portable-identity-document-template-OPEN/skills/PID-initial-creation-skill.md

---
name: pid-initial-creation
description: Create a person's initial Portable Identity Document (PID) from gathered source materials using the PID template structure. Use this skill when a user wants to generate a first PID from resumes, LinkedIn profiles, bios, project notes, personality tests, websites, social posts, portfolio materials, or other reference documents.
version: 1.0
status: draft
intended_hosts:
  - Claude Desktop
  - Codex Desktop
  - ChatGPT with file/context access
  - other local or cloud AI agent apps
---

# PID Initial Creation Skill

## Purpose

This skill creates a person's first **Portable Identity Document (PID)** from materials they gather and provide.

The goal is not to create a traditional resume. The goal is to create a rich, AI-readable, human-reviewable identity document that helps AI systems understand:

- who the person is
- what they know
- what they have done
- what they are currently focused on
- what they need
- what they can help others with
- what makes them distinctive
- what opportunities, collaborators, ideas, and resources may be relevant to them

This skill should produce a draft PID in the flow of the PID template while preserving the person's authentic voice, experience, values, interests, and intentions.

---

# Contract

This skill guarantees:

- It will create a complete first-draft PID using the standard PID template flow.
- It will use only the user's provided materials and clearly marked user statements unless the user explicitly asks for outside research.
- It will not invent credentials, achievements, affiliations, projects, relationships, or claims.
- It will identify gaps, uncertainties, and places where the user should add more detail.
- It will preserve the user's authentic signal rather than turning them into generic AI-generated professional language.
- It will include privacy cautions and avoid sensitive identifiers.
- It will produce a reviewable Markdown PID draft.
- It will produce a separate improvement checklist for the user.
- It will include customization prompts where the user may adapt the PID for their own goals.

---

# Inputs

The skill expects as many of the following as the user can provide.

## Required

- The current PID template.
- At least one source of personal/professional information.

## Recommended Source Materials

The user may provide:

- resume
- LinkedIn profile export or pasted profile text
- short bio
- long bio
- personal website text
- company website text
- project notes
- portfolio materials
- case studies
- writing samples
- social posts
- newsletters
- podcast appearances
- presentation abstracts
- business descriptions
- product/service descriptions
- personality test results
- strengths assessments
- values exercises
- testimonials
- endorsements
- publications
- education history
- certifications
- affiliations
- event participation
- personal notes about current goals
- list of what they need
- list of what they can offer
- list of things they want AI agents to discover about them

## Optional User Direction

Ask the user to provide short answers to these questions if source materials are thin:

1. What do you want to be found for?
2. What kinds of people or opportunities do you want to attract?
3. What are you open to right now?
4. What are you currently working on?
5. What do you need help with?
6. What can you help others with?
7. What makes your approach different?
8. What should AI systems not misunderstand about you?
9. What should not be included publicly?
10. What tone should the PID use: straightforward, warm, technical, entrepreneurial, creative, academic, executive, or other?

---

# Outputs

This skill produces:

## Primary Output

- `PID-draft.md`

A complete first-draft Portable Identity Document in Markdown using the PID template flow.

## Secondary Output

- `PID-review-checklist.md`

A checklist of:

- missing information
- unclear claims
- generic language to improve
- unsupported claims to verify
- privacy items to review
- suggested user edits
- sections that need more specificity
- optional customizations based on the user's goals

## Optional Output

If the user requests structured data or the host supports writing multiple files, produce:

- `PID-source-map.md` — maps PID claims back to source materials
- `PID-open-questions.md` — questions the user should answer before publishing
- `PID-publication-notes.md` — guidance for publishing via Google Drive, OneDrive, GitHub, PDF, or personal website

---

# Skill Shape

`service`

This is one bounded workflow with clear inputs and outputs.

It may optionally use a lightweight `reviewer-panel` pattern if the host supports subagents or multiple review passes.

---

# Requires

This skill requires:

- access to the PID template
- access to the user's provided source materials
- ability to read text files or pasted text
- ability to write a Markdown output file or provide Markdown text
- ability to ask clarifying questions when essential information is missing

If the host cannot read attachments, ask the user to paste the materials or provide accessible text.

---

# Ensures

Before finishing, this skill ensures:

- all standard PID sections are present
- unsupported claims are removed or marked for user verification
- sensitive details are excluded or flagged
- generic resume language is reduced
- the PID contains concrete capabilities, assets, needs, proof, and match context
- the output is organized for AI comprehension and human review
- the final answer tells the user what was produced and what still needs review

---

# Capabilities

Required host capabilities:

- CLI tools: optional
- MCP/connectors: optional
- browser access: optional; use only if user explicitly requests public web enrichment
- filesystem access: recommended for reading source documents and writing outputs
- network access: optional
- subagent support: optional
- image/document/spreadsheet support: useful but not required

If a required capability is unavailable, fail closed or ask the user for another format. Do not silently pretend to have read unavailable materials.

---

# State Scope

`project`

Persistent writes, if available:

- `PID-draft.md`
- `PID-review-checklist.md`
- optional source map and open questions files

Do not update long-term user memory unless the user explicitly asks.

---

# Host Primitive Adapter

Map abstract needs to available host actions:

- spawn subagent: optional; use reviewer personas if available
- ask user: ask only when missing information blocks a useful draft
- read/write files: read user materials and write Markdown outputs when possible
- run shell command: optional; not normally required
- use browser: only if user asks for web enrichment or public source verification
- use connector: optional for Google Drive, OneDrive, GitHub, or local files
- create durable report: required if file writing is available

If the host cannot create files, output Markdown content directly and tell the user to save it.

---

# Customization Points

This is a general-purpose PID creation skill. Users may customize it for their own needs.

## Customize Audience

The user may tune the PID toward:

- hiring
- being hired
- partnerships
- investor discovery
- advisory work
- project collaborators
- local community building
- industry networking
- research collaboration
- creator/media visibility
- AI-agent matchmaking
- NetworkSIG participation

## Customize Domain

The user may add domain-specific language; for example:

- outdoor industry
- paddlesports
- software
- AI
- manufacturing
- education
- finance
- energy
- agriculture
- local services
- consulting
- creative work
- nonprofit work
- public lands/conservation
- pet/dog training
- any other field

## Customize Privacy

The user may set rules such as:

- do not include employer names
- do not include client names
- do not include revenue numbers
- do not include family details
- do not include health information
- do not include exact street address
- do not include private projects
- summarize sensitive work at a high level

## Customize Tone

The user may request:

- concise
- warm
- executive
- technical
- entrepreneurial
- plainspoken
- academic
- creative
- community-oriented
- highly detailed
- minimally promotional

## Customize Publication Target

The user may indicate where the PID will live:

- Google Doc
- Microsoft OneDrive Word document
- public Github Markdown file
- PDF hosted in cloud storage
- personal website
- advanced PID repo (see pid-maturity-model-roadmap.md)

---

# Workflow

## Phase 1: Intake And Source Inventory

1. List all source materials provided.
2. Identify the type of each source:
   - resume
   - profile
   - bio
   - project notes
   - social posts
   - personality tests
   - portfolio
   - website
   - other
3. Determine whether source materials are sufficient to create a useful first draft.
4. If materials are too thin, ask only the most essential missing questions.

Completion criteria:

- sources are known
- missing material is identified
- privacy risks are noted

---

## Phase 2: Extract Raw Identity Signals

Extract information into these buckets:

- open-to categories
- skills and expertise
- tools and technologies
- relationships and networks
- data/content assets
- physical assets
- platforms and systems
- capital/access
- products and services
- immediate needs
- strategic needs
- constraints and gaps
- current projects
- experiments
- research
- business initiatives
- interests
- industries
- technologies
- problems
- curiosities
- experience
- education
- affiliations
- credibility signals
- values
- principles
- strengths
- weaknesses/blind spots
- energy patterns
- work style
- superpowers
- builds
- results
- experiments
- case studies
- artifacts
- additional signals
- ideal collaborators
- ideal problems
- non-ideal matches
- recent updates

Completion criteria:

- each relevant signal is captured
- uncertain signals are marked as uncertain
- no unsupported claim is promoted as fact

---

## Phase 3: Create AI-Distinctive Identity Layer

Improve machine-legibility by identifying:

1. Clear category anchoring
2. Differentiation statement
3. Named systems, methods, or frameworks
4. Vocabulary ownership
5. Explicit capabilities
6. Inputs → transformation → outputs
7. Audience and use-case specificity
8. Memorable concept hooks
9. Generic language to replace

Do not over-polish. The goal is distinctive signal, not generic professional branding.

Completion criteria:

- the PID contains clear category anchoring
- the PID includes at least one differentiation statement or flags that the user must supply one
- the PID avoids generic claims wherever possible

---

## Phase 4: Draft The PID In Template Flow

Create `PID-draft.md` using this structure:

```md
# Portable Identity Document: [Person Name]

## Overview

## Privacy And Publication Notes

# 1. Open To

# 2. What I Have

# 3. What I Need

# 4. Current Focus

# 5. Interests, Passions, Talents

# 6. History

# 7. Credibility

# 8. Identity Layer

# 9. Proof Of Work

# Additional Signals

# Match Context

# Update Log

# Appendix / Open Questions

This list is based on the pid-template.md file.  That file may evolve to a different structure.  Make sure the user has given the AI access to the latest version of this file.  
```

If the person's name is not provided, use:

```md
# Portable Identity Document
```

Do not fabricate a name.

Completion criteria:

- all PID sections exist
- weak sections include useful prompts rather than invented filler
- the draft is coherent and ready for human review

---

## Phase 5: Add Review Prompts Inside The PID

Where appropriate, insert short prompts such as:

```md
[USER REVIEW: Confirm whether this is accurate.]
```

```md
[USER ADD: Add examples, links, or proof.]
```

```md
[USER DECIDE: Keep this public, summarize it, or remove it.]
```

```md
[USER CUSTOMIZE: Adjust this section for your specific goals.]
```

Use these sparingly. The PID should be readable, not cluttered.

Completion criteria:

- important uncertainty is visible
- user knows where to refine
- the draft does not pretend to be final

---

## Phase 6: Privacy And Sensitivity Review

Review the PID for:

- exact home address
- phone numbers
- personal identifiers
- private client details
- private employer information
- family details
- health information
- financial details
- legal issues
- confidential business information
- private project details
- anything the user explicitly marked private

If found, either remove, generalize, or flag.

Examples:

- Replace exact street address with City/State/Country.
- Replace client names with industry or category.
- Replace revenue numbers with ranges or qualitative descriptions if appropriate.
- Remove sensitive personal details unless explicitly approved.

Completion criteria:

- the PID is suitable for public URL sharing, subject to user review
- sensitive items are not accidentally included

---

## Phase 7: Reviewer Panel

If subagents or multiple review passes are available, run a lightweight reviewer panel.

Use these personas:

## Designer

Reviews:

- readability
- document flow
- clarity
- tone
- human usability

## Architect

Reviews:

- structure
- section separation
- future migration to repo/data files
- machine readability

## Domain Expert

Reviews:

- whether the person's domain positioning is specific
- whether jargon is appropriate
- whether capabilities and proof are credible

## Human Advocate

Reviews:

- authenticity
- privacy
- user agency
- over-polishing
- whether the person still sounds like a real person

## Performance Expert

Reviews:

- retrieval usefulness
- whether agents can quickly identify needs, offers, capabilities, proof, and match context

## Code Expert

Normally not required for a Level 1 PID. Use only if the PID includes structured JSON, GitHub repo setup, scripts, or technical publication requirements.

Completion criteria:

- reviewer issues are either fixed or included in the review checklist

---

## Phase 8: Produce Review Checklist

Create `PID-review-checklist.md` with these sections:

```md
# PID Review Checklist

## Highest Priority Edits

## Missing Information

## Claims To Verify

## Privacy Items To Review

## Generic Language To Improve

## Suggested Specificity Upgrades

## Suggested Proof Links

## Suggested Differentiation Improvements

## Suggested Match Context Improvements

## Publication Readiness

## Optional Next-Level Upgrades
```

Completion criteria:

- the user knows exactly what to edit next
- publication risks are clear
- next steps are practical

---

## Phase 9: Publication Guidance

At the end of the PID or in `PID-publication-notes.md`, include brief guidance.

Recommended publication options:

1. Google Doc with public URL
2. Microsoft OneDrive Word document with public URL
3. Markdown file in a public GitHub repository
4. PDF hosted in cloud storage
5. Personal website page
6. Advanced PID repository

Warn:

- do not share static copies that will go out of date
- share the URL to the maintained source
- review privacy before making public
- update periodically

Completion criteria:

- the user understands where to save the PID
- the PID is URL-accessible after the user publishes it

---

# Validation

Before finishing, verify:

## Structural Validation

- [ ] PID title exists.
- [ ] Overview exists.
- [ ] Open To exists.
- [ ] What I Have exists.
- [ ] What I Need exists.
- [ ] Current Focus exists.
- [ ] Interests, Passions, Talents exists.
- [ ] History exists.
- [ ] Credibility exists.
- [ ] Identity Layer exists.
- [ ] Proof Of Work exists.
- [ ] Additional Signals exists.
- [ ] Match Context exists.
- [ ] Update Log exists.
- [ ] Open Questions or Review Checklist exists.

This list is based on the pid-template.md file.  That file may evolve to a different structure.  Make sure the user has given the AI access to the latest version of this file.  


## Faithfulness Validation

- [ ] No major claim is invented.
- [ ] Unsupported claims are flagged.
- [ ] The draft does not exaggerate credentials.
- [ ] The draft distinguishes facts from inferences.
- [ ] The draft preserves the user's actual direction and interests.

## Specificity Validation

- [ ] Generic phrases are reduced.
- [ ] Capabilities are stated explicitly.
- [ ] At least one differentiation statement is present or requested.
- [ ] Current focus is concrete.
- [ ] Needs are actionable.
- [ ] Match context is clear enough for agents to use.

## Privacy Validation

- [ ] No sensitive identifiers are included.
- [ ] Exact address is not included.
- [ ] Private details are removed or flagged.
- [ ] Public-readiness warning is included.

## AI-Usability Validation

- [ ] Section headings are clear.
- [ ] Bullets are used where helpful.
- [ ] Needs/offers/capabilities are easy to extract.
- [ ] Proof links or artifact prompts are included where needed.
- [ ] The document is suitable for future conversion into repo structure or JSON.

---

# Test Surface

This skill can be tested through:

- Static checks:
  - required sections exist
  - output file names are correct
  - no unresolved placeholders remain except intentional `[USER ...]` review prompts

- Invariant checks:
  - no invented claims
  - no sensitive identifiers
  - all PID sections appear in the correct order

- Fixture tests:
  - resume-only input
  - LinkedIn-only input
  - project-notes-only input
  - sparse input
  - highly technical input
  - nontraditional career input
  - business owner input
  - student/early-career input
  - retired/advisory-focused input

- Behavioral tests:
  - agent asks for missing essentials when needed
  - agent does not fabricate information
  - agent flags uncertainty
  - agent produces review checklist
  - agent performs privacy review before finishing

- LLM-as-judge evals:
  - authenticity
  - specificity
  - usefulness for AI matching
  - clarity
  - faithfulness to sources

---

# Edge Cases

Actively handle:

- user provides only a resume
- user provides only scattered notes
- user has multiple careers or identities
- user has no formal resume
- user is early career
- user is retired or semi-retired
- user is a founder with multiple companies
- user has confidential clients
- user has sensitive personal history
- user wants to be hired but also wants partnerships
- user has many interests and no clear focus
- user has no obvious proof of work
- user uses vague language
- source materials contradict each other
- source materials are outdated
- source materials are overly promotional
- source materials contain private information
- user wants a highly public PID
- user wants a semi-private PID
- user plans to migrate to a GitHub PID repo later

---

# Ratchet Rules

When this skill discovers a recurring mistake, ambiguous case, failed validation, or agent shortcut, convert the lesson into at least one durable artifact:

- updated skill instruction
- anti-pattern
- example prompt
- validation checklist item
- privacy rule
- source-material intake question
- fixture case
- output schema requirement
- reviewer-panel rule

Do not merely fix the current PID. Improve the skill so future PID drafts are better.

Examples:

- If the agent invents achievements, add a stronger unsupported-claim rule.
- If the agent misses privacy risks, add a privacy checklist item.
- If the agent creates generic language, add examples of stronger specificity.
- If the agent struggles with early-career users, add an early-career fixture.
- If users repeatedly omit "What I Need," add intake questions for needs.
- If users do not know their differentiation, add a differentiation interview step.

---

# Anti-Patterns

Do not:

- write a traditional resume
- reduce the person to job titles
- over-polish the person into generic professional branding
- invent claims
- invent metrics
- invent credentials
- invent affiliations
- invent current goals
- include sensitive identifiers
- include exact home address
- expose private client names without approval
- assume all source materials are current
- bury needs and offers in long prose
- omit the review checklist
- skip privacy review
- skip uncertainty flags
- create a PID that sounds like everyone else
- use vague phrases like "innovative," "hardworking," "detail-oriented," or "customer-focused" without concrete proof
- ask AI to make the person sound like internet averages instead of themselves

---

# Run Receipt

For serious use, leave a short run receipt at the end of the final response or in a separate file:

```md
# PID Creation Run Receipt

## Inputs Used

## Outputs Produced

## Sections Completed

## Sections Needing User Review

## Privacy Checks Performed

## Unsupported Claims Removed Or Flagged

## Validation Results

## Ratchet Lessons

## Recommended Next Steps
```

---

# Final Report

When finished, report:

- what was produced
- what source materials were used
- what was validated
- what still needs user review
- whether any sensitive material was removed or flagged
- where the user should publish the PID
- what optional next-level upgrades are recommended

Keep the final report concise unless the user asks for detail.

---

# Suggested User Prompt

Users can run this skill with a prompt like:

```text
Use the PID Initial Creation Skill to create my first Portable Identity Document.

I am providing:
1. my source materials
2. the PID template
3. this skill

Create:
- PID-draft.md
- PID-review-checklist.md

Follow the PID template flow. Do not invent claims. Flag anything uncertain. Remove or flag privacy-sensitive details. Make the PID specific, authentic, and useful for AI agents to understand what I know, what I have, what I need, what I am working on, and what kinds of opportunities or collaborators would be relevant.
```

---

# Advanced Optional Prompt

For users who want a stronger first draft:

```text
Before drafting my PID, first extract my raw identity signals into buckets:
- skills
- assets
- needs
- current focus
- interests
- history
- credibility
- identity layer
- proof of work
- additional signals
- match context

Then generate the PID draft.

After drafting, run a review pass for:
- specificity
- authenticity
- privacy
- AI findability
- missing proof
- unsupported claims

Finally, produce a review checklist and publication notes.
```
---

# One-Sentence Version

Use the person's own materials to create a specific, authentic, privacy-reviewed Portable Identity Document that helps AI agents understand who they are, what they have, what they need, what they are building, and how they should be discovered.