# Claude code discoverability auditor Human Guide

## What This Is For
Audits documentation, pricing, compatibility, and technical pages for retrieval and accurate recommendation inside Claude Code. It gives the agent a clearer input/output frame for Claude code discoverability auditor: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Claude code discoverability auditor agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for Claude code discoverability auditor.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Claude code discoverability auditor guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- In 24,135 sampled responses with web search enabled, Claude searched in 93% of responses while Claude Code searched in 13%.
- Brand overlap between the two products averaged only 20%, despite their related model foundation.
- Nearly three-quarters of observed Claude Code agent visits went to documentation, informational, and pricing pages.
- Claude Code favored shorter, highly structured responses and frequently used lists and tables.
- product and canonical domain
- documentation, API reference, SDK, pricing, changelog, and support-policy URLs
- supported languages, runtimes, frameworks, regions, and environments
- authentication and installation methods
- current limitations, deprecations, and migration paths
- priority Claude Code tasks and competing tools
- Define the tasks users ask Claude Code to perform: install, authenticate, integrate, migrate, debug, compare, estimate cost, or verify compatibility.
- Map each task to its canonical page and required facts.

## Decision Points And Nuance
The original skill emphasizes: Research basis, Goal, Intake, Workflow, Output.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- These are observational results from a defined sample and period. Do not claim that page formatting guarantees a mention or that Claude Code always behaves this way.
- Map each task to its canonical page and required facts.
- Use question-shaped headings only when they match real user tasks. Do not mechanically rewrite every heading or stuff product names into documentation.
- Never infer official Anthropic ranking factors from Profound's observations. Verify crawler and access controls against current Anthropic documentation.

## Copy-And-Paste Prompt
```text
Use the Claude code discoverability auditor human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the Profound skill entry for `claude-code-discoverability-auditor`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Claude Code Discoverability Auditor

## Research basis

This skill operationalizes Profound's research, [Claude and Claude Code are distinct Answer Engines](https://www.tryprofound.com/blog/claude-and-claude-code-are-distinct-answer-engines), published August 24, 2026.

Key takeaways from the study:

- In 24,135 sampled responses with web search enabled, Claude searched in 93% of responses while Claude Code searched in 13%.
- Brand overlap between the two products averaged only 20%, despite their related model foundation.
- Nearly three-quarters of observed Claude Code agent visits went to documentation, informational, and pricing pages.
- Claude Code favored shorter, highly structured responses and frequently used lists and tables.

These are observational results from a defined sample and period. Do not claim that page formatting guarantees a mention or that Claude Code always behaves this way.

## Goal

Make the exact facts a coding agent needs easy to discover, retrieve, verify, and apply without sacrificing human usability or technical accuracy.

## Intake

Collect:

- product and canonical domain
- documentation, API reference, SDK, pricing, changelog, and support-policy URLs
- supported languages, runtimes, frameworks, regions, and environments
- authentication and installation methods
- current limitations, deprecations, and migration paths
- priority Claude Code tasks and competing tools

## Workflow

1. Define the tasks users ask Claude Code to perform: install, authenticate, integrate, migrate, debug, compare, estimate cost, or verify compatibility.
2. Map each task to its canonical page and required facts.
3. Audit discovery: navigation, internal links, sitemap, robots controls, canonical URLs, status codes, and rendered text.
4. Audit retrieval:
   - precise page titles and headings
   - direct answers before background
   - explicit commands and prerequisites
   - copyable examples
   - named versions and dates
   - stable anchors and URLs
5. Audit product facts: supported versions, platform constraints, limits, uptime claims, pricing units, rate limits, data handling, and availability.
6. Check consistency across docs, pricing, README files, package registries, examples, and changelogs.
7. Identify missing decision pages such as compatibility matrices, migration guides, troubleshooting references, and pricing explanations.
8. Test representative tasks using fresh sessions and record whether the product is mentioned, retrieved, and represented accurately.
9. Prioritize corrections by task frequency, decision impact, evidence confidence, and maintenance cost.

Use question-shaped headings only when they match real user tasks. Do not mechanically rewrite every heading or stuff product names into documentation.

## Output

Return:

1. Executive diagnosis.
2. Task-to-page coverage map.
3. Technical fact ledger with canonical source and freshness owner.
4. Retrieval blockers and conflicting claims.
5. Page-level recommendations with proposed facts, structure, and examples.
6. Claude versus Claude Code test matrix.
7. Retest plan with prompt, environment, date, and observed outcome.

Never infer official Anthropic ranking factors from Profound's observations. Verify crawler and access controls against current Anthropic documentation.