From enterprise-harness-engineering
Writes and restructures documents using HWPR/AWOR framework to separate short human value judgments from AI-expanded content. Triggers on requests to write, rewrite, or review document quality.
npx claudepluginhub addxai/enterprise-harness-engineering --plugin enterprise-harness-engineeringThis skill uses the workspace's default tool permissions.
In the AI era, human **value judgments** get buried in AI-expanded long documents. This skill uses HWPR/AWOR markers so readers (human or AI) can quickly locate what the human actually thought.
Guides users through 3-stage workflow for co-authoring documentation: context gathering, iterative refinement, and reader testing for proposals, specs, and decision docs.
Guides users through structured workflow for co-authoring documentation via context gathering, iterative refinement, and reader testing for specs, proposals, and decision docs.
Guides users through structured workflow for co-authoring documentation, proposals, technical specs, and decision docs via context gathering, refinement, and reader testing.
Share bugs, ideas, or general feedback.
In the AI era, human value judgments get buried in AI-expanded long documents. This skill uses HWPR/AWOR markers so readers (human or AI) can quickly locate what the human actually thought.
For the detailed template, see examples/TEMPLATE-HWPR.md.
**[HWPR]** and **[AWOR]** as headers, followed by paragraph titles> block quotes for visual distinctionUser requests "help me write a document," "write a proposal," "draft a PRD," etc.
Ask the user questions to extract core value judgments:
To write an effective document, I need you to provide the following HWPR content (keep it brief, 1-3 sentences per item):
1. **Background**: Why are we doing this? What is the core problem?
2. **Judgment**: What do you think we should do? Why this direction?
3. **Trade-offs**: What was deliberately given up? What are the known risks?
Organize the user's answers into HWPR paragraphs and display them for user confirmation. Once confirmed, HWPR is never modified afterwards.
Following the TEMPLATE-HWPR.md structure, expand corresponding AWOR paragraphs after each HWPR paragraph.
User provides an existing document and requests "restructure using HWPR/AWOR," "split and label," etc.
Read the full text and mark sentences/paragraphs that appear to contain human value judgments (identification criteria: contains subjective decisions, trade-offs, "we chose" / "gave up" language, etc.).
List the identified results and ask the user to confirm each one:
I identified the following as potentially your value judgments (HWPR) in the document. Please confirm:
1. yes/no "We chose option B because..." (paragraph X)
2. yes/no "Abandoned real-time push, switched to polling..." (paragraph Y)
3. yes/no ...
Extract confirmed HWPR into **[HWPR]** paragraphs, mark remaining content as **[AWOR]**, and expand where necessary.
User requests "review the document," "check HWPR formatting," etc.
Check and report the following issues:
| Check Item | Issue Description |
|---|---|
| Missing markers | Paragraph has no [HWPR] or [AWOR] marker |
| HWPR too long | HWPR paragraph exceeds 5 sentences |
| HWPR contains AI style | HWPR has obvious AI-expansion artifacts (boilerplate, "in summary," etc.) |
| AWOR contains value judgments | AWOR contains "we decided" / "gave up" etc. that should be HWPR content |
| Incorrect marker format | Not using the standard **[HWPR]** / **[AWOR]** format |
Output format: List each issue + suggested fix.
**[HWPR]** Background and Judgment
> After in-depth analysis of user behavior data and multi-dimensional competitive market research,
> our team discovered that the core problem lies in the new user onboarding experience not being smooth enough,
> which has led to a first-day retention rate of only 35%, significantly below the industry average of 50%.
> Based on the above analysis, we believe we should start by simplifying the onboarding flow,
> improving user experience through reducing step count and optimizing interaction design... (200 words)
Problem: HWPR is too long; contains AI boilerplate ("after in-depth analysis," "multi-dimensional," "significantly below").
**[HWPR]** Background
> New user first-day retention is 35%. I believe the main cause is onboarding being too complex (5 steps).
> Plan to simplify to 2 steps first, targeting 45% retention.
**[AWOR]** Detailed Analysis
User growth data over the past three quarters: Q1 retention 38%, Q2 35%, Q3 33%, showing a continuous decline.
Competitor comparison: Product A's onboarding has only 2 steps with 52% first-day retention...
| Scenario | Condition |
|---|---|
| Pure record documents | Meeting minutes and other pure records without value judgments — HWPR may be omitted |
| Existing mature templates | Weekly reports and other documents with fixed formats — only add HWPR to "judgment/decision" sections |