truth-layer
Verify Claims Before Reporting Progress
Teams can overstate progress when builds, tests, and type checks are not verified. This skill gives Claude, Codex, and Claude Code a structured review process for honest blocker reporting.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "truth-layer" from https://skillstore.io/skills/cleanexpo-truth-layer.md and its manifest at https://skillstore.io/api/skills/cleanexpo-truth-layer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "truth-layer". A developer says the feature is ready, but only a typecheck log is available.
Expected outcome:
The report states that readiness is not verified. It lists missing test evidence, unknown runtime behavior, and the next check required.
Using "truth-layer". A release manager asks whether deployment can continue after a build warning.
Expected outcome:
The response treats the warning as unresolved until reviewed. It explains deployment impact and names the owner action needed to unblock.
Using "truth-layer". An AI agent reports that tests passed, but the test file appears empty.
Expected outcome:
The response flags the test result as unsupported. It separates the claimed success from the actual empty test coverage.
Security Audit
Medium RiskAll 12 static findings are false positives caused by Markdown code fences or inline command formatting, not Ruby or shell backtick execution. The skill is mainly a verification workflow, but it tells agents to automatically use MCP tools and Bash when blocked, which creates a medium tool-use risk. No evidence of prompt injection or data exfiltration intent was found.
Confirmed security concerns (1)
Risk Factors
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/cleanexpo-truth-layer/audits/11?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/cleanexpo-truth-layer?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/cleanexpo-truth-layer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cleanexpo-truth-layer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/cleanexpo-truth-layer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
CleanExpo. (2026). truth-layer security audit report (audit version 11) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cleanexpo-truth-layer/audits/11BibTeX citation
@techreport{cleanexpo-cleanexpo-truth-layer-2026,
author = {CleanExpo},
title = {truth-layer security audit report (audit version 11)},
institution = {Skillstore},
year = {2026},
number = {11},
url = {https://skillstore.io/skills/cleanexpo-truth-layer/audits/11},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "truth-layer security audit report (audit version 11)"
version: "unspecified"
type: report
authors:
- name: "CleanExpo"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/cleanexpo-truth-layer/audits/11"
identifiers:
- type: other
value: "skillstore:cleanexpo-truth-layer:audit:11"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Validate Delivery Claims
Check whether a feature is truly complete before status is reported to stakeholders.
Stop Release Blockers Early
Identify build, dependency, migration, or type errors before release work continues.
Audit Agent Work
Review AI-generated progress reports against real files, tests, and command results.
Try These Prompts
Use the truth-layer process to verify this claim: [paste claim]. Compare the claim with the available evidence and report any blockers.
Review the current project state for blockers before progress continues. Check build status, tests, type errors, dependencies, and missing evidence.
Assess whether the tests prove the feature works. Identify stub tests, skipped tests, missing assertions, and claims that are not supported.
Perform a full truth-layer audit for this workstream. Validate all completion claims, list unresolved blockers, rank impact, and state what must happen next.
Best Practices
- Provide the claim, expected evidence, and recent command output.
- Run checks in a safe project environment before accepting conclusions.
- Resolve blocker root causes before reporting work as complete.
Avoid
- Using the skill to approve work without running requested checks.
- Treating warnings, skipped tests, or empty tests as success.
- Allowing automatic commands in sensitive repositories without review.