AGENT SKILLBY RETIEEDRA-PROFOUND
Claude code discoverability auditor
AT A GLANCE
Claude code discoverability auditor is an agent skill for SEO. Audits documentation, pricing, compatibility, and technical pages for retrieval and accurate recommendation inside Claude Code. It is published by retieedra-profound in the retieedra-profound/skills-marketing-library GitHub repository under the MIT license. To add it, run npx skills add retieedra-profound/skills-marketing-library --skill claude-code-discoverability-auditor
- REPO STARS
- NOT AVAILABLE
- LICENSE
- MIT
- CATEGORIES
- SKILL.MD SIZE
- 3.2 KB65 LINES
QUICK ANSWER
- WHAT IT IS01
- Audits documentation, pricing, compatibility, and technical pages for retrieval and accurate recommendation inside Claude Code. It brings Profound's specific operating context into Claude code discoverability auditor, so the agent is guided by a sharper source than a generic prompt.
- INPUTS02
- Context the agent needs: your goals, audience, constraints, and any source material the skill asks for.
- OUTPUT03
- A ready-to-use result: the analysis, copy, or recommendations the agent produces.
INSTALL
One command adds this skill from its source repository.
npx skills add retieedra-profound/skills-marketing-library --skill claude-code-discoverability-auditorREAD THE SKILL.MD BELOW BEFORE YOU RUN IT. SKILLS INSTRUCT YOUR AGENT.
SKILL.MD
The full file, as published in the source repository. Copy it, download it or open it on GitHub.
FRONTMATTER
- name
- claude-code-discoverability-auditor
- description
- Audits documentation, pricing, compatibility, and technical pages for retrieval and accurate recommendation inside Claude Code. Use when a developer product, API, SDK, infrastructure tool, or SaaS company wants to improve how Claude Code agents discover, evaluate, and use it.
ON THIS PAGE · 5
Claude Code Discoverability Auditor#
Research basis#
This skill operationalizes Profound's research, Claude and Claude Code are distinct Answer Engines (opens in a new tab), 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#
- 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.
- Audit discovery: navigation, internal links, sitemap, robots controls, canonical URLs, status codes, and rendered text.
- 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
- Audit product facts: supported versions, platform constraints, limits, uptime claims, pricing units, rate limits, data handling, and availability.
- Check consistency across docs, pricing, README files, package registries, examples, and changelogs.
- Identify missing decision pages such as compatibility matrices, migration guides, troubleshooting references, and pricing explanations.
- Test representative tasks using fresh sessions and record whether the product is mentioned, retrieved, and represented accurately.
- 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:
- Executive diagnosis.
- Task-to-page coverage map.
- Technical fact ledger with canonical source and freshness owner.
- Retrieval blockers and conflicting claims.
- Page-level recommendations with proposed facts, structure, and examples.
- Claude versus Claude Code test matrix.
- 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.
FAQ
07 QUESTIONS
01What is the Claude code discoverability auditor agent skill?
Audits documentation, pricing, compatibility, and technical pages for retrieval and accurate recommendation inside Claude Code. It is listed under SEO in the 100xLab agent skills directory.
02How do I install Claude code discoverability auditor in Cursor, Claude Code, or Codex?
Run npx skills add retieedra-profound/skills-marketing-library --skill claude-code-discoverability-auditor in the project where you want it, then ask your agent for the skill by name. The --skill flag installs only Claude code discoverability auditor, not every skill in the repository.
03What does the Claude code discoverability auditor SKILL.md cover?
The SKILL.md includes sections on Research basis, Goal, Intake, Workflow and Output. Read the full text on this page or in plain markdown at /resources/agent-skills/retieedra-profound-skills-marketing-library--claude-code-discoverability-auditor--on6m9p/raw.
04Which agents can use Claude code discoverability auditor?
Claude code discoverability auditor installs with the cross-agent skills installer (npx skills add), which sets it up for agents such as Claude Code, Cursor and Codex. Each agent loads the SKILL.md when you ask for the skill by name.
05What license is Claude code discoverability auditor under?
The retieedra-profound/skills-marketing-library repository declares the MIT license. Read the license file in the repository before you copy or redistribute the skill.
06Is Claude code discoverability auditor free to use?
Reading, copying and installing Claude code discoverability auditor costs nothing: it is published in a public GitHub repository under the MIT license. Reuse and redistribution follow that license.
07Where is the source of Claude code discoverability auditor?
Claude code discoverability auditor comes from https://github.com/retieedra-profound/skills-marketing-library. The SKILL.md is at https://github.com/retieedra-profound/skills-marketing-library/blob/HEAD/profound/claude-code-discoverability-auditor/SKILL.md. The author is retieedra-profound.
Need an agent workflow built around your stack?
Tell us the workflow you want automated. We reply within 4 working hours (IST).
ATTRIBUTION
Claude code discoverability auditor was written by its original authors and is published in retieedra-profound/skills-marketing-library (opens GitHub in a new tab) under the MIT license. All rights stay with the original authors.
100xLab did not write, maintain or endorse this skill. This page lists it for discovery. Repo stars belong to the source repository, not to the skill. Review any skill before you install it.