Menu
Draft PRD with scope, stories, acceptance criteria, verification. Use when shaping a new feature or spec.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
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).
Based on SOC occupation classification
| name | create-prd |
| description | Draft PRD with scope, stories, acceptance criteria, verification. Use when shaping a new feature or spec. |
Copy the template: assets/prd-template.md
Fill it out in the target dossier:
prd.mdprd-overall.mdprds/: prds/<slice_id>_<slug>/prd.mdNotes:
prd.md (no prd-slice-* filenames).auth-token-rotation or invoice-pdf-export.Pull all details from shaping inputs into the PRD so it’s implementable without extra context (no information loss)
The minimum structure is defined by assets/prd-template.md and must include:
Additionally, every PRD must include:
One or more of the following:
If any of the following shaping files exist, no information should be lost from them:
brief.mdbreadboard-pack.mdspike-investigation.mdrisk-register.mdGuidance:
Try find this information:
brief.mdbreadboard-pack.mdspike-investigation.mdrisk-register.mdWhere unclear, use the ask-questions-if-underspecified skill.
prd.md in the dossier root.prd-overall.md.prds/<slice_id>_<slug>/prd.md.Ask 3-5 clarifying questions (answerable as 1A, 2B) that force a thin slice:
Run the slicing rubric:
Use the PRD template at assets/prd-template.md.
Fill sections (short, explicit; keep the template headings):
Ensure criteria map to verification; split oversized stories. If generating multiple PRDs:
prd-overall.md.prds/<slice_id>_<slug>/prd.md (one folder per slice).Each PRD must be independently implementable and must not lose shaping input information.
docs/AGENTS.md.prd-overall.md in the dossier rootprds/<slice_id>_<slug>/prd.md (folder-per-slice; lowest-level PRD filename is always prd.md)