task-agent
claudeRead tasks from a YAML file (unified or legacy two-file format), implement one per run via an agent, and open a PR. Also ships `pr-reviewer` and `review-fixer` skills callable as workflow steps.
3 skills · 3 agents
10
claude
site-audit
Audit a website for UX issues, bugs, accessibility problems, and unexpected behavior. site-mapper crawls once via Playwright MCP to produce sitemap.json; ux-analyst, accessibility-auditor, performance-auditor, and bug-script-runner then run in parallel against the shared artifact. bug-script-runner generates a Playwright spec on the fly using real selectors and executes it via npx playwright test.
/
Plugin site-audit from marketplace easier-life-skills in dan323/easier-life-skills. Commands read from the repo's manifest — 11 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
What it installs
Skills (1)
audit-siteAudit a website for UX issues, bugs, accessibility problems, performance issues, and behavior that would surprise users. Use when the user says "audit this site", "check this URL", "review this website", "find issues on", "test this page", "what's wrong with", or anything about evaluating a live web
Subagents (5)
accessibility-auditorChecks WCAG 2.1 compliance using axe-cli or pa11y (via npx) with AI HTML analysis as fallback, using the checklist provided by the caller. Audits every URL in sitemap.json when available; otherwise audits only the seed.
bug-script-runnerAuthors a Playwright test spec on the fly using real selectors from sitemap.json, executes it via npx playwright test, and converts the JSON reporter output into bug findings. On Windows, uses Playwright MCP tools directly instead (npx path is unreliable on Windows due to /tmp path divergence betwee
performance-auditorAudits website performance using Lighthouse (via npx) if available, falling back to HTML analysis, using the thresholds and checks provided by the caller. Audits up to 3 pages from sitemap.json when available; otherwise audits only the seed.
site-mapperCrawls a website with Playwright (via the Playwright MCP server) and writes a sitemap.json artifact describing pages, real selectors, forms, links, and console/network errors observed during the crawl. Other site-audit agents read this artifact instead of crawling the site themselves.
ux-analystAnalyzes a website for UX issues against a checklist provided by the caller. Reads sitemap.json (produced by site-mapper) for the page list when available; falls back to extracting links from the homepage HTML if no sitemap is provided.
MCP servers (1)
playwrightruns: npx -y @playwright/mcp@latest --headless --isolated
Hooks (1)
- Stop
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/audit-logger.py
More from dan323/easier-life-skills
All 14 plugins →code-audit
claudeCode-quality audit bundle — find unused code, find breaking REST API changes, and audit logging quality. All three skills are read-only and produce prioritised reports.
3 skills
10
auto-board-task
claudeProcess the top Todo card on a GitHub Project (v2) board end-to-end: pull the board into a task-agent tasks.yml, claim the top Todo card (moved to In Progress), run task-agent against that task to open a PR, sync the PR back so the card moves to In Review, then review the PR with the `pr-reviewer` agent and apply fixes for actionable review comments. Bundles the `gh-project-sync` reconciler skill (used twice in the chain) and composes it with `task-agent` and the `pr-reviewer` and `review-fixer` skill wrappers (shipped by `task-agent`) via the `workflow` skill — `task-agent` and `workflow` must also be installed.
2 skills
10
docs
claudeDocumentation skills: generate or update CHANGELOG.md from git history, and create a root README.md with a linked /docs structure
2 skills
10
brainstorm
claudeSuggest the 5 most valuable next features or improvements for a project
1 skill
10
cost-tracker
claudeAppend token usage and estimated cost to ~/.claude/cost-log.jsonl on Stop and SubagentStop events
hooks
10
Similar plugins
karpathy-coder
claudeActive coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, simplify, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check command, and pre-commit hook. All stdlib-only.
1 skill · 1 command · 1 agent
alirezarezvani/claude-skills 29,725
slopmop
claudeQuality gates for AI-assisted codebases. Provides refit onboarding, the swab/scour/buff/sail remediation loop, and barnacle friction reporting as a Claude skill and slash commands.
1 skill · 6 commands
davepoon/buildwithclaude 3,741
sentrux
claudeMCP server for structural health analysis — 14 dimensions graded A-F, dependency cycles, coupling, dead code, test coverage, and quality gates
1 skill · 1 MCP server
sentrux/sentrux 3,342
wps
claudeWrite code that passes wemake-python-styleguide
1 skill
wemake-services/wemake-python-styleguide 2,948
geepers-agents
claudeMulti-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, games, and more. Includes orchestrators for checkpoint, deploy, quality, fullstack, research, games, corpus, web, and python workflows.
51 agents
jeremylongshore/tons-of-skills-marketplace 2,917
code-craftsmanship
claudecodexCode quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of Software Design (John Ousterhout), The Pragmatic Programmer (Hunt & Thomas), Domain-Driven Design (Eric Evans), Working Effectively with Legacy Code (Michael Feathers), and Google's Developer Documentation Style Guide (technical-documentation)
65 skills
wondelai/skills 2,680
Maintain site-audit?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins14 plugins