Agent Skills

---

name: browser4-web-miner

description: Groups similar web pages together and produces an interactive HTML report with clusters of related pages, plus Excel spreadsheets for analysis. Use when the user wants to cluster downloaded HTML files, convert detail web pages into interactive views, or analyze a folder of web pages locally.

---

name: coworker

description: Reference for the Coworker file-queue automation system: task lifecycle, directory state machine, PowerShell workers, scheduler configuration, and operational conventions. Use when you need to understand how Coworker works or debug its behavior.

---

name: data-validation

description: Validates data against common and custom rules (required fields, formats, ranges). Use when checking data quality, input validation, or enforcing schemas and constraints.

---

name: form-filling

description: Automatically fills web forms using provided field data and can optionally submit the form. Use when automating form input, testing forms, or submitting structured data to websites.

---

name: maintenance

description: Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra). Use when asked to run maintenance, check quality, verify docs, audit SKILLs, or clean up artifacts.

---

name: mcp-builder

description: Guide for creating advanced-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).

---

name: organize-task-files

description: Lists, pairs, deduplicates, and moves task files across the Coworker task state machine (0draft → 6git-pushed). Use when asked to organize, clean up, or audit task files.

---

name: pdf

description: Extracts text and tables from PDF files, fills PDF forms, and creates/merges/splits PDF documents. Use when users mention PDFs, forms, document extraction, or PDF generation.

---

name: run-tests

description: Discovers and runs Browser4 test suites (unit, integration, E2E, CLI, PowerShell, real-world scenarios, production acceptance). Use when asked to run, check, or verify tests.

---

name: task-token-usage

description: Analyzes Claude Code session traces (JSONL) and draft task files to report token usage per task. Use when asked about token usage, session costs, or task efficiency metrics.

---

name: test-production

description: Runs bin/test-production.ps1 to acceptance-test a production (or prerelease) release of browser4-cli. Use when asked to run production tests, acceptance-test a release, or verify the published CLI.

---

name: weather

description: Fetches current weather conditions and a 7-day forecast for a requested location using Open-Meteo geocoding and forecast APIs. Use when the user asks about weather, temperature, rain, wind, or a weekly forecast for a place.

---

name: web-scraping

description: Extracts data from web pages using browser automation and CSS/JavaScript selectors. Use when you need to scrape titles/text/structured fields from live web pages or when the user mentions scraping, extraction, or selectors.

---

name: ask-questions-if-underspecified

description: Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

---

name: audit-library-health

description: Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.

---

name: backend-development

description: Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.

---

name: backprop

description: Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

---

name: best-practices

description: Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

---

name: browse-and-evaluate

description: Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

---

name: build-workspace-docs

description: Use when regenerating README.md and WORK_AREAS.md in a managed library workspace. Always dry-run first to preview changes.

---

name: caveman

description: Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens ~75% vs prose while staying precise. Triggers on any write to SPEC.md or when user says "caveman", "compress this", "be brief".

---

name: changelog-generator

description: Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

---

name: check

description: Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".

---

name: code-documentation

description: Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.