marketplace

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.

Process GitHub issues end-to-end with TDD, interactive selection, conflict detection, and parallel work support. Use when the user asks to work on an issue, fix issue #N, pick issues to tackle, batch-process several issues in parallel, or spin up PRs from a prioritized issue list.

Perform repository maintenance and cleanup - garbage collection, branch pruning, stash cleanup, and integrity verification. Use when the user asks to clean up the repo, run git gc, delete merged branches, prune old stashes, verify repo integrity with git fsck, or shrink the .git directory.

Review PR workflow results and reviewer comments, then address substantive feedback and suggestions. Use when the user asks to address PR review comments, apply reviewer suggestions, reply to review threads, resolve reviewer feedback after CHANGES_REQUESTED, or work through a list of unresolved review threads on a pull request.

Active Record: models, associations, validations, callbacks, scopes, and query interfaces. Use when working with persistence layer.

Bootstrapping and configuring Rails 8 apps: new apps, config, environments, credentials, and initial structure. Use when creating or reconfiguring a Rails application.

Rails controllers: strong parameters, filters, respond_to, streaming, and HTTP semantics. Use when implementing request handling.

Rails routing: REST, resources, scopes, concerns, shallow routes, and route helpers. Use when designing URLs or debugging `routes.rb`.

Rails security: OWASP, CSRF, SQL injection, XSS, mass assignment, headers. Use when reviewing security or hardening apps.

Rails testing stack: fixtures, factories, system tests, VCR, and test helpers. Use for integrated Rails test strategy.

Authoring Ruby gems: gemspec, versioning, releases, and testing. Use when building libraries or extracting code from apps.

Minitest patterns for Ruby and Rails: assertions, parallel tests, fixtures, and Rails 8 default test stack. Use when working in `test/` directories or Minitest-only projects.

RSpec 3 patterns: expectations, contexts, shared examples, factories, and request specs. Use when writing or fixing RSpec tests in Ruby or Rails projects.

Universal dependency installer that auto-detects the project's package manager (uv, bun, npm, yarn, pnpm, cargo, go, bundler, brew) and runs the correct install command for dev, global, or project-local installs. Use when the user wants to install dependencies without worrying which package manager the project uses, add a package as a dev dependency, install globally, sync the lockfile, or when they mention "install dependencies", "add package", or "run the right package manager here".

Review gate owned by code-reviewer; security-engineer leads for sensitive changes (auth, payments, secrets, permissions). Covers what to check, a severity taxonomy (blocking / should-fix / nit), a review checklist, how to give actionable feedback, and when to request changes vs. approve. Use when someone says "review this", "code review", "is this ready to merge", "check this PR", "look at my diff", "LGTM?", or "give me feedback on this code".

Problem framing and requirements gathering, owned by product-manager. Clarifies the problem, users, constraints, and success criteria; separates problem from solution; cuts scope to what matters. Produces a problem statement and acceptance criteria. Use when someone says "what are we actually building", "gather requirements", "define scope", "discovery", "frame the problem", "what problem are we solving", or "what do users need".

Build phase owned by tech-lead and executed by language experts (rails-engineer, python-engineer, rust-engineer, go-engineer, bash-engineer). Covers work breakdown, sequencing, picking the right language expert, taking small reversible steps, keeping tests green, and definition of done. Use when someone says "break this down", "implement", "plan the build", "start coding", "work breakdown", "how do we build this", "create a task list", or "implementation plan".

Release readiness owned by sre with tech-lead support. Covers pre-ship checklist, rollout strategy (canary, blue-green, feature flags), observability and rollback plan, release notes, and post-deploy verification. Use when someone says "ship it", "release readiness", "ready to deploy", "go-live checklist", "rollout plan", "can we deploy", "cut a release", "pre-deploy checklist", or "what do we need before we go live".

THE ROUTER. Given any engineering task, decide which roles and lifecycle phases apply, in what order, and whether to run them sequentially or in parallel. Use when someone says "assemble the team", "who should work on this", "route this task", "what roles do I need", or invokes the /dev-collective:assemble command. Handles right-sizing so a one-line fix does not spin up the whole org.

System and technical design owned by principal-architect with staff-engineer support. Produces a design doc or RFC covering architecture, trade-off analysis, non-functional requirements, alternatives considered, and architecture decision records (ADRs). Use when someone says "design this", "write a design doc", "RFC", "architecture for", "evaluate approaches", "how should we build this", "technical design", or "write an ADR".

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", or needs guidance on slash command structure, dynamic arguments, or command development best practices for Claude Code plugins.

This skill should be used when the user asks to "create a hook", "add a PreToolUse hook", "add a PostToolUse hook", "validate tool use", "set up event-driven automation", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification).

This skill should be used when the user asks about "modular skills", "composable skills", "skill composition", "split a skill", "skill boundaries", "skill interfaces", "token-efficient skills", "single responsibility for skills", or needs design patterns and implementation guidelines for reusable skill components in Claude Code plugins.

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "validate a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "register in marketplace", or needs guidance on Claude Code plugin layout, manifest configuration, or meaganewaller-marketplace registration.

This skill should be used when the user asks to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", "audit a skill", or needs guidance on SKILL.md structure, progressive disclosure, trigger phrases, or skill quality for Claude Code plugins.

Writing Architecture Decision Records for the dotfiles repo in the existing format — numbered NNNN-slug.md files under docs/adrs/, with Context/Decision/Consequences sections and an entry in docs/adrs/README.md. Triggers on "write an ADR", "architecture decision record", "ADR for dotfiles", "docs/adrs", "decision record", "0001-specialized-agent-shell".

Writing BATS specs for the dotfiles repo — file layout, shared helpers (assert_valid_shell, assert_script_structure), running via ./bin/test, CI integration. Triggers on "BATS", "bats test", "test shell script", ".bats file", "bin/test", "test_helper.bash", "bats-core", "shell test".

Adding and editing YAML/TOML data files under home/.chezmoidata/ that templates consume — aliases, packages, themes, ghostty config, tmux plugins, authorized_keys. Triggers on ".chezmoidata", "aliases.yaml", "packages.yaml", "themes.yaml", "add a brew package", "add an alias to dotfiles", "template data", "update homebrew bundle".

Managing third-party content fetched via Chezmoi externals — home/.chezmoiexternals/*.toml.tmpl files for zsh plugins, fish plugins, tmux plugins, ghostty themes. Pinning by commit SHA so Renovate can update them. Triggers on "chezmoi external", "chezmoiexternal", "zsh-autosuggestions", "tmux plugin", "fish plugin", "pin to commit", "Renovate dotfile", "third-party content".

Authoring run_once_* and run_onchange_* scripts under home/.chezmoiscripts/ — idempotency, strict mode, DEBUG awareness, template-data inputs, and how Chezmoi decides when to re-run them. Triggers on "run_onchange", "run_once", "chezmoi script", ".chezmoiscripts", "install packages script", "post-apply script", "trigger on apply".

Writing and debugging Chezmoi .tmpl files using Go text/template — lookPath, stat, joinPath, OS branching, the .chezmoi namespace, and template data from .chezmoidata. Triggers on "chezmoi template", ".tmpl", "Go template", "lookPath", "promptStringOnce", ".chezmoi.os", "template render error", "conditional dotfile content", "branch by OS".

Day-to-day Chezmoi loop for a dotfiles repo — edit only in the source tree, preview with chezmoi diff, apply targeted or full, validate with chezmoi status. Covers partial apply, troubleshooting drift, and recovering from accidental edits in $HOME. Triggers on "chezmoi diff", "chezmoi apply", "chezmoi status", "dotfile change", "apply my dotfiles", "what changed in my dotfiles", "drift", "chezmoi destination is different".

Reads and writes plugin-local settings for the dotfiles plugin — primarily the path to the Chezmoi-managed dotfiles repository. Other skills in this plugin route through this one to resolve the working tree. Triggers on "dotfiles repo path", "where is my dotfiles", "configure dotfiles plugin", "set dotfiles location", "dotfiles plugin settings", or any time a sibling skill needs the repo path.