一键导入
wf-ralph
Run a Ralph-style, one-story-per-iteration loop using the Ralph CLI (dev, research, e2e, review), Codex-by-default, and dossier-local PRD JSON discovery.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Run a Ralph-style, one-story-per-iteration loop using the Ralph CLI (dev, research, e2e, review), Codex-by-default, and dossier-local PRD JSON discovery.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill when the user wants to test a business idea, strategy, or initiative against real-world risk. Triggers include: 'test my idea', 'what are the riskiest assumptions', 'help me validate this', 'run EMT on this', 'extract assumptions', 'assumption mapping', 'what could go wrong with this plan', 'pressure test this', 'validate this plan', 'what could go wrong with this strategy', 'identify hidden risk in this idea', or any request to pressure-test a business decision before committing resources. Runs a guided Extract → Map → Test system based on David J. Bland's Precoil methodology.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.
This skill should be used when shaping a software change and needing to breadboard the solution at the right level of abstraction (places, affordances, connections), including mapping an existing system via UI + code affordances, producing a wiring diagram, a parts/BOM plan, a fit check, and (when relevant) an extract-vs-duplicate analysis.
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
This skill should be used when a user needs a demo package that starts with a live demo (not slides) and produces both a demo script and a navigable single-file HTML runbook, including caveats, respectful competitive comparison, and LLM architecture details (RAG, evals, observability).
| name | wf-ralph |
| description | Run a Ralph-style, one-story-per-iteration loop using the Ralph CLI (dev, research, e2e, review), Codex-by-default, and dossier-local PRD JSON discovery. |
| license | MIT |
Run a "Ralph loop" using the ralph CLI.
--agent.prd.json or prd-<slug>.json).$dev-browser).Use this skill when any of the following is true:
ralph commands for dev | research | e2e | review | prd-gen.@slug and need to locate the PRD JSON under docs/04-projects/**.If any of these are missing, ask only these questions first (reply format at the end).
./prd.json if present (default)./prd-*.json@slug (search under docs/04-projects/**)--no-commitReply shorthand:
defaults (accept all defaults)1c 2c @bulk-invite-members 3b etcRun ralph from the repo root so .ralph/ state/logs land in the right place:
cd "$(git rev-parse --show-toplevel)"
Ralph auto-discovery only scans .agents/tasks/*.json. For dossier-local PRDs, pass --prd explicitly.
Resolution order:
prd.json, use it.prd-*.json:@slug (dossier folder name contains the slug), or# Find PRDs and filter by slug
find docs/04-projects -type f \( -name 'prd.json' -o -name 'prd-*.json' \) | rg '<slug>'
# Example
find docs/04-projects -type f \( -name 'prd.json' -o -name 'prd-*.json' \) | rg 'bulk-invite-members'
If you don't have rg, run the find ... and inspect the results.
ralph build 1.--prd <file> for dossier-local PRDs.ralph build 1 --agent=codex --prd "<PRD_JSON>"
Behavioural requirements:
verify skill and report commands + results.$dev-browser).ralph build 1 --agent=codex --prd "<PRD_JSON>" --no-commit
Behavioural requirements:
docs/04-projects/.../<dossier>/research/…).Recommendation:
--no-commit if you're exploringBehavioural requirements:
$dev-browser.$test-browser.<dossier>/artifacts/e2e/ (screenshots, notes, logs)Test suite status:
test-browser screenshots and a short run log.Use ralph review (do not run ralph build unless explicitly asked).
ralph review
ralph review --scope staged
ralph review --scope range --range main..HEAD
Generate a new PRD JSON into .agents/tasks/:
ralph prd --agent=codex
Override output path:
ralph prd --agent=codex --out .agents/tasks/prd-<short>.json "<feature description>"
Ralph PRD JSON uses top-level qualityGates[] and stories[].
status automatically (open -> in_progress -> done). Avoid editing story statuses manually.stories[].passes and stories[].notes are supported for downstream workflows, but Ralph does not set them.When this skill is invoked in a chat/thread:
pickup at the start (new thread) and handoff at the end (before switching threads).