Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Documentation Claim Check · modu-ai | DecimalAI

documentationby modu-ai

Documentation Claim Check

modu-ai/moai-workflow-docs-claim-check

Source modu-ai/moai-adk ↗License Apache-2.0

Read-only check of whether the claims a public-facing document makes (README, release notes, install and usage guides) are supported by user-supplied evidence. Runs Preflight, Claim Triage, and Validation, splits composite claims into atomic ones, and labels each. Runs no commands and writes no fixes.

SkillScore74Maintained

Automatic

Doc Ops pack

Last verified 8/15/2026

What it changes

Passed 16 of 21 test cases with the skill, and 4 of 21 without it.

Without skill17%

With skill74%

Checks it passed that the model alone missed

Labels the default port claim as unsupported.
Labels the download dialog UI step as needs-human.
Labels the unevidenced TLS 1.3 claim as unsupported.

and 16 more in the full report

13 fixed4 passed either way6 still failing0 broke

Pass-rate lift: +57 pp
Tokens: +157%
Agent turns: 0%
Response time: +18%

Model gemini-3.6-flashMeasured 8/15/2026v117 of 23 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/modu-ai-moai-workflow-docs-claim-check/SKILL.md https://app.decimal.ai/s/modu-ai-moai-workflow-docs-claim-check/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add modu-ai-moai-workflow-docs-claim-check, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/modu-ai-moai-workflow-docs-claim-check/ and pins it in .decimal/skills.lock

decimalai skills add modu-ai-moai-workflow-docs-claim-check

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/modu-ai-moai-workflow-docs-claim-check/SKILL.md https://app.decimal.ai/s/modu-ai-moai-workflow-docs-claim-check/SKILL.md

Raw file: /s/modu-ai-moai-workflow-docs-claim-check/SKILL.md ↗ · machine-readable summary at /s/modu-ai-moai-workflow-docs-claim-check.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Here is our internal engineering RFC document 'rfc-0042-cache-invalidation.md' outlining proposed architecture for internal service cache invalidation. Audit all claims made in this RFC and evaluate whether our internal engineering decisions are valid.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies the document as an internal engineering document rather than a public user document.	Missed	Passed
Declines to perform claim triage because internal design notes are out of scope.	Missed	Passed

case-04 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md190 lines3 files

Documentation Claim Check

Assess whether the statements a public-facing document makes are actually supported by the evidence supplied alongside it. The assessment reads, judges, and reports. It changes nothing and runs nothing.

Typical subjects: a README, a release note, an install guide, a quickstart, a migration note, a feature or compatibility table.

Hard boundaries

Three boundaries are absolute. They hold even when the request asks for more; in that case perform the assessment and decline the rest in Boundary Notes.

No command execution. Do not run builds, tests, package managers, linters, network requests, or any shell command as part of the assessment. When a claim can only be settled by running something, name the exact command and the file it should run against and label the claim needs-human. Naming the command is the deliverable; running it is not.
No fixes. Do not produce patches, diffs, rewritten passages, or file edits. Describe what a maintainer would change and where, then stop.
No code review and no security review. Do not assess code quality, architecture, performance, or vulnerabilities. If asked, state the boundary in Boundary Notes and continue with the claim assessment only.

Opening the files the user pointed at, to locate the evidence they supplied, is in scope — that is reading, not executing.

Phase 1 — Preflight

Complete all three steps before triaging a single claim. If a step cannot be completed, report that and stop rather than guessing.

Confirm the document is public-facing. This skill judges documents written for users of the software: README, release notes, install and usage guides, published site pages. Internal design notes, task trackers, and private runbooks are out of scope — say so and stop.
Inventory the supplied evidence. For every item record what it is, where it came from, its version identifier, and its timestamp. An item with neither is still usable, but record it as undated: it cannot later support a

Track record

Benchmark

16 / 21

test cases passed, vs 4 / 21 without

Adoption

Users: 1
Times used: 16

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

modu-ai / moai-adk

.claude/skills/moai-workflow-docs-claim-check/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 2 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Documentation Claim Check

Hard boundaries

Phase 1 — Preflight

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills