ai-answerability-audit
Evidence-backed deterministic audit of whether common brand questions can be answered from crawled website content.
Skill by Ishu250412
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ishu250412-ai-answerability-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, security, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ai-answerability-audit
What's inside
- Skill name
ai-answerability-audit- Description
- Evidence-backed deterministic audit of whether common brand questions can be answered from crawled website content.
- License
- Apache-2.0
- Instructions
- 24 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- answerability_rules.md · references/
- audit_answerability.py · scripts/
SKILL.md (first lines)
# AI Answerability Audit Skill Evaluates a fixed set of high-value brand questions using only evidence observed in the audited site's crawled pages. ## Statuses - `answerable`: sufficient direct evidence was observed. - `partially_answerable`: some relevant evidence exists, but the answer signal is weak or incomplete. - `not_answerable`: no reliable evidence was found. - `conflicting`: multiple materially different signals were observed. This is a deterministic, evidence-backed audit. It does not simulate an LLM and does not claim to measure actual model-answer accuracy. ## Questions - What does this company do? - What products or services does it offer? - Who is it for? - Where is it located? - How can someone contact it? - What does its primary offering cost? - What differentiates the brand? Every result includes a source URL and evidence. Missing information is never invented.
From Ishu250412/Brand--ai-readiness-audit, Apache-2.0.
More from Ishu250412/Brand--ai-readiness-audit
- 0.523score
audit-orchestrator
Ishu250412
Entrypoint orchestrator for the Brand AI-Readiness Audit Marketplace.
SkillBFreshness: BClaude Code +9 - 0.521score
freshness-corroboration
Ishu250412
Audits observable temporal signals and cross-page factual consistency without treating missing dates or copyright years as proof of staleness.
SkillBFreshness: BClaude Code +9 - 0.521score
rag-chunking-audit
Ishu250412
Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.
SkillBFreshness: BClaude Code +9 - 0.521score
crawl-render-audit
Ishu250412
Audits automated crawler access, AI crawler directives, static ingestion surfaces, render gaps, and facts locked in non-text media.
SkillBFreshness: BClaude Code +9 - 0.518score
entity-facts-audit
Ishu250412
Audits organizational identity clarity and cross-page factual consistency.
SkillBFreshness: BClaude Code +9 - 0.518score
engagement-audit
Ishu250412
Audits first-impression orientation, CTA discoverability, and responsive viewport configuration.
SkillBFreshness: BClaude Code +9 - 0.518score
structured-data-audit
Ishu250412
Audits JSON-LD structured data, visible-vs-structured parity, and question answerability.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 19, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ishu250412
- 0.523score
audit-orchestrator
Ishu250412
Entrypoint orchestrator for the Brand AI-Readiness Audit Marketplace.
SkillBFreshness: BClaude Code +9 - 0.521score
freshness-corroboration
Ishu250412
Audits observable temporal signals and cross-page factual consistency without treating missing dates or copyright years as proof of staleness.
SkillBFreshness: BClaude Code +9 - 0.521score
rag-chunking-audit
Ishu250412
Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.
SkillBFreshness: BClaude Code +9 - 0.521score
crawl-render-audit
Ishu250412
Audits automated crawler access, AI crawler directives, static ingestion surfaces, render gaps, and facts locked in non-text media.
SkillBFreshness: BClaude Code +9 - 0.518score
entity-facts-audit
Ishu250412
Audits organizational identity clarity and cross-page factual consistency.
SkillBFreshness: BClaude Code +9 - 0.518score
engagement-audit
Ishu250412
Audits first-impression orientation, CTA discoverability, and responsive viewport configuration.
SkillBFreshness: BClaude Code +9
Cite this page
ai-answerability-audit skill. Agent Mart. https://agentmart.dev/skills/ishu250412-ai-answerability-audit (last updated 2026-10-24)