Agent skills for Claude Code

Sets up eval-driven development (EDD) for an agent-assisted feature — define capability and regression evals before coding, grade them…

Guides git commit discipline, trunk-based branching, and semantic versioning/changelogs for released code, including Go modules'…

Refine a vague or raw idea into a sharp, actionable concept through structured divergent-then-convergent ideation — expand into…

Builds in thin vertical slices -- implement one piece, test it, verify it, commit, then expand -- instead of writing a whole feature in…

Extract what a user actually wants, rather than what convention makes them ask for, via a one-question-at-a-time interview with a stated…

Use when asked to verify a Laravel project before a PR, after a major refactor or dependency upgrade, or before deploying to…

Conduct business market research, competitive analysis, investor due diligence, and market-sizing that supports a business decision rather…

Use when designing a system where one agent delegates to multiple subagents/workers, deciding whether a task should fan out to multiple…

Guides instrumenting Go (and TypeScript/PHP) services with structured logging, RED/USE metrics, and distributed tracing so production…

Converts a single feature request, bug report, or vague task into one short, ordered plan document with a goal, acceptance criteria, sized…

Breaks an existing spec or clear requirement into a dependency-ordered, sized task list with checkpoints and parallelization notes.

Codified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in…

Analyze a draft prompt, diagnose gaps, match it to relevant skills already in this catalog, and output a ready-to-paste improved prompt…

Runs a two-pass vulnerability scan on a snippet, file, or diff — a static pattern pass across fixed categories (injection, secrets, auth…

Hardens a feature against attack before or while it's built — threat-model trust boundaries with STRIDE, apply the Always/Ask-First/Never…

Reviews code for security vulnerabilities across Go, TypeScript, PHP, and infrastructure config.

Audits an agent harness's own configuration — CLAUDE.md, .claude/settings.json, MCP server configs, hooks, and agent definitions — for…

Optimize for search engine visibility and ranking.

Writes a structured, human-reviewed specification before any code, deriving implementation from that written contract rather than from a…

Use when deciding whether to manually compact conversation context now versus later — at a phase boundary (research done, plan written…

Drives development with tests written before implementation code, in Go, TypeScript, PHP, or any language.