fact-check
Skill0 starsChanged 57 days agoMITView on GitHub
Checking course and research claims against their cited sources for accuracy, currentness, jurisdiction and correct claim category (law vs guidance vs evidence vs synthesis). Use when verifying facts or citations in a CourseForge artifact.
38 other projects use a version of this.
Adopted by
Most recently taken up by
- surfmind-space/awesome-surfmindtheir own version, first seen Nov 8, 2026
- AmethystLuna/embedded-workbenchtheir own version, first seen Nov 5, 2026
- aktsmm/Agent-Skillstheir own version, first seen Nov 1, 2026
- kfangw/research-opstheir own version, first seen Oct 25, 2026
- mingxinbi112-source/OBI-xiao-skilltheir own version, first seen Oct 20, 2026
- soilSpoon/skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use deep-research, seo and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkilldeep-research
Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.
Also in 4 projects that use this
nilssonrSkillseo
Full SEO workflow for auditing pages and creating SEO-optimized content. Provides checklists with educational explanations aligned with Google Search Central documentation.
Also in 3 projects that use this
- NVIDIASkill
research
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
Other versions38 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 38
- leonardomso/33-js-concepts★ 67ksame name
- THU-MAIC/OpenMAIC★ 43ksame name
- garrytan/gbrain★ 32ksame name
- elvisun/newsjack★ 1.7ksame name
- srid/emanote★ 963same name
- akitaonrails/my-skills★ 283same name
- Jamie-BitFlight/claude_skills★ 67same name
- jezweb/vite-flare-starter★ 49same name
- namedtoaster/The-Last-Mile★ 39same name
- AmethystLuna/embedded-workbench★ 32same name
28 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibility-reviewSkill
- alignment-reviewSkill
- assessment-designSkill
- assessment-reviewSkill
- course-gap-analysisSkill
- editorial-humanizationSkill
- html-intake-reviewSkill
- instructional-designSkill
- instructional-graphicsSkill
- research-authoringSkill
- research-planningSkill
- research-reviewSkill
- scenario-designSkill
- storyboard-authoringSkill
- ui-reviewSkill
- ux-reviewSkill
- visual-directionSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 31 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Read the statement as a learner would read it.
“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Fact check
Classify before you check
Different statements need different checks:
| Category | Check |
law-regulation | the provision exists at the locator, is current, applies in the stated jurisdiction, binds the stated party, and says "must" where the text says "must" |
guidance-recommendation | the issuer is who is claimed; the text is presented as advice; any claim that it is mandatory is backed by an incorporating law |
scientific-technical | the source supports the statement at the stated strength; no overgeneralisation beyond the population or conditions studied |
statistic | number, unit, year of data, population and denominator all match; percentage vs percentage points; latest release |
version-currentness | the edition or amendment status is true today |
definition | the definition matches the source's wording in meaning, and the source is the right authority for it |
scenario-synthesis | the inference follows from the cited sources and is presented as synthesis, not as a stated fact |
Procedure
- Read the statement as a learner would read it; note modality, scope, numbers, jurisdiction and time words.
- Find its claim(s) and source(s). If there are none, it is an evidence gap.
- Open the source at the locator. Compare wording point by point.
- For time-sensitive sources, check the issuer's site for the current version or later amendments.
- Record exactly what the source says (short quote, locator, URL, date checked).
Frequent errors
- Modality inflation ("should" to "must") or deflation (a statutory duty described as good practice).
- Jurisdiction drift: a provincial rule presented as national; one country's rule as universal.
- Lost qualifiers: "where reasonably practicable", "for listed substances", "in most cases".
- Outdated versions: superseded editions, repealed sections, old statistics described as current.
- Misattributed authority: a consultancy page cited for a regulatory requirement.
- Numbers: unit errors, wrong year, rate vs count, rounding that changes meaning.
- Laundered claims: a secondary source's paraphrase broader than its primary source.
- Synthesis presented as fact.
- Mismatched citations: the cited source is about the topic but does not contain the specific point.
When you cannot verify
Say so, with what you tried. Do not guess, and never supply a replacement citation you have not opened. Recommend "research needed" or "teach with a caveat" rather than inventing support.
Reporting
Location: the claim, block or screen ID. Evidence: the statement as written, the source text with locator and URL, and the date checked. Severity: fabricated support is a blocker; wrong legal duties, wrong numbers, guidance taught as law, or wrong graded keys are critical; lost qualifiers and weak support on substantive points are major; missing locators or metadata are minor.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.