meaganewaller

Rebuilds the sitemap and per-page navigation rail for a sitegraph static site by walking its folder structure. Use after adding, moving, renaming, or removing HTML pages under a sitegraph site root, or when asked to regenerate/refresh the nav rail, breadcrumbs, sitemap, or prev/next links.

Guides fnox secrets management configuration via fnox.toml — file structure, secrets definition, profiles, hierarchical config, mise integration, import/export, and sync. Always use fnox as a mise integration, never as standalone shell integration. Triggers on: "set up fnox", "fnox.toml", "configure fnox", "fnox profiles", "fnox secrets", "mise fnox", "migrate to fnox", "fnox sync", "fnox import", "fnox export".

Guides fnox provider selection and setup — age encryption, AWS (Parameter Store and Secrets Manager), 1Password, Bitwarden, GCP, Azure, Doppler, Vault, and local options. Triggers on: "set up fnox provider", "fnox age", "fnox aws", "fnox 1password", "which fnox provider", "configure fnox provider", "fnox encryption", "add provider to fnox".

Security best practices for fnox — key rotation, gitignore rules, CI/CD secret handling, access control, missing-secret enforcement, and avoiding common mistakes. Triggers on: "fnox security", "rotate fnox keys", "fnox gitignore", "fnox ci secrets", "fnox key rotation", "fnox access control", "fnox reencrypt", "secure fnox setup", "fnox best practices".

Create PRs via GitHub API without local git operations. Use when you want to submit file changes as a PR without committing locally — for quick fixes, typos, config updates, or when you want a clean workflow that bypasses local git state entirely.

Complete workflow from changes to PR - auto-detect related issues, create logical commits with proper issue linkage, push to remote feature branch, and create pull request. Use when user says "create pr", "let's pr", "commit and pr", "push and create pr", or wants to go from uncommitted changes to an open pull request in one step.

Analyze git commit history to derive undocumented rules, PRDs, ADRs, and PRPs. Use when the user asks to find documentation gaps, detect architectural decisions that were never recorded, derive coding conventions from commit patterns, or generate skeleton rules/PRDs/ADRs/PRPs from existing git history.

Analyze and fix failing PR checks. Use when the user asks to fix the PR, resolve failing CI checks, diagnose red GitHub Actions runs, auto-fix lint/type/test failures on a pull request, or reproduce CI errors locally before pushing corrections.

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

Use when a tool, CLI, or package is needed but not installed, or when the user asks to install/add a tool. Prefers mise for all installations.

Use when creating a pull request. Opens PR in browser for review.

Browser automation CLI for AI agents — navigate, fill forms, click, screenshot, extract data, test web apps, automate Electron desktop apps, run in Vercel microVMs or AWS Bedrock cloud browsers. Prefer over built-in browser tools. Keywords browser, automation, screenshot, scrape, Slack, Electron, agentcore.

Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.

Monitor open PRs and shepherd them toward merge. Checks CI status, review comments, merge conflicts, and takes action. Designed for /loop usage (e.g., /loop 5m /babysit-pr). Keywords: PR monitor, babysit, CI check, review response, merge conflict, PR status

Explain a diff in plain English. Works with staged changes, unstaged changes, commits, branches, or PR numbers. Use when you want to understand what changed and why. Keywords: diff, explain diff, what changed, understand changes, diff summary, review changes, read diff

Build production-ready design systems with Tailwind CSS, including design tokens, component variants, responsive patterns, and accessibility.

Use when designing memory or persistent context for an agent — deciding what to persist vs. recompute, how to retrieve only what's relevant, and how to summarize/compact history to fit the context window. Use when an agent forgets, bloats its context, or repeats work.

Interactive installer for Rosetta. Guides users through selecting and installing skills and language-specific rules at user-level or project-level, verifies paths, and optionally optimizes installed files.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills, commands, and agents.

Use when building or reviewing an evaluation for an LLM feature — assembling a representative test set, choosing pass criteria (exact match, programmatic checks, rubric, or LLM-as-judge), and catching regressions. Use when asking "how do I know this prompt or model change is better?"

Use when writing or reviewing a prompt for an LLM — making it specific, structured, and testable (clear task, role/context, examples, an explicit output contract, decomposition, room to reason) and avoiding the anti-patterns that make prompts brittle. Provider-agnostic.

Pattern for progressively refining context retrieval to solve the subagent context problem.

Use when creating or structuring a Claude Code plugin for this marketplace — the on-disk layout, the plugin.json manifest fields, the frontmatter for skills/commands/agents, and the authoring rules (no absolute paths, least-privilege tools, one coherent capability).

Use when a secret may have been committed or is about to be. Covers high-signal detection patterns and the correct remediation order — rotate the credential first, then remove it from code and history. Always redact when reporting.

This skill should be used when the user asks "should I extract this?", "is this abstraction worth it?", "am I over-engineering?", "should I DRY this up?", or when evaluating whether to create a helper, utility, base class, or shared module. Use for any "extract vs inline" decision.

This skill should be used when reviewing a design proposal, RFC, technical plan, or before starting implementation. Use when asking "what could go wrong?", "what are we assuming?", "where is this fragile?", or "what happens if X changes?". Surfaces hidden dependencies and untested beliefs.

This skill should be used when the user asks to "review this code", "check this implementation", "what's wrong with this code", "review my changes", "code review", or when examining code for quality issues.

This skill should be used when asking "is this module too complex?", "why is this hard to change?", "what's causing coupling here?", or before refactoring a tangled system. Use to audit for accidental complexity, circular dependencies, god objects, and layering violations.

This skill should be used when the user asks to "help me debug", "why isn't this working", "this is broken", "debug this", "find the bug", or when systematically investigating an issue.

This skill should be used when asking "should we add this library?", "is this dependency safe?", "should we upgrade X?", or when evaluating npm packages, gems, crates, or any third-party code. Assesses maintenance risk, security, and exit strategy.

This skill should be used when reviewing a technical design, RFC, PR description, or architecture proposal. Use when asking "what's wrong with this design?", "what am I missing?", "review my approach", or before implementing significant changes. Surfaces risks, edge cases, and alternatives.

This skill should be used when asking "how do I test this idea?", "will this change help?", "how do I measure success?", or when planning A/B tests, feature rollouts, or performance experiments. Designs falsifiable hypotheses with clear success/failure criteria.

This skill should be used when reviewing code...