When the user wants to plan PR, write a press release, or manage media relations. Also use when the user mentions "public relations," "PR," "press release," "media relations," "news release," "journalist," "media coverage," "product announcement," or "earned media." For on-site "As Seen In" or logos page, use press-coverage-page-generator.

Advanced Python: async/await, type hints, dataclasses, context managers, decorators, testing patterns, and performance optimization.

Provide real-time quality guidance during artifact creation - section completion, anti-pattern detection, cumulative-tag and naming checks - before an artifact is finished. Use while authoring or reviewing a single SDD document.

Patterns for optimizing database query performance

Create detailed engineering implementation plans for features or fixes based on user requirements. Generates comprehensive specifications with technical approach, step-by-step implementation, and testing strategy. Use when you need to plan before building, create detailed specs for complex features, or document the approach to solve a problem.

This skill should be used only when the user explicitly asks to use `$ralph-specum-implement`, or explicitly asks Ralph Specum in Codex to run implementation for approved tasks, quick mode, or an explicit continue request.

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

Run ralphex autonomous plan execution with progress monitoring

Configure readme-and-co plugin with project-specific defaults using .claude/readme-and-co.local.md

Run the full release workflow end-to-end on a synthetic artist + release, so a teammate can see what the releases bundle produces before pointing it at a real release. Use when the user types /recoup-release-demo, says "show me the release workflow", "demo the release bundle", or "what does a release run produce". Do NOT use for a real release — use recoup-release-start.

Reflect on the current session and suggest AGENTS.md improvements based on user corrections, repeated feedback, and patterns observed during interaction. Use when ending a session to encode lessons learned. Don't use for cross-session learning from git history - use `learn` instead.

Improve relationships with communication tools, conflict resolution, and connection ideas

Ship features safely with progressive rollouts, feature flags, and canary deployments. Use when deploying risky features or need gradual rollouts.

You MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.

repo-structure-linter skill for Claude.

Fetch and analyze GitHub issues, extract requirements, gather context from referenced URLs, and compile comprehensive requirements documentation for implementation.

Rerun a discovery pipeline on an existing project. Cleans previous output and re-runs with fresh config.

Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.

Research-driven investigation. Validate solutions and explore documentation before presenting. Never ask questions you can answer yourself through research.

This skill should be used when the user has already run resume-analyzer and wants to generate the tailored resume.tex. Trigger phrases include "generate resume", "write the resume", "create resume.tex", "tailor the resume now", "build the resume from notes", or when the user asks to proceed after a resume analysis session. It reads the notes.md produced by resume-analyzer and generates a tailored LaTeX resume.

Implement findings from verification reports with scope-based parallel workflow

Use when working with Flutter Riverpod state management. Covers providers, consumers, refs, containers, overrides, async state, code generation, testing, and safe defaults.

Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing between Now/Next/Later or quarterly formats, or presenting roadmap tradeoffs to stakeholders.

Creates safe rollback procedures for deployments with automated workflows, rollback runbooks, version management, and incident response. Use for "rollback automation", "deployment recovery", "incident response", or "production rollback".

Resolves, adds, and edits routes in the project. Use when you need to determine route paths, add routes to routes.ts, or look up existing routes.

Help users add knowledge base documents to Runway Characters for domain-specific conversations

Research market rates, build negotiation strategy, and create counter-offer scripts

Use for Salesforce Flow Builder work — Record-Triggered, Screen, Scheduled, Platform-Event-Triggered, Auto-launched. Bulk-safe patterns, error handling, sub-flows, performance.

Run a reusable fresh-app benchmark for a new idea, tool, or control-plane challenger by comparing a clean `main` baseline against a committed challenger branch in separate top-level Codex sessions with isolated benchmark environments.

Generate incremental local code modules following existing codebase patterns. Use for endpoints, components, packages, collections, or modules inside an existing repo; not for full project scaffolds.

Hard-block edits outside declared frozen directories and protect paths during risky changes.

Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps engram persistence. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd".

Shows the status of all active SDD changes and orchestrator state. Uses engram for persistence. Trigger: /sdd-status, show active changes, what changes are in progress, SDD status, orchestrator status.

Search across all connected sources in one query

Send context to parent, child, or sibling session before switching

Save session state to ledger file for continuity across crashes, context switches, or /clear + reload cycles.

This skill should be used when the user asks to "recap", "brief me", "remind me", "what did we work on", "what happened last time", "catch me up on recent sessions", "sessionlog recap", "session recap", "recent session summary", "tldr sessions", or wants a quick summary of what was worked on in recent sessions for this project.

Use when onboarding to a project or creating/updating CLAUDE.md - covers codebase analysis, documentation generation, and policy management

Initialize, upgrade, or migrate the claude-harness plugin in a project. Triggers on first-time setup, plugin installation, version migration, memory directory configuration, legacy file cleanup, and project harness initialization.

Guides through installation, configuration, and first-time setup of the Claude Patent Creator system.

Use when creating CLAUDE.md files or .claude/ directories - detects project type, generates appropriate templates, and scaffolds Claude configuration with commands and hooks

Guide for setup Codemap CLI for intelligent codebase visualization and navigation

Configure screenshotr for your macOS environment. Sets output directory, format, naming, and capture preferences.

Use when "SHAP", "Shapley values", "feature importance", "model explainability", or asking about "explain predictions", "interpretable ML", "feature attribution", "waterfall plot", "beeswarm plot", "model debugging"

Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.

Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.

Comprehensive pre-deployment verification to ensure release readiness

Update the shipping address on an unfulfilled order before it ships.

Read-only: tracks AOV over time buckets and segments by new vs. returning customers.

Finds stale draft orders older than N days and optionally deletes them to reduce admin clutter.

Query all tracked product variants below a stock threshold and export a restock list grouped by vendor.

Bulk transition products through DRAFT → ACTIVE → ARCHIVED status for seasonal launches and sunsetting.

Read-only: calculates refund rate by product, collection, or period — identifies quality and listing issues.

Read-only: calculates what percentage of customers place 2+ orders within N days, segmented by product or collection.

Read-only: measures average time from return request to refund completion, surfacing SLA breaches.

Read-only: aggregates shipping revenue charged to customers vs. actual shipping line costs by carrier and method.

Read-only: aggregates tax collected by jurisdiction from order tax lines for filing prep.

Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done

Lock in user goals upfront and validate outputs against them — use to prevent scope drift

Implement Service Level Objectives (SLOs), Service Level Indicators (SLIs), and error budgets. Use this skill when defining reliability targets, measuring service health, or balancing reliability vs velocity. Activate when: SLO, SLI, SLA, error budget, reliability targets, service level, uptime target, availability target, latency target, nine nines, 99.9%.

Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.

Use when configuring or working with Solid Queue for background jobs. Applies Rails 8 conventions, database-backed job processing, concurrency settings, recurring jobs, and production deployment patterns.

Add a new machine's age public key to .sops.yaml and re-encrypt all files. Use for multi-machine setups. Use when user mentions "add key", "add machine", "sops add key", "new machine", "authorize machine", "share key", "add public key", "multi machine sops".

Synthesize supply-side and demand-side evidence into a practical sourcing judgment for a product, niche, or shortlist without collapsing platform data collection and business judgment into one step.

Control Spotify playback on macOS. Play/pause, skip tracks, control volume, play artists/albums/playlists. Use when a user asks to play music, control Spotify, change songs, or adjust Spotify volume.

SQLite performance optimization techniques

Squash-merge a PR into main. Invoke only when the user explicitly requests a squash merge. Single PR by number or current branch.

User guide for the local squash-safe `stack` CLI for stacked PR repair. Use when someone asks how to inspect, track, sync, merge, document, or undo stacked pull requests in squash-merge repositories. Prefer this tool over GitHub's `gh stack` command for this workflow.

Use this skill when analyzing stack traces. Activate when the user has a stack trace to understand, needs to decode error traces, wants to find the root cause from a stack trace, is debugging crashes, or needs help interpreting exception traces.

Identify the people who need to be informed, consulted, or asked to approve a change, project, or decision

Generates a casual, human-sounding daily standup from your git activity in the last 24 hours. Make sure to use this skill whenever the user says "standup", "daily standup", "write my standup", "what did I do yesterday", "write my daily update", or invokes /standup — even if they just ask "can you write my standup?"

Patterns for managing application state - local, global, server, and URL state

Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture

Initialize or update subsystem documentation.

Explore codebase structure, entry points, tech stack, hotspots, and call graphs

Request someone to cover one of your upcoming on-call shifts. Lists your shifts, helps identify a candidate based on availability, and creates an override after explicit confirmation. Write action - never executes without confirming.

Update a specific feature's memory files to reflect current codebase state

Switches the active Salesforce org (default target-org) using the Salesforce CLI. Use whenever someone wants to change which org CLI commands run against — whether they say "switch org", "change default org", "set my org to", "use alias", "point to", or describe wanting to work against a specific org, scratch org, sandbox, or production.

Synthesize user research from interviews, surveys, and feedback into structured insights

Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

Creates data table patterns with filtering, sorting, pagination, row actions, column configuration, server/client rendering modes, and empty/loading states. Use when building "data tables", "list views", "admin tables", or "data grids".

How tag-to-command routing works in autopilot. Defines default mappings, precedence rules, and customization patterns.

Use when the user invokes $spec-kit:tasks or /spec-kit:tasks, or asks to generate dependency-ordered tasks from the plan and repo context.

On-demand interpreted view of sprint progress, velocity, quality signals, and defect trends. Available to any role at any time — returns insight, not raw data. Works without codebase access.

Show the highest-priority work items from the backlog and help the developer pick one to work on next. Use when the user says 'pick next issue', 'what should I work on next from the backlog', 'show me the backlog', 'what's highest priority in the backlog', or 'pick an issue for me'.

Update the terminator kill phrases or case sensitivity for the current project. Rewrites only the changed fields in .claude/terminator.json; new phrases must be non-obvious; no restart needed since the hooks read config live. Use when the user asks to "update the kill phrase", "change the single/double kill phrase", or "toggle case sensitivity".

Read, search, add, and update tasks/projects/areas in Things 3 via its CLI. Use when the user says 'what's in my Things inbox', 'add this to Things', 'show today in Things', 'find Things tasks tagged X', or asks about repeating templates.

Use when you're unsure whether you actually know the answer. If you lack the evidence or context to answer reliably, abstain, ask, or fetch it — don't confabulate a confident reply.

Use when provisioning capacity, setting a timeout/limit, or committing to an estimate under uncertainty. Size a buffer to the cost of being wrong instead of optimizing to the edge.

Use when stating a forecast, estimate, or risk. Anchor on the base rate, give a confidence range instead of a point, and update the number when new evidence arrives.

Generate Mermaid Gantt charts for project timelines with phases, dependencies, and milestones

Track time, manage projects and tasks using timesheet.io CLI

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Teaches tree shaking for dead code elimination in JavaScript bundles. Use when your bundle includes unused exports and you want to reduce the final bundle size during the build step.

Reliability trend summary for a service, team, or the whole org. Reports incident volume, severity mix, and MTTR direction over a window (default 30 days). Use for standups, 1-on-1s, or quarterly reviews.

Background knowledge for droid-control workflows -- not invoked directly. Tuistory driver mechanics for terminal TUI automation via virtual PTY.