training

Plugin training from marketplace devclarity-marketplace in devclarityai/devclarity-marketplace. Commands read from the repo's manifest — 3 days ago.

Skills (9)

• api-playwright-testing

  Guides the creation of Playwright API tests from exploration through implementation. Covers API discovery, test plan creation, helper/data factory development, and test writing with human checkpoints at each stage.

• context-coverage

  Audit how agent context (CLAUDE.md, AGENTS.md, GitHub Copilot instructions, Cursor/Windsurf rules, rules directories, skills) lines up with the code across a set of repositories and generate a self-contained HTML report. The report leads with a short list of specific "things to check" (context behin

• context-management

  Sorts the lines in your agent context (CLAUDE.md, .claude/rules/, docs/, skill files) with five questions and moves each one to where it belongs: lint or CI, a ticket, CLAUDE.md, a path-scoped rule, a doc, or nowhere. Use when auditing or trimming a CLAUDE.md, when context files have grown long and

• designing-ai-workflows

  Interviews the user through the design of a new AI-enabled workflow. Frames it, drafts a skeleton early, then refines context, freedom, alignment, verification, and feedback phase by phase, including where the context window resets (same thread, a script, an in-skill subagent, or a separate skill) a

• e2e-testing

  Guides the creation of Playwright E2E tests from planning through implementation. Covers test plan creation, data seeding, Page Object Model development, and test writing with human checkpoints at each stage.

• finding-skill-opportunities

  Use when asked to find skill opportunities in a codebase, audit a repo for automatable workflows, decide what skills to write, or mine git history, existing automation, and recent Claude Code session transcripts for recurring multi-step procedures worth turning into agent skills.

• managing-locators

  Explores features to discover stable locators and fixes broken locators in Playwright tests. Two modes — explore (proactive discovery) and fix (reactive repair) — both using Playwright MCP for live browser interaction.

• skill-eval-builder

  Use when the user wants to measure or set up evals/checks for one of their skills — how fast it is, whether its output is valid, whether it fires when expected, or whether its opening classification/routing gate labels inputs correctly.

• skill-improver

  Use when reviewing, grading, critiquing, or improving an existing agent skill or SKILL.md. Checks name/scope, invocation description, structure, leanness, and surfaces concrete opportunities to add references, scripts, and determinism.