Update an existing pull request. Use when the user wants to modify PR title, description, publish a draft, convert to draft, abandon, or reactivate a PR.

Archive completed or cancelled PRDs

Show implementation progress from linked tasks

Check and update PRD status through lifecycle

Pre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches, major decisions, or risky initiatives to surface hidden risks.

Quickly understand and load a codebase by examining repository structure, README, and AI documentation. Use when starting work on a new project, need to refresh context about how a project is organized, or want to get a quick overview of a codebase's architecture and purpose.

Find Mozilla telemetry probes and Glean metrics. Use when user asks about: Firefox metrics, Glean probes, telemetry data, accessibility probes, search metrics, or any Mozilla product instrumentation.

Linux process management and control

Create training and nutrition programs. Activate when users want a workout routine, meal plan, or ask "what should I do?" for fitness goals.

# Project Guidelines Skill (Example)

# Project Guidelines Skill (Example)

# Project Guidelines Skill (Example)

Onboard new projects with standardized configuration and documentation

The standard for how a repo is laid out and how files/modules are named, so every project looks the same and generated code has an obvious right place. Use when creating a new file, module, or directory, deciding where something goes, naming a file/folder, scaffolding a new repo, or reviewing whether code is well-organized. Counters the AI-slop failure mode of sprawling, inconsistently-placed, god-everything files.

Propose additions to project CLAUDE.md based on session learnings

Python development with ruff, mypy, pytest - TDD and type safety

You must use this when designing qualitative studies, developing coding schemes, or performing thematic analysis.

You must use this when selecting statistical tests, interpreting effect sizes, or conducting power analysis.

R documentation patterns with roxygen2, pkgdown, vignettes, examples, and package site structure.

Rails caching strategies including fragment caching, low-level caching with Rails.cache, cache keys, and conditional GET. Use when the user asks about caching performance or invalidation in Rails.

This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.

This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback.

This skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specum in Codex for help or command guidance.

This skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Specum in Codex to generate or refresh index artifacts.

This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Specum in Codex for status or active spec progress.

This skill should be used only when the user explicitly asks to use `$ralph-specum-switch`, or explicitly asks Ralph Specum in Codex to switch the active spec.

Record Brownian Ratchet gates.

How to use the Readwise CLI — access highlights, documents, and your entire reading library from the command line

Rebase local changes on top of remote branch updates

Use this skill when rebasing Git branches. Activate when the user mentions rebase, interactive rebase, squash commits, reorder commits, edit commit history, clean up commits before merge, rebase onto main, or fixing up commit history. Also use when rebase fails or causes conflicts.

Recursive master-orchestration for complex multi-step tasks. Decompose work, delegate execution to sub-agents, and iterate until verified. Use when users request recursive reasoning, multi-pass refinement, or explicit plan-execute-verify loops.

This skill should be used when the user asks to "migrate rego", "rego v1", "v0 to v1", "upgrade rego", "opa fmt --rego-v1", "rego breaking changes", "rego compatibility", mentions Rego version migration, or encounters v0 syntax errors in OPA 1.0+. Provides Rego v0 to v1 migration patterns and tooling.

Generate audience-targeted release announcements. Specify the audience (customers, internal team, investors, social media) and optionally a version or scope. Use after shipping to announce what was built.

Generate comprehensive release notes and changelogs. Compiles version history, feature descriptions, and breaking changes from commit information.

Implements reliability patterns including circuit breakers, retries, fallbacks, bulkheads, and SLO definitions. Provides failure mode analysis and incident response plans. Use for "SRE", "reliability", "resilience", or "failure handling".

Renames an album or track, updating slugs, titles, and all mirrored paths. Use when the user wants to rename an album or track.

# Requirements Gathering Skill

Document codebase as-is with thoughts directory for historical context

You must use this when matching research questions to appropriate designs, sampling strategies, or validity controls.

You must use this when merging findings from multiple studies into a coherent narrative with grounded evidence.

Synthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations

Customize resume for specific job postings while maintaining truthfulness

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits.

Create a feature specification from existing code

Refactors TypeScript codebases with AST-aware rename, extract, and reference finding. Use for moving functions between files, renaming across codebase, or finding all usages of a symbol.

Show RFC details or update RFC status through lifecycle

RICE prioritization scoring initiatives by Reach, Impact, Confidence, and Effort. Use for feature prioritization, roadmap planning, or when comparing initiatives objectively.

Committing working-tree changes as atomic conventional commits: analyzes the diff, groups it into coherent commits, confirms the plan, then creates GPG-signed commits carrying the mandatory X-Lerian-Ref trailer and offers to push. Use when the user says 'commit' or has changes ready to record. Skip when the tree is clean, work is still in progress, or the user wants raw git commands without grouping.

Routing feature planning through the ring-pm-team pre-dev workflow: choosing the Small Track (5 gates, <2 days) or Large Track (10 gates, 2+ days) and entering via ring:planning-small-features or ring:planning-large-features. Indexes pre-dev gates, standalone skills, and research agents. Use when starting a feature that needs systematic planning. Skip for quick exploratory work, known-solution bug fixes, or trivial changes.

Update, create, or reprioritize your product roadmap

Use when working with Roblox animation systems including playing, stopping, or blending animations on Humanoid characters or non-Humanoid models, handling AnimationTrack events, replacing default character animations, or debugging animation priority and blending issues.

Use when implementing player data persistence in Roblox, saving/loading player stats or inventory, building leaderboards with ordered datastores, handling data migration between versions, diagnosing data loss issues, or adding auto-save and shutdown-safe data handling with DataStoreService.

Use when optimizing a Roblox game for better frame rates, reducing lag, improving server or client performance, diagnosing FPS drops, handling large worlds, or when asked about streaming, draw calls, object pooling, LOD, MicroProfiler, or expensive loop operations.

R package documentation with roxygen2 and pkgdown, including reference topics, articles, and site configuration.

Execute plan tasks autonomously until completion

A safe calculator for mathematical expressions

Read files from documents directory safely

Scalable toolkit for analyzing single-cell gene expression data. Built on top of Anndata, focusing on clustering, trajectory inference, and visualization.

Use when "scientific computing", "astronomy", "astropy", "bioinformatics", "biopython", "symbolic math", "sympy", "statistics", "statsmodels", "scientific Python"

Conduct scoping conversation with user to define research question, key findings, and constraints. Generates scope.md that guides all subsequent steps. Second step of writer workflow. Requires inventory.md to exist.

Score migrated code against style guidelines and best practices. Evaluates code quality independent of functional correctness.

Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.

Search and analyze your own session logs (older/parent conversations) using jq.

Search and analyze your own session logs (older/parent conversations) using jq.

Search and analyze your own session logs (older/parent conversations) using jq.

Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.

This skill should be used when the user asks to "continue session", "resume session", "pick up where I left off", "sessionlog continue", "continue from compact", "load session context", or wants to restore context from a previously compacted session file.

Downloads and starts a local CockroachDB cluster for development using the official binary. Use when a developer needs a local CockroachDB instance, when no cluster is available, or when setting up a new development environment.

Configure lefthook git hooks with biome linting and type checking. Use when user says "setup lefthook", "add git hooks", "configure pre-commit", or "setup lefthook".

Implement internationalization in Storefront Next using i18next with useTranslation for components and getTranslation for server-side code. Use when adding translations, configuring locales, handling pluralization, using the Zod schema factory pattern, or managing extension translations. Covers namespaces, interpolation, and language switching.

Devloop commit and PR creation with validation for completed plan work

Six Thinking Hats parallel thinking—explore from six perspectives (facts, feelings, caution, benefits, creativity, process). Use for group decisions or ensuring all angles are considered.

Create new skills following the GBrain conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks MECE against existing skills. Updates manifest and resolver.

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert

Generate structured skill specifications for independent skill creators. Use when asked to ideate, brainstorm, or specify multiple skills for a domain, workflow, or problem space. Outputs self-contained specs with list-level context so each skill can be built independently. Triggers on requests like "what skills would help with X", "generate skill ideas for Y", "specify skills to cover Z workflow".

Create diagrams with Mermaid in Slidev. Use this skill for flowcharts, sequence diagrams, class diagrams, and more.

Add live coding with Monaco Editor in Slidev. Use this skill for interactive code demos, executable code, and real-time editing.

Master Slidev navigation and keyboard shortcuts. Use this skill for efficient slide control, custom shortcuts, and navigation customization.

Understand Slidev project structure and configuration. Use this skill to configure themes, addons, and customize your presentation setup.

Use and customize Slidev themes. Use this skill to apply themes, configure theme options, and create custom themes.

Add smooth slide transitions in Slidev. Use this skill for fade, slide, and custom transitions between slides.

Removes AI-generated code slop from git diffs to maintain code quality

Control Sonos speakers (discover/status/play/volume/group).

Analyze data source characteristics including update frequency, volume patterns, and schema stability.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

Generates metadata for research documents and specifications including date/time, git commit, branch, and repository info. Use when creating research documents, handoffs, or any documentation that needs timestamp and git metadata.

Spring Boot 3 patterns for configuration, DI, and web services. Trigger: When building or refactoring Spring Boot 3 applications.

Plan a sprint — scope work, estimate capacity, set goals, and draft a sprint plan

SQLMesh patterns for data transformation with column-level lineage and virtual environments. Use when building data pipelines that need advanced features like automatic DAG inference and efficient incremental processing.

Use when configuring SSH access, keys, tunnels, host diagnostics, or safe remote command workflows.

Catalog of all ssmd health metrics — sources, query methods, labels, healthy/unhealthy thresholds. Covers data pipeline Prometheus metrics, HTTP endpoints, infrastructure components, DQ scores, and composite health scoring. Use when checking environment health, interpreting metrics, setting alert thresholds, or building health dashboards.

Generate a stakeholder update tailored to audience and cadence

Expert guidance for Stan probabilistic programming language development, including modern syntax, cmdstanr/cmdstanpy integration, and testing patterns

Hydrate session context from last handoff. Triggers: resume, pick up where I left off, continue from last session, what was I working on, session status, what's the state. Use for deep hydration beyond the auto-injected summary.

Begins a new version release using git-flow. This skill should be used when the user asks to "start a release", "create release branch", "prepare a release", "git flow release start", or wants to begin a new version release.

Generate a Startup Canvas combining Product Strategy (9 sections) and Business Model (costs + revenue) for a new product. An alternative to BMC and Lean Canvas that separates strategy from business model. Use when launching a new product or evaluating a startup concept.