agentleFS
patricksavallepatricksavalle/investigate-journalism-skills/.claude/skills/intuitive-thinking/SKILL.md

intuitive-thinking

Skill8 starsChanged 3 months agoApache-2.0View on GitHub

Micro-skill for recording gut feelings, hunches, anomaly signals, and "something feels off" reactions as pre-evidence hypotheses before article review, investigations, OSINT, claim audits, rhetoric audits, peer review, scientific fact classification, or belief revision. Use only as a Phase 0 hunch register; intuition may guide tests and searches but never supports a verdict.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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
  1. Distinctive:

    Use this as a Phase 0 hunch register before a real analytical skill.

    line 10
  2. Distinctive:

    Use when a task starts from a gut feeling, hunch, suspicion, unease, pattern match, or "something feels off".

    line 16
  3. Distinctive:

    If the hunch later proves useful, cite the traced evidence that tested it, not the hunch itself.

    line 33
  4. Distinctive:

    Use this before search, then hand off.

    line 37
  5. Distinctive:

    Before routing onward, ask:

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Intuitive Thinking

Use this as a Phase 0 hunch register before a real analytical skill.

Core rule: intuition generates hypotheses; evidence carries verdicts.

When To Use

Use when a task starts from a gut feeling, hunch, suspicion, unease, pattern match, or "something feels off".

Common article-review triggers:

HunchDownstream test
Headline feels too strongHeadline-body alignment
Source mix feels capturedSource independence / right of reply
Number feels inflatedRaw count, denominator, baseline, timeframe, absolute effect
Framing feels manipulativeRhetoric, omissions, quote context
Story feels too neatAlternative hypotheses, missing primaries
Timing feels convenientChronology, beneficiaries, prior drafts

Warrant Label

(intuition — unwarranted) = a gut feeling, anomaly signal, or pattern impression. It may generate hypotheses and search leads. It is never evidence, never load-bearing, and cannot revise, refute, or establish a claim.

If the hunch later proves useful, cite the traced evidence that tested it, not the hunch itself.

Micro-Template

Use this before search, then hand off.

## Intuition Register
- **Trigger:** [what was noticed]
- **Immediate story:** [first explanation] `(intuition — unwarranted)`
- **Competing explanations:** H1 [hunch right]; H2 [ordinary explanation]; H3 [opposite-direction explanation]; H4 [missing information]
- **Disconfirmation:** [what would weaken or kill the hunch]
- **Search leads:** [primary/data/source to fetch]; [disconfirming source/query]; [strongest alternative source/query]

Routing

  • Article quality, headline, sourcing, omissions -> journalistic-article-review
  • Single empirical or causal claim -> scientific-fact-classification
  • Contested event or official narrative -> investigative-reasoning
  • Source identity, funding, account, image, domain -> osint-research
  • Rhetoric or manipulation -> fallacy-bias-and-manipulation-analysis
  • Hidden assumption or definition -> first-principles-thinking
  • New hunch about a prior verdict -> belief-revision

Self-Check

Before routing onward, ask:

  • Would this hunch still be worth testing if it pointed the other way?
  • Is the feeling being used as evidence, or only as a search prompt?
  • Did the first story crowd out ordinary, opposite, or missing-information explanations?

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.