skills/one-pager-prd/SKILL.md
Creates concise, decision-ready product specifications (one-pagers and PRDs) that align stakeholders on problem, solution, users, success metrics, and constraints. Use when proposing new features/products, documenting product requirements, creating concise specs for stakeholder alignment, pitching initiatives, scoping projects before detailed design, capturing user stories and success metrics, or when user mentions one-pager, PRD, product spec, feature proposal, product requirements, or brief.
npx skillsauth add lyndonkl/claude one-pager-prdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When NOT to use: Detailed technical design docs (use ADRs instead), comprehensive product strategy (too high-level for one-pager), user research synthesis (different format), post-launch retrospectives (use postmortem skill).
Copy this checklist and track your progress:
One-Pager PRD Progress:
- [ ] Step 1: Gather context
- [ ] Step 2: Choose format
- [ ] Step 3: Draft one-pager
- [ ] Step 4: Validate quality
- [ ] Step 5: Review and iterate
Step 1: Gather context
Identify the problem (user pain, data supporting it), proposed solution (high-level approach), target users (personas, segments), success criteria (goals, metrics), and constraints (technical, business, timeline). See Common Patterns for typical problem types.
Step 2: Choose format
For simple features needing quick approval → Use resources/template.md one-pager format (1 page, bullets). For complex features/products requiring detailed requirements → Use resources/template.md full PRD format (1-2 pages). For writing guidance and structure → Study resources/methodology.md for problem framing, metric definition, scope techniques.
Step 3: Draft one-pager
Create one-pager-prd.md with: problem statement (user pain + why now), solution overview (what we're building), user personas and use cases, goals with quantified metrics, in-scope flows and out-of-scope items, constraints and assumptions, open questions to resolve. Keep concise—1 page for one-pager, 1-2 for PRD.
Step 4: Validate quality
Self-assess using resources/evaluators/rubric_one_pager_prd.json. Check: problem is specific and user-focused, solution is clear without being overly detailed, metrics are measurable and have targets, scope is realistic and boundaries clear, constraints acknowledged, open questions identified. Minimum standard: Average score ≥ 3.5.
Step 5: Review and iterate
Share with stakeholders (PM, design, engineering, business). Gather feedback on problem framing, solution approach, scope boundaries, and success metrics. Iterate based on input. Get explicit sign-off before moving to detailed design/development.
User Pain (Most Common):
Competitive Gap:
Strategic Opportunity:
Technical Debt/Scalability:
Simple Feature (Weeks):
Medium Feature (Months):
Large Initiative (Quarters):
B2B SaaS:
B2C Consumer:
Enterprise:
Internal Tools:
Problem:
Solution:
Metrics:
Scope:
Constraints:
Red Flags:
Resources:
resources/template.md - One-pager and PRD templates with section guidanceresources/methodology.md - Problem framing techniques, metric trees, scope prioritization, writing clarityresources/evaluators/rubric_one_pager_prd.json - Quality criteriaOutput: one-pager-prd.md with problem, solution, users, goals/metrics, scope, constraints, open questions
Success Criteria:
Quick Decisions:
Common Mistakes:
Key Insight: Brevity forces clarity. If you can't explain it in 1-2 pages, you haven't thought it through. One-pager is thinking tool as much as communication tool.
Format Tips:
Stakeholder Adaptation:
testing
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
testing
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
testing
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
testing
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.