freshness-trust-audit
Evaluates how current, consistent, and corroborated a website's key facts are, and whether those facts are supported by trustworthy evidence.
Skill by Haloninja2605
Chalk Labs
Need help deploying freshness-trust-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/haloninja2605-freshness-trust-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: security
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/freshness-trust-audit
What's inside
- Skill name
freshness-trust-audit- Description
- Evaluates how current, consistent, and corroborated a website's key facts are, and whether those facts are supported by trustworthy evidence.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Freshness & Trust Audit ## Goal Determine whether the website’s important claims are current, consistent, and supported by evidence. ## Checks - last updated metadata and freshness signals - fact consistency across pages - contradictions with independent sources - unsupported claims - stale or time-sensitive business facts - evidence quality for claims and metrics ## Typical findings - stale claim without update date - conflicting figures across pages - claim unsupported by evidence - external contradiction in key metrics ## Evidence to collect - visible timestamps - page metadata - claim values across pages - external corroboration attempts - repeated business metrics ## Decision rule A fact is not trusted if it is stale, inconsistent, or not corroborated by evidence that a retrieval system can verify.
From Haloninja2605/Adobe_Hackathon, MIT.
More from Haloninja2605/Adobe_Hackathon
- 0.521score
render-content-audit
Haloninja2605
Compares raw HTML versus rendered DOM to detect JavaScript-driven content gaps, hidden facts, and machine-invisible business information.
SkillBFreshness: BClaude Code +9 - 0.521score
semantic-entity-audit
Haloninja2605
Extracts and validates entity identity, schema metadata, and semantic coherence across visible content and structured data.
SkillBFreshness: BClaude Code +9 - 0.521score
crawl-access-audit
Haloninja2605
Audits machine reachability, crawlability, robots exposure, sitemap coverage, canonical consistency, and access health of a website.
SkillBFreshness: BClaude Code +9 - 0.521score
ai-retrieval-audit
Haloninja2605
Measures whether the site is answerable, extractable, semantically aligned, and citation-ready for AI search and retrieval systems.
SkillBFreshness: BClaude Code +9 - 0.521score
audit-orchestrator
Haloninja2605
Orchestrates the full website AI-readiness and engagement audit, coordinates sub-skills, aggregates evidence, and produces the final report.
SkillBFreshness: BClaude Code +9 - 0.518score
engagement-ux-audit
Haloninja2605
Evaluates on-site orientation, navigation clarity, conversion flow, accessibility, and user journey quality.
SkillBFreshness: BClaude Code +9 - 0.518score
recommendation-engine
Haloninja2605
Converts audit findings into mechanism-based, prioritized fixes and recommended actions grounded in evidence.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 1, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Haloninja2605/Adobe_Hackathon
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Haloninja2605
- 0.521score
render-content-audit
Haloninja2605
Compares raw HTML versus rendered DOM to detect JavaScript-driven content gaps, hidden facts, and machine-invisible business information.
SkillBFreshness: BClaude Code +9 - 0.521score
semantic-entity-audit
Haloninja2605
Extracts and validates entity identity, schema metadata, and semantic coherence across visible content and structured data.
SkillBFreshness: BClaude Code +9 - 0.521score
crawl-access-audit
Haloninja2605
Audits machine reachability, crawlability, robots exposure, sitemap coverage, canonical consistency, and access health of a website.
SkillBFreshness: BClaude Code +9 - 0.521score
ai-retrieval-audit
Haloninja2605
Measures whether the site is answerable, extractable, semantically aligned, and citation-ready for AI search and retrieval systems.
SkillBFreshness: BClaude Code +9 - 0.521score
audit-orchestrator
Haloninja2605
Orchestrates the full website AI-readiness and engagement audit, coordinates sub-skills, aggregates evidence, and produces the final report.
SkillBFreshness: BClaude Code +9 - 0.518score
engagement-ux-audit
Haloninja2605
Evaluates on-site orientation, navigation clarity, conversion flow, accessibility, and user journey quality.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get freshness-trust-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
freshness-trust-audit skill. Agent Mart. https://agentmart.dev/skills/haloninja2605-freshness-trust-audit (last updated 2026-10-24)