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 Leo-maomao/pm-copilot --skill requirement-intakegit clone --depth 1 https://github.com/Leo-maomao/pm-copilotWrote 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/leo-maomao/pm-copilot/requirement-intake)<a href="https://agentmods.dev/skills/leo-maomao/pm-copilot/requirement-intake"><img src="https://agentmods.dev/badge/skills/leo-maomao/pm-copilot/requirement-intake/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leo-maomao/pm-copilot/requirement-intake"><img src="https://agentmods.dev/badge/skills/leo-maomao/pm-copilot/requirement-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00637 |
| Opus 5 | $0.00014 | $0.00318 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
requirement-intake 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirement Intake
Goal
Convert a vague product request into a usable brief without inventing business-critical facts.
Workflow
- Restate the request in one sentence.
- Load relevant current-state product context from the best available source: host repository, historical PRDs, specs, product docs, screenshots, analytics exports, support tickets, meeting notes, or direct user answers.
- Identify the target user, problem, desired outcome, platform, affected product area, and business goal.
- Summarize source quality: confirmed context, inferred context, stale or missing context.
- Ask only high-impact clarification questions that materially change scope, metrics, solution direction, compliance, or release risk.
- Split unknowns into
must answer before generation,can draft with stated assumption, andmust confirm before development or launch. - Stop before PRD generation if any
must answer before generationquestion is unanswered. - Stop before a
Ready for engineeringPRD/UI delivery if any engineering-blockingmust confirm before development or launchitem is unanswered. - If the user explicitly asks for iterative evaluation or says to choose recommended options automatically, select conservative defaults instead of stopping, record each default and rationale, and keep unresolved risk visible in readiness.
- Write explicit assumptions only after the user says to proceed with a draft or the unknown is low-impact.
- Do not put the same unknown in more than one bucket.
- If enough evidence exists to draft safely, proceed with assumptions instead of asking low-value questions.
- For a consequential unresolved decision, run a focused decision interview: ask one branch-changing question at a time, summarize the answer and trade-off, then ask the next question only when it changes the recommendation.
- Record a durable decision only after the user confirms it. Store the decision, alternatives, rationale, owner, and reopen condition in the run artifact; do not create or update a project-wide glossary, ADR, ticket, or host document automatically.
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.
- 10d ago First seen · 54 lines · 28 tokens per session scan A ded5f83c0aa3
requirement-intake is a skill published in the GitHub repository Leo-maomao/pm-copilot (4 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 637 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
dcjc
Use when executing multi-step tasks, when code quality or progress deviates from plan, when tool calls fail repeatedly, or when a task delay exceeds 50% of the estimate.
qsbg
Use when starting a new task, facing ambiguous requirements, choosing between multiple technical approaches, making architectural decisions, or considering parallel agent execution.
xxfw
Use when completing a milestone, encountering a major risk or blocker, finishing a task, or when more than two reporting nodes have passed without a status update.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.