jamiebrynes7/dotfiles

plannotator-user-code-review

Request a code review from the user via plannotator. Use at the end of an implementation task, or when the user asks for a review cycle. Collects structured annotations, then addresses each item.

Langue du texte source : anglais

brainstorming

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation; uses plannotator for structured option/spec review and…

Langue du texte source : anglais

devils-advocate

Challenges AI-generated plans, code, designs, and decisions before you commit. Pairs with any other skill as a review layer. Uses pre-mortem analysis, inversion thinking, and Socratic questioning to find what AI missed — blind spots, hidden assumptions,…

Langue du texte source : anglais

maintaining-project-context

Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed, determines affected contracts and documentation, and coordinates updates

Langue du texte source : anglais

writing-claude-md-files

Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates

Langue du texte source : anglais

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code. Decomposes the spec into bite-sized TDD tasks; emits a beans hierarchy (epic / feature / task) when the beans CLI is available, otherwise a markdown plan.

Langue du texte source : anglais

critical-code-reviewer

Conduct rigorous, adversarial code reviews. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad…

Langue du texte source : anglais

coding-effectively

Always use this skill when writing or refactoring code. Covers general code design, error handling, file organization, and code style patterns.

Langue du texte source : anglais

comment-cleanup

Analyze and clean up code comments for accuracy, completeness, and long-term maintainability. Use when the user asks to review or clean up comments, after generating documentation, or before finalizing a pull request with comment changes.

Langue du texte source : anglais

house-style-code-comments

Use when writing, reviewing, or cleaning up code comments. Defines which comments earn their place - why-not-what, the categories that always get removed, and the few kinds worth keeping.

Langue du texte source : anglais

writing-claude-directives

Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts. Covers what earns a place in a directive, token budgets, compliance techniques, discovery, and skill portability.

Langue du texte source : anglais

whats-next

Use when the user asks what to work on next ("what's next?", "what should I pick up?", "anything ready?"). Surfaces in-progress and ready beans, grouped by parent with real blocker/container status, recommends a starting point, and hands off to…

Langue du texte source : anglais

task-implementer

Use when asked to implement a bean, work on a bean, or pick up a task by its bean id (e.g. "implement dotfiles-4byb", "work on this bean"). Drives the full loop — read, validate, branch, implement, subagent review, user review, then land via a PR with…

Langue du texte source : anglais

diff-scope

Determine which git diff to analyze based on the user's request. Supports current diff, most recent commit, or current branch.

Langue du texte source : anglais