AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Audience Judgment Framing

skill-suibianqugenichenghaole-pm-workflow-system-audience-judgment-framing · by suibianqugenichenghaole

触发:文档/PPT/PRD需先定读者判断;不触发:需求价值→用pm-value-anchor;需求澄清→用pm-requirement-intake;输出:读者判断+证据

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-suibianqugenichenghaole-pm-workflow-system-audience-judgment-framing

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-suibianqugenichenghaole-pm-workflow-system-audience-judgment-framing)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Audience Judgment Framing? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Audience Judgment Framing

Use this skill before creating or reviewing an artifact that has readers.

The core principle: any artifact with a reader should first define what judgment the reader should form after reading it.

Core Job

Frame the artifact around:

  • who will read it
  • what decision, judgment, or confidence they need to form
  • what evidence they need
  • what they may question
  • what the artifact must not over-explain or under-prove

This skill prevents outputs that are internally complete but fail their audience.

Use When

Use when preparing or reviewing:

  • PRD / requirement docs
  • prototype annotations
  • embedded PRD left-side documents
  • review materials
  • project summaries
  • weekly/monthly reports
  • performance summaries
  • PPT or presentation narratives
  • leadership updates
  • cross-team handoff docs

Do Not Use When

Do not use this skill for:

  • purely private notes with no reader
  • raw memory capture
  • simple file edits or small local changes
  • artifacts where the reader and expected judgment are already obvious and low-risk

Reader Types

Common reader frames:

  • leadership: wants value, progress, risk, ownership, and next-step confidence
  • development: wants implementable rules, boundaries, states, data expectations, and dependencies
  • testing: wants verifiable behavior, edge cases, acceptance criteria, and regression risk
  • design: wants layout intent, interaction priority, component reuse, and visual constraints
  • operation/content: wants process impact, configuration rules, and action ownership
  • user/customer-facing reviewer: wants clarity, benefit, trust, and reduced confusion
  • future self / future AI: wants continuation pointers, stable decisions, and unresolved items

Working Flow

1. Identify the artifact

Name the artifact and its situation:

  • PRD
  • PPT
  • review doc
  • embedded PRD
  • project summary
  • handoff
  • report

2. Identify the primary reader

Choose one primary reader. Secondary readers may exist, but do not let the artifact serve everyone equally.

3. Define the expected judgment

Write one sentence:

After reading this, the reader should conclude that {judgment}.

Examples:

  • "this requirement is clear enough for development"
  • "this project has produced meaningful business progress"
  • "this prototype is ready for review but not freeze"
  • "this AI workflow improves continuity, not only writing speed"

4. Identify required evidence

List the evidence needed to support that judgment:

  • facts
  • metrics
  • milestones
  • concrete examples
  • before/after contrast
  • risk handling
  • state coverage
  • implementation boundaries
  • user/data feedback

5. Predict reader objections

Ask:

  • what would this reader doubt?
  • what would they ask next?
  • where might they think the output is vague, inflated, or incomplete?
  • what proof would make them more confident?

6. Shape the artifact

Recommend what the artifact should emphasize, reduce, or restructure.

For example:

  • leadership materials should convert work detail into impact and confidence
  • PRDs should convert product intent into implementable and testable rules
  • embedded PRDs should keep explanation on the left and real prototype on the right
  • project summaries should convert scattered work into state, result, risk, and next step

Output Format

## Audience judgment frame
- Artifact:
- Primary reader:
- Expected judgment:
- Evidence needed:
- Likely objections:
- Emphasis:
- Reduce / avoid:
- Recommended structure:

Relationship With Other Skills

  • Use before pm-prd-writer when reader confidence matters.
  • Use before pm-embedded-prd when the left document must guide review judgment.

Self-Check

Before finishing, check:

  • Did I choose one primary reader?
  • Did I define the judgment, not only the topic?
  • Did I identify evidence instead of relying on polished wording?
  • Did I predict likely objections?
  • Did I avoid turning every artifact into a leadership report?

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.