Preflight Discovery — Productivity skill for Claude Code
Structured discovery, planning, and execution workflow with task dossier.
How to install Preflight Discovery
Installs to ~/.claude/commands/33-strategies-33-strategies-claude-code-starter-kit-preflight-discovery.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/33-Strategies/33-strategies-claude-code-starter-kit/HEAD/.claude/commands/preflight-discovery.md -o ~/.claude/commands/33-strategies-33-strategies-claude-code-starter-kit-preflight-discovery.md Restart Claude Code, or start a new session, for it to be picked up.
What Preflight Discovery does
description: Structured discovery, planning, and execution workflow with task dossier allowed-tools: Read, Grep, Glob, Edit, Write, Bash(git:*), Bash(npm:*), Bash(npx:*), Task(playwright-expert) argument-hint: "" category: workflow
Preflight ▸ Discovery ▸ Plan
**Task Brief:** $ARGUMENTS
Workflow Instructions
Execute this structured engineering workflow that enforces "homework before hacking" for any code-change task (bug fix or feature). Follow each step sequent
Alternatives in Productivity
- P7 — PUA P7 骨干模式 — 方案驱动执行 19.5k ★
- Claudekit Problem Solving — Structured problem-solving tools 1.9k ★
- Run Discovery — Workflow recipe — go from a vague opportunity to validated insight and a prioritised next step by chaining 4 s 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Workflow Orchestration
A Claude Code skill for disciplined task execution with planning, verification, and self-improvement loops
Multi Agent Training Grpo
A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.
Launchpad Claude Skill
Claude Code skill for end-to-end planning and execution orchestration. Chains wave-planner, plan-review, linea
Ship It Skill
Cross-platform coding-agent skill (Claude Code / OpenCode / omp): disciplined phased workflow with mandatory a
Clirank MCP Server
(npm) API discovery for agents -- scores 210+ APIs on CLI-friendliness across 11 signals. Find the right API f
Crap Check
Runs the target repo's own wired CRAP tooling and presents the ranked worst-functions report — discovering the
Related Agents
AI Context
Compresses discovery output into the single structured task-context document every later agent reads instead o
Playwright Test Explorer
Internal Testgen role for proposing evidence-backed Playwright scenarios after Main has completed preflight an
Task Coordinator
Use this agent when starting ANY task in the UBERON ontology project. This agent MUST be used first and proact