AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Verify

skill-yha9806-academic-writing-toolkit-verify · by yha9806

Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.

No reviews yet
0 installs
34 views
0.0% view→install

Install

$ agentstack add skill-yha9806-academic-writing-toolkit-verify

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yha9806-academic-writing-toolkit-verify)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Verify? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/verify — Fact Verification Skill

Purpose

Fact-check claims encountered during reading sessions. This covers dates, names, historical events, publication details, and attribution of ideas. Use when the user questions a claim or when a factual assertion seems uncertain.

Trigger Words

This skill activates on: verify, check this, fact-check, is this correct, /verify.

Workflow

  1. Extract the claim from the user's input or from conversation context. Identify the specific factual assertion to verify (date, name, event, publication, attribution).
  2. Search authoritative sources using WebSearch. Prioritise:
  • Wikipedia (for dates, biographical facts, historical events)
  • Academic databases (Google Scholar, JSTOR, PhilPapers)
  • Publisher websites (for publication dates, editions, ISBNs)
  • Encyclopedias (Stanford Encyclopedia of Philosophy, Britannica)
  1. Compare the original claim against verified information.
  2. Output the verdict using the format below.
  3. Optionally annotate the notes file. If the user confirms, use Edit to add a (verified) or (corrected: {correct info}) tag next to the relevant entry in the notes file.

Output Format

## Verification

**Claim**: {the original claim as stated in the source}
**Verdict**: Confirmed | Needs correction | Incorrect | Unverifiable

| Item | Original | Verified |
|------|----------|----------|
| {specific fact} | {as claimed} | {as verified} |

**Source**: {single-line citation in the project's declared style — see `literature/reading_notes/_template_NOTES.md` for per-style examples; the active style is `Citation style:` in `CLAUDE.md`. Append the URL after the citation if the source is web-only}
**Confidence**: High | Medium | Low
**Notes**: {any additional context, e.g., "Date varies by edition" or "Multiple conflicting sources"}

Multiple Claims

When verifying several claims at once, produce one verification block per claim, numbered sequentially:

### 1. {Brief claim description}
{verification block}

### 2. {Brief claim description}
{verification block}

Annotation

When the user says "annotate" or "mark in notes" after verification:

  • Use Edit to find the relevant passage in the notes file.
  • Append the tag inline: (verified 2026-03-30) or (corrected: {correct value}, verified 2026-03-30).
  • Do not alter the original text of the note -- add the tag after it.

Constraints

  1. Never auto-correct notes without user confirmation. Present the verdict first, then ask if the user wants to annotate.
  2. Cite sources with URLs whenever possible. Do not present unverifiable assertions as fact.
  3. Acknowledge uncertainty. If sources conflict, report all versions and mark confidence as Low.
  4. No emoji in output.
  5. Scope: This skill verifies factual claims only. For argument analysis or interpretation, defer to the user's own reading.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.