Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v10-case-study-buildergit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-case-study-builder)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-case-study-builder"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-case-study-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 110 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.02840 |
| Opus 5 | $0.00056 | $0.01420 |
| Sonnet 5 | $0.00022 | $0.00568 |
| Haiku 4.5 | $0.00011 | $0.00284 |
Grade A, and why
prd-v10-case-study-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Study Builder
Position in workflow: v1.0 Mom Test Interview → v1.0 Case Study Builder → v1.0 Testimonial Collector, GTM channels
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | Short-format case (testimonial + 1-paragraph story + logo); single placement |
| standard | Full case study (1,500 words) + short and medium derivatives + customer-approved + 3 channel placements |
| deep | Long-form case (2,500–4,000 words) + multi-format derivatives (PDF, blog, video, conference talk) + measurable outcome quantified + outcome-attribution interview |
What This Does
Turns customer success — already documented as CFD-* evidence and ADO-REF-* candidates — into structured case studies. Case studies are the pragmatist buyer's #1 reference signal: they need to see a customer in their segment achieving the outcome they want, with enough detail to make it credible.
This is an operational "doing" skill, not a strategy skill. The strategic question (which segment, what story angle, what outcome to highlight) was answered by prd-v10-chasm-adoption-moore. This skill produces the artifact.
How It Works
- Identify candidate customers — Pull from ADO-REF-* candidates and CFD-* entries with strong outcome quantification. Must satisfy:
- In-beachhead (or in an adjacent segment where the story would still resonate)
- Has a quantifiable outcome to talk about
- Willing to be public (consent path is clear)
- Run the case-study interview — Extended Mom Test interview (45–60 min), focused on:
- Before-state (specific past: what life was like, what tools, what cost)
- Trigger (what changed; why they evaluated alternatives)
- Evaluation (who they considered; how they chose)
- Implementation (what happened in onboarding; what was hard)
- After-state (specific present: quantified outcome, time/money saved, what they can do now they couldn't)
- Structure the story — Situation → Complication → Question → Resolution (the McKinsey SCQR pattern):
- Situation: where they were before
- Complication: what broke / changed / hit a wall
- Question: what they needed to figure out
- Resolution: how they solved it (your product as one part of the answer, ideally credibly)
- Quantify outcome — Specific numbers beat vague claims:
- "Cut tier-selection time from 3 days to 30 minutes" beats "much faster"
- "Saved $12k/year on tool consolidation" beats "saves money"
- "85% activation rate (industry average 35%)" beats "great activation"
- Get customer review — Send draft to customer for accuracy + tone + legal. Iterate until approved.
- Produce in 3 formats:
- Short (testimonial — 1–2 sentences + name + role + logo): for landing pages, pricing page, ad creative
- Medium (1-paragraph + 3 bullet outcomes + logo + linked deeper): for "Customers" page, social, email
- Long (1,500–2,500 word case study): for blog, sales enablement, sales call followup
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 231 lines · 112 tokens per session scan A 5e77d9435763
prd-v10-case-study-builder is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 7d ago), licensed MIT. It adds 112 tokens to every session and 2,840 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.