Claude Skills

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. Also used during /shipyard:init for requirements gathering.

Use when working with Terraform (.tf, .tfvars), Ansible (playbooks, roles, inventory), Docker (Dockerfile, docker-compose.yml), CloudFormation, or any infrastructure-as-code files — provides validation workflows, tool chains, and common mistake prevention

Use when generating documentation, updating README files, writing API docs, creating architecture documentation, or when documentation is incomplete or outdated

Use when user asks 'how should I...' or 'what's the best approach...' after exploring code, OR when you've tried to solve something and are stuck, OR for unfamiliar workflows, OR when user references past work. Searches conversation history.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when writing tests, structuring test suites, choosing test boundaries, or debugging test quality issues like flakiness, over-mocking, or brittle tests

Use when you have a written implementation plan to execute, either in the current session with builder/reviewer agents or in a separate session with review checkpoints

Use when implementing any feature or bugfix, before writing implementation code

Precision editing for prose and copy. Use when user says "edit this", "improve this", "review my writing", "use [name]'s voice", or provides draft text to refine. Triggers on editing, voice extraction, voice library, narrative structure, microcopy.

Surface relevant learnings from past sessions. Use when starting work in a domain to avoid repeating mistakes. Triggers on "recall learnings", "past failures", "surface insights", "what did I learn".

This skill should be used when implementing slash commands that execute without Claude API calls. Use when: adding a new /bumper-* command, understanding why commands return "block" responses, debugging UserPromptSubmit hooks, or learning the pattern for instant command execution. Keywords: UserPromptSubmit, block decision, hook response, slash command implementation.

Create interactive feedback loop visualizer with poke mode. Use when user wants to map a system, see loops, understand why something keeps happening, or find intervention points.

Fresh-instance orchestration for multi-story features. Use when N>5 stories risk context exhaustion. Spawns fresh Claude per story via bash script. Triggers on "ralph", "fresh instances", "multi-story loop", "context exhaustion".

Create interactive 10-10-10 timeline simulator with parallel tracks and regret markers. Use when user wants temporal analysis, project forward, see consequences over time, or run regret minimization.

Evaluate skill quality using 8-dimension framework. Use when reviewing skills, before publishing, or auditing existing skills. Triggers on "evaluate skill", "review skill", "skill quality", "audit skills".

Creative problem-solving techniques when stuck. Use when progress has stalled, solutions feel forced, or conventional approaches have failed. Triggers on "stuck", "blocked", "can't figure out", "hitting a wall".

Human-in-the-loop code review with chunk-by-chunk approve/reject/chat loop (git add -p style). Use when reviewing PRs, diffs, patches, or documents interactively. Triggers on "review my PR", "walk through changes", "interactive review".

List, apply, or delete saved voice profiles. Use when user wants to see available voices or apply a saved voice to writing.

Turn rough ideas into iron-clad work orders. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests.

Use when preparing for interviews, assessing skills, analyzing job opportunities, navigating stakeholder politics, or developing professional capabilities. Auto-activates on interview prep, career assessment, job search, skill gaps, feedback interpretation, leadership development, or professional growth tasks.

Surface what needs human attention during complex AI work. Use when context is large, user seems overwhelmed, or after substantial output. Triggers on "what just happened", "summarize progress", "what do I need to know", "lost track", "overwhelmed".

Use when validating ideas, sizing markets, building pitch decks, preparing for investors, modeling financials, planning launches, or creating board reports. Auto-activates on fundraising, pitch, investor, TAM/SAM/SOM, unit economics, runway, or board deck tasks.

Safely remove files and directories without breaking the shell session