AI Agent Skills

Manages Dots task tracking with the dot CLI, dependencies, and completion reasons. Use when tracking work items across sessions or coordinating task dependencies.

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names…

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Guides the agent through creating and maintaining Capacitor plugins from scratch. Covers scaffolding a new plugin project, designing the TypeScript API, implementing nat…

Stress-test a plan through a product and founder lens before committing to it. Triggers "ceo review", "founder review", "product review", "should we even build this".

Behavior-preserving restructuring of code outside the current diff, such as extracting modules, renaming across files, or paying down debt. Triggers "refactor X", "restr…

Review the local diff against Darkroom's checklist, or summarize feedback on the active PR. Triggers "review my changes", "check this diff", "summarize PR feedback". Nat…

Write or run tests, check coverage, or drive TDD. Triggers "write tests", "run tests", "coverage", "TDD", "red-green-refactor", or a pre-merge test pass.

Code analysis through TLDR (call graphs, impact, dataflow, semantic search) for far fewer tokens than reading files raw. Triggers "who calls X", "blast radius", or befor…

Bring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything, then reads the codebase to draft what i…

App Store Connect commands: discover and run generic `asc` CLI auth, schemas, canonical verbs, pagination, output, records, API requests, and timeouts; exclude Apple Ads…

Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by posi…

Use when turning a marketing, growth, CRO, pricing, onboarding, email, ad, or acquisition idea into a useful experiment or test plan.

Turn a vague request, voice dump, rough plan, or half-written prompt into a self-contained prompt that a fresh agent can execute. Use when asked to clarify, refine, impr…

Coordinates a batch of GitHub issues through separate Claude Code sessions running in visible Herdr tabs, with tested pull requests, review loops, and gated merges. Use…