agentleFS
moonpiesheldon1337moonpiesheldon1337/grounded-research/SKILL.md

grounded-research

Skill0 starsChanged 6 months agoApache-2.0View on GitHub

Enforces source-grounded, citation-first research discipline. Use this skill whenever the user asks to research a topic, fact-check a claim, summarize recent findings, look up current information, explain what the evidence says about something, or produce any factual output where accuracy and verifiability matter. Trigger even on conversational phrasing like "what's the deal with X", "is it true that Y", "what do experts say about Z", or "can you check if..." — if the answer requires facts that could be wrong or outdated, this skill applies. When in doubt, use it.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. PrisacariuRobert/sidemates★ 9same name
    2. berkeley-humanoids/skills★ 4same name
    3. berkeley-humanoids/Skills★ 4same name
    4. masbrokemanaaja/reethink★ 3same name
    5. Kaagemusha/agent-skills★ 0same name

    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.

The file

Show its rules and text

We split this skill into the rules it gives an agent

25 rules. 0 are common, 24 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 24

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before producing any output, mentally classify every claim the response will make:

    line 23
  2. Distinctive:

    Never mix types silently. If a paragraph contains a Type C claim presented with Type A confidence, that's a hallucination risk.

    line 32
  3. Distinctive:

    Only after verification is complete for all B and C claims, proceed to Phase 3.

    line 47
  4. Distinctive:

    Do not state a statistic without a source, even if you are "pretty sure"

    line 50
  5. Distinctive:

    Do not state someone's current job title, role, or status without searching

    line 51
  6. Distinctive:

    Do not describe a product's current features or pricing without searching

    line 52
  7. Distinctive:

    Do not summarize a study's findings without finding the actual study or a primary report

    line 53
  8. Distinctive:

    Every Type B and C claim gets an inline source reference immediately after it.

    line 65
  9. Distinctive:

    Never reproduce long quotes — paraphrase and attribute.

    line 67
  10. Distinctive:

    Use these inline markers when precision matters:

    line 76
  11. Distinctive:

    If a claim cannot be verified and is important to the answer, say so explicitly:

    line 88
  12. Distinctive:

    After drafting the response, do a final pass:

    line 98
  13. Distinctive:

    Check that no Type D (analytical) claim is presented as if it were Type A (established fact)

    line 102
  14. Distinctive:

    Verify the response does not contradict itself across sections

    line 103
  15. Very specific:

    Read references/source-quality-tiers.md for the full tier guide.

    line 112
  16. Distinctive:

    When sources conflict, report the conflict.

    line 120
  17. Distinctive:

    Add: "This situation may have developed since [date/time of source]"

    line 128
  18. Distinctive:

    Do not speculate about what "probably" happened after your last source

    line 129
  19. Distinctive:

    Prefer CVE databases, vendor advisories, NIST, and official security bulletins

    line 132
  20. Distinctive:

    Do not paraphrase vulnerability details in ways that could introduce inaccuracy

    line 133
  21. Distinctive:

    If the claim involves a specific version, configuration, or exploit, find the primary advisory

    line 134
  22. Distinctive:

    Always source to peer-reviewed literature, official guidelines, or regulatory bodies

    line 137
  23. Distinctive:

    Always add: "This is not medical/legal advice.

    line 138
  24. Distinctive:

    Never state a treatment or legal position as settled if the primary literature shows debate

    line 139
  25. Distinctive:

    Always prioritise precision over comprehensiveness.

    line 166

“Common” is measured: kept by at least 6 in 10 of the 5 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Grounded Research Skill

This skill enforces a structured, citation-first discipline to produce outputs where every factual claim is either verified, explicitly uncertain, or openly declared unknown. The goal: no confident-sounding hallucinations. Ever.


Phase 1 — Claim Taxonomy (do this before writing anything)

Before producing any output, mentally classify every claim the response will make:

TypeDescriptionHandling
A — StableWell-established, timeless facts (laws of physics, historical events pre-2020, definitions)State directly, no search needed
B — Time-sensitiveCurrent status, prices, positions, policies, recent events, statistics that changeMust search before stating
C — Domain-specificTechnical claims, research findings, medical/legal/security facts, statisticsMust find a source before stating
D — AnalyticalOpinions, comparisons, interpretations, synthesisLabel clearly as analysis/opinion

Never mix types silently. If a paragraph contains a Type C claim presented with Type A confidence, that's a hallucination risk. Classify first, then write.


Phase 2 — Pre-Response Verification Loop

For every Type B and Type C claim identified in Phase 1:

  1. Search before writing — run a web search targeting that specific claim
  2. Extract the key fact — find the specific sentence or data point that supports it
  3. Note the source tier — see references/source-quality-tiers.md
  4. Flag if unverifiable — if no reliable source is found after 2 searches, the claim must be either dropped or explicitly marked as unverified

Only after verification is complete for all B and C claims, proceed to Phase 3.

Verification shortcuts to never take:

  • Do not state a statistic without a source, even if you are "pretty sure"
  • Do not state someone's current job title, role, or status without searching
  • Do not describe a product's current features or pricing without searching
  • Do not summarize a study's findings without finding the actual study or a primary report

Phase 3 — Structured Output

Structure all research responses as follows:

3a. Lead with the answer

Give the direct answer first. Do not bury it in preamble.

3b. Inline citations

Every Type B and C claim gets an inline source reference immediately after it. Format: state the claim in your own words, then note the source naturally in prose. Never reproduce long quotes — paraphrase and attribute.

Example (correct):

The ECB held rates steady in April 2026, according to its official press release.

Example (wrong):

The ECB held rates steady in April 2026. [This is stated confidently with no source]

3c. Confidence signals

Use these inline markers when precision matters:

  • [High confidence — primary source] — sourced from official/primary publication
  • [Medium confidence — secondary source] — sourced from reputable but secondary coverage
  • [Low confidence — unverified] — couldn't find a strong source; treat as uncertain
  • [Analytical — my interpretation] — this is synthesis/opinion, not a sourced fact

You do not need to add these markers to every sentence — use them where the confidence level is non-obvious or where a reader might otherwise mistake analysis for established fact.

3d. "I don't know" declarations

If a claim cannot be verified and is important to the answer, say so explicitly:

I could not find a reliable source for [X]. This should be verified before acting on it.

This is always better than a confident-sounding guess.


Phase 4 — Confidence Audit

After drafting the response, do a final pass:

  1. Scan for any factual claim that lacks a source or uncertainty marker
  2. For each: either add attribution, add an uncertainty signal, or remove the claim
  3. Check that no Type D (analytical) claim is presented as if it were Type A (established fact)
  4. Verify the response does not contradict itself across sections

This audit step is not optional. It's the difference between a grounded response and a plausible-sounding one.


Phase 5 — Source Quality

Read references/source-quality-tiers.md for the full tier guide.

Quick reference:

  • Tier 1 (strongest): Official publications, primary studies, government data, company IR
  • Tier 2: Major wire services, peer-reviewed journals, established specialist press
  • Tier 3: Quality general news, well-sourced blog posts from known experts
  • Tier 4: Aggregators, wikis, forums — only as pointers to Tier 1–3, never as the final source

When sources conflict, report the conflict. Do not silently pick one.


Special Cases

Rapidly changing topics (breaking news, live events)

  • State the timestamp of your most recent source explicitly
  • Add: "This situation may have developed since [date/time of source]"
  • Do not speculate about what "probably" happened after your last source

Technical / security claims

  • Prefer CVE databases, vendor advisories, NIST, and official security bulletins
  • Do not paraphrase vulnerability details in ways that could introduce inaccuracy
  • If the claim involves a specific version, configuration, or exploit, find the primary advisory

Medical / legal claims

  • Always source to peer-reviewed literature, official guidelines, or regulatory bodies
  • Always add: "This is not medical/legal advice. Consult a qualified professional."
  • Never state a treatment or legal position as settled if the primary literature shows debate

Historical research (pre-cutoff, no search needed)

  • Type A claims can be stated without search
  • But if the user is researching something where recent scholarship might have updated the consensus (e.g. archaeology, historical attribution, economic history), flag it

Anti-Patterns to Avoid

Anti-patternWhy it's a problem
"Studies show..." with no citationFabricated authority
"It is widely believed that..."Vague appeal that hides a missing source
"As of my last update..." followed by a specific factFraming stale knowledge as verified
Summarising a document you haven't readHigh hallucination risk on specific details
Quoting statistics without a sourceNumbers are the most frequently hallucinated element
Confidently resolving a contested claimMisrepresents genuine expert disagreement

Output Length Guidance

  • For quick fact checks: 2–4 sentences + source. Do not pad.
  • For research summaries: structured prose, one section per sub-topic, sources inline.
  • For contested topics: present multiple positions with their respective sources. Do not collapse to one view unless the evidence is overwhelming and sourced.
  • Always prioritise precision over comprehensiveness. A shorter, accurate answer beats a longer, partly-hallucinated one.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.