skills

Convert an approved SEO/GEO strategy into independently executable tracker work packages.

Research and maintain an evidence-backed SEO/GEO thesis, opportunity portfolio, and execution-ready roadmap.

Deliver one tracker work package labeled `ready-for-seo-agent` through acceptance → delivery → evidence.

Codebase-driven SEO + GEO (Generative Engine Optimization) audit. Gathers site facts into SEO.md, scores the site against a fixed rubric, and writes a dated report with a prioritized improvement plan.

Turn an ADO user story — or a rough idea — into a verifiable, code-grounded blueprint a TDD executor can build from. Use when the user wants work planned before coding.

Create a PRD with an embedded Design Direction section through user interview, codebase exploration, and design intent capture. Use when building or revamping any feature with frontend or UI work — landing pages, components, UI redesigns — where design intent needs to be locked in before implementation. Extends the standard PRD process with structured design thinking: audience, tone, aesthetic direction, and the one memorable differentiator.

Right-sized guided feature development with three presets (Quick / Standard / Deep) covering everything from one-line tweaks to risky new modules. Invoke for any non-trivial feature work.

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

Review multiple pull/merge requests across GitHub, GitLab, and Azure DevOps in parallel. Thin orchestrator over the single-PR code-review skill — one agent per PR, consolidated summary, optional PR comments. Use when the user wants to review several PRs/MRs at once (release sweep, multi-repo audit, batch review).

Autonomous feature development with goal-loop verification. Front-loads all decisions through interactive stages, then drives implementation unattended against verifiable goals — re-architecting, diagnosing, and self-correcting until green or escalation thresholds hit. Use for substantial feature work with a verifiable end state ("until tests pass / type-check clean / acceptance criteria hold").

Interview the user to extract coding standards and project context, grounded in what the codebase already does. Use when user wants to generate a CLAUDE.md, CODING_STANDARDS.md, or otherwise capture conventions from an existing codebase.

Structured bug fixing with reproduction, root cause analysis, fix design, regression risk analysis, and quality review. Only invoke this skill when the user explicitly asks to use it by name (e.g. "use bug-fix", "run bug-fix") or clearly requests a structured/systematic bug fixing process. Do not invoke for general bug reports, error messages, or broken behavior — handle those directly without this skill.

Build and maintain a persistent structural index of a Java, Go, Python, or Rust codebase under .codemap/ (graph.json + MAP.md), so other skills explore via the map instead of grep + read loops. Tree-sitter based; supports polyglot repos. Use when starting work in an unfamiliar non-TS/JS repo, when the user asks to build/refresh/update the codemap, after large refactors, or before any exploration phase that would otherwise scan source files. For TypeScript/JavaScript repos, use the sibling `ts-codemap` skill — it has higher fidelity (path aliases, re-export flattening, JSX).

Optimized guided feature development with deep requirement drilling, codebase understanding, and design-quality frontend implementation. Use this skill whenever the user wants to build or implement a feature — whether they say "let's build X", "add feature Y", "implement Z", "I want to create", "can we add", or any variation. This is the go-to skill for any non-trivial software feature work. Prefer this over a plain coding response whenever the feature has more than one moving part.

Build and maintain a persistent structural index of a TypeScript/JavaScript codebase under .codemap/ (graph.json + MAP.md), so other skills explore via the map instead of grep + read loops. Uses ts-morph for high-fidelity TS/JS parsing (tsconfig path aliases, re-export flattening, JSX). Use when the user asks to build, refresh, or update the codemap on a TS/JS repo, when starting work in an unfamiliar TS/JS repo, or before any exploration phase that would otherwise scan source files. For Java/Go/Python/Rust repos, use the language-agnostic `codemap` skill instead.

Review changed code for bugs, simplicity, security, and convention adherence using parallel reviewer agents. Use when the user asks to review code, review a PR, check quality, or wants a second pair of eyes before merging.

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.