_diffCommit history for a ref / path.
git_logDetail for a single commit — message, files, diff.
git_showWorking tree status — staged, modified, untracked.
git_statusEnumerate paths matching a glob pattern.
globPattern search across files. Returns matching lines with file:line locations.
grepList entries in a directory. Read-only.
list_dirRead a file from the workspace. Read-only; no side effects beyond opening the file.
read_fileFile metadata: size, mtime, mode, type.
statA Conventional Commits message: typed subject in the imperative under 72 characters, a body that explains why (not what) wrapped at 72, and the provenance trailer when an AI wrote significant code.
A PR body a reviewer can act on: a summary that names the non-obvious decisions, what changed by area, a checkable test plan, and anything the reviewer should know before merging.
Autonomous, resumable graph-driven software delivery for the current repository, GitHub-backed or local-only. Scans and reconciles work, forms small isolated bundles, hands each bundle to a tech-lead persona that runs TDD/implementation/verification/code review/documentation/PR creation in its own context, refills freed slots with newly filed issues, monitors checks, cleans merged work, audits merged changes, hands off at 80 percent context and resumes, and loops until no actionable work remains or a real human authority boundary is reached. `/develop clean` runs repository-hygiene only: discovers unmerged branches, optionally integrates them with a selectable strategy (rebase/merge/squash/none), verifies the result landed on the canonical branch, then cleans up. `--dashboard` starts a live browser board of the graph first, for either mode.
Nothing matches.