SkillAgentSearch skills...

verify-claims

Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a fresh context (never a conversation fork) so it never sees the draft β€” then reports which claims are supported, contradicted, or unverifiable

Install / Use

npx skills add pedrohcgs/claude-code-my-workflow --skill verify-claims

Installs into whichever agent you are using.

About this skill
πŸ“„

SKILL.md

Installable skill definition

Quality Score

92/100

Supported Platforms

Universal

Our assessment of verify-claims

verify-claims scores 92/100 on our quality scale, 114th of 319 Customer Support skills we index (top 36%).

Its SKILL.md is 8.7 KB long, well organised into 15 sections with 4 code examples: a thorough specification that gives an agent plenty to work with.

With 1,598 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
20/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so verify-claims is actively maintained.
  • Our last check on 2026-10-27 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-08. Automated pattern scan on 2026-10-08. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

verify-claims compared with similar skills

All 4 of these similar skills score higher than verify-claims; compare them before choosing.

SkillScoreStarsUpdatedFormat
verify-claims (this skill)by pedrohcgs921.6k3mo agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install verify-claims?
Run npx skills add pedrohcgs/claude-code-my-workflow --skill verify-claims. The install tabs above show the steps for each supported agent.
Which AI agents does verify-claims work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is verify-claims safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is verify-claims still maintained?
The repository was last updated about 3 months ago, so verify-claims is actively maintained.

name: verify-claims description: Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the claim-verifier agent in a fresh context (never a conversation fork) so it never sees the draft β€” then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use /proofread) or substance review (use /review-paper). argument-hint: "[file-or-text-path] [--source <path-or-url>] [--no-fail-closed]" allowed-tools: ["Read", "Grep", "Glob", "Agent", "Task", "Write"] disallowed-tools: ["Edit", "MultiEdit"]

/verify-claims β€” Chain-of-Verification on a Draft

Fact-check a draft using the Post-Flight Verification protocol (.claude/rules/post-flight-verification.md).

Input: $ARGUMENTS β€” path to a file containing the draft (markdown, .qmd, .tex, .md) or a shorthand pointer. Optional flags:

  • --source <path-or-url> β€” one or more source-material pointers (repeat for multiple). If omitted, the skill infers from context (e.g., papers referenced, cited arXiv URLs).
  • --no-fail-closed β€” downgrade FAIL outcomes to warnings without regeneration. Use sparingly.

When to pick this skill

  • /verify-claims (this skill) β€” ad-hoc fact-checking on any draft or text block the user hands you. One-shot, user-invoked.
  • Other skills that auto-run Post-Flight internally (/lit-review, /research-ideation, /respond-to-referees, /review-paper --peer) β€” no need to call this separately; they already run it.
  • /proofread β€” grammar, typos, overflow. Different lens.
  • /review-paper (default mode) β€” full manuscript review, not just claim verification.
  • /validate-bib β€” checks citations exist and are well-formed (structural + DOI). This skill checks they hold (the cited paper supports the attributed claim). Complementary β€” run both before submission.

How it works

Implements the 4-step CoVe loop from Dhuliawala et al. 2023 (arXiv:2309.11495), with architectural enforcement of the fresh-context independence trick.

Phase 0 β€” Pre-Flight

Confirm:

  • Draft file exists and is readable
  • At least one source pointer available (either --source or auto-detected from draft)
  • claim-verifier agent file exists at .claude/agents/claim-verifier.md

If any fail β†’ surface the failure, do NOT proceed.

Phase 1 β€” Extract claims

Read the draft. Identify factual assertions of these types:

| Type | Example | |------|---------| | Citation | "Smith (2019, JEL) shows X" | | Numerical fact | "N = 10,000", "ATT = 0.42" | | Negative literature | "No prior work studies X" | | Named entity | researcher, paper title, venue, package, estimator name | | Dataset claim | "The CPS contains field educ_attain" |

Skip: opinions, forward-looking suggestions, definitions the draft introduces.

For citation-type claims, extract the claim↔citation PAIR β€” not just the citation. Capture what the draft attributes to which work, so the verifier checks appropriateness (does Smith 2019 actually show X?), not merely existence. "Smith (2019) shows a positive wage effect" becomes {cite: Smith2019, attributed: "positive wage effect"}. This is the layer /validate-bib explicitly defers here: validate-bib confirms the citation exists and is well-formed; this skill confirms it holds. A mis-citation (the paper exists but says something else, or the opposite) is exactly a numeric/directional contradiction β†’ HIGH-WARN unless a concrete author_alternative is recorded (then EXPLAINED).

Output a claims table:

| ID | Claim | Source hint |
|----|-------|-------------|
| C1 | ... | ... |

Phase 2 β€” Generate verification questions

One question per claim. Make it specific and answerable from the source alone.

Phase 3 β€” Spawn claim-verifier (fresh context β€” never a conversation fork)

Agent: subagent_type=claim-verifier   # a named subagent starts fresh; a /fork copy would inherit the draft
Prompt: hand over claims table + verification questions + source material pointers.
        Do NOT include the draft text.

The forked agent runs the CoVe independent-answer step. It has never seen the draft and cannot confirm-bias. It returns a structured verification report.

Phase 4 β€” Reconcile

The verifier returns a per-claim verdict in one of these severity tiers:

  • HIGH-WARN β€” fabricated reference (the cited paper doesn't exist at the named venue/year), draft claim directly contradicted by the source, or not_found retrieval that the verifier interprets as a hallucinated citation. Fail closed β€” surface these first and never present the draft as verified while one stands. This is a reporting rule, not a mechanical gate: nothing in /commit or the pre-commit hook reads these verdicts, so the author decides, and a HIGH-WARN left in place is stated in the report the user sees.
  • MED-WARN β€” transient infrastructure / retrieval failure (paywall the verifier can normally bypass via cached metadata; DOI resolver timeout; partial PDF read). Surface for the author; do not gate-refuse.
  • LOW-WARN β€” source genuinely inaccessible (paywalled and not in cache; private dataset; pre-print server transient). Surface with cannot-verify flag; do not gate-refuse.
  • EXPLAINED (v2.0) β€” a numeric/directional contradiction the author has pre-justified with a concrete named alternative (different defensible edition, specification, sample, or rounding convention), passed to the verifier via the claim's author_alternative field. Surfaced with the evidence and the recorded reason; non-gating. The hard floor holds: a fabricated citation is never EXPLAINED, and a blank/vague alternative stays HIGH-WARN. This mirrors audit-reproducibility's EXPLAINED disposition for numeric claims β€” a mismatch is not always a failure when a defensible alternative is named.

Verdict aggregation by tier across all extracted claims (EXPLAINED counts as non-gating, like LOW):

| Tier counts | Outcome | What the report says | |---|---|---| | 0 HIGH, 0 MED, β‰₯ 0 LOW/EXPLAINED | PASS (green block) | draft verified | | 0 HIGH, β‰₯ 1 MED, any LOW/EXPLAINED | PARTIAL (yellow block) | verified with warnings | | β‰₯ 1 HIGH | FAIL (red block) | never reported as verified while a HIGH-WARN stands (unless --no-fail-closed) |

--no-fail-closed reports HIGH-WARN verdicts as ordinary warnings instead of failing closed. Use sparingly β€” it's there for offline / hallucination-sensitive contexts where the user accepts the risk in writing.

If the draft is writeable and the user asked for auto-correction, regenerate the affected sections using the verifier's evidence. Otherwise return the report and let the user decide.

Example

/verify-claims quality_reports/lit-review_measurement-error.md --source master_supporting_docs/author_2021_method.pdf --source master_supporting_docs/coauthor_2020_survey.pdf

Expected output (abridged):

## Post-Flight Verification β€” lit-review_measurement-error.md

**Claims extracted:** 14
**Verified independently:** 14 (fresh-context claim-verifier)
**Outcome:** FAIL β€” 12 verified, 1 contradicted by its source (HIGH-WARN), 1 unverifiable (LOW-WARN); the draft is not reported as verified until C7 is corrected

### Discrepancies

- **C7** β€” draft claims "Coauthor (2020) *proposes* a bias-corrected estimator." Source Section 4 shows they propose a weighting estimator, not a bias-corrected one. Recommend correction.

### Unverifiable

- **C12** β€” draft cites "Third Author et al. 2024 (working paper)". No canonical URL in provided sources. Recommend user supply DOI or arXiv link.

### Verified

| ID | Claim | Evidence |
|----|-------|----------|
| C1 | "Author 2021 defines the calibration constant as a ratio of moments" | p. 5, eq. (3) |
| ... | ... | ... |

Fail modes and recovery

Verifier times out: surface a warning block, return draft as provisional. Do not silently ship.

Source material inaccessible (paywall, 404): report the specific claims that hinge on it, flag as cannot-verify, recommend user supply an alternative source.

Draft contains only opinions / forward-looking text: report "no verifiable factual claims extracted β€” nothing to check" and return.

Cross-references

Related Skills

View on GitHub
GitHub Stars1.6k
CategoryCustomer
Updated2mo ago
Forks3.1k

Languages

HTML

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

No cautions
verify-claims β€” Universal Skill: Install & Safety Check | SkillAgent