agentleFS
Sign inStart free
fzfcleefzfclee/consulting-skills/skills/abductive-reasoning/SKILL.md

abductive-reasoning

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when the best explanation must be inferred from incomplete, ambiguous, or competing evidence. Use when applying abductive reasoning, inference to the best explanation, mystery diagnosis, competing explanation review, or plausible hypothesis selection.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to choose the most plausible explanation when evidence is incomplete.

    line 9
  2. Very specific:

    If an input is missing, mark it as missing, state the assumption used, and add a validation action.

    line 28
  3. Very specific:

    Do not use when a formal rule already determines the conclusion.

    line 32
  4. Distinctive:

    Do not present the best explanation as proven.

    line 72
  5. Distinctive:

    Look for evidence that discriminates between explanations, not only more confirming evidence.

    line 74
  6. Distinctive:

    Avoid overly complex explanations when a simpler one fits the evidence.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Abductive Reasoning

Use this skill to choose the most plausible explanation when evidence is incomplete.

Method Notes

  • Abductive reasoning asks: what explanation would best account for the facts we see?
  • The output is a ranked explanation, not proof.
  • It is useful when stakeholder behavior, market signals, failures, or events can be explained in several ways.
  • A good abductive diagnosis names what each explanation explains, what it fails to explain, and what evidence would change the ranking.

Required Inputs

Collect or infer these inputs before execution:

  • surprising fact, event, behavior, or outcome
  • known evidence
  • candidate explanations
  • missing evidence
  • decision consequence if the explanation is wrong

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when a formal rule already determines the conclusion. Use deductive-reasoning instead. Do not use when the task is broad pattern discovery; use inductive-reasoning first.

Step-by-Step Execution

StepRequired inputHow to executeOutput
State the puzzleSurprising fact or outcome.Define what needs explaining.Explanation question.
List evidenceFacts, signals, timing, observations.Separate strong facts from interpretations and missing evidence.Evidence list.
Generate explanationsCandidate causes, motives, mechanisms.Create plausible explanations without settling too early.Explanation candidates.
Score explanatory fitEvidence and candidates.Rate how well each explanation accounts for the facts, timing, and contradictions.Fit table.
Check parsimony and riskCandidates, assumptions, downside.Prefer explanations that require fewer unsupported assumptions, while noting high-risk alternatives.Plausibility ranking.
Identify discriminating evidenceTop explanations.Define evidence that would clearly separate one explanation from another.Validation tests.
State working explanationRanking and confidence.Choose the best current explanation and action implication.Working diagnosis.

Output Template

### 1. Explanation Question
- What needs explaining:
- Why it matters:

### 2. Evidence Base
| Evidence item | Strength | Notes |
|---|---|---|
|  | strong / medium / weak / missing |  |

### 3. Competing Explanations
| Explanation | What it explains well | What it does not explain | Assumptions needed | Plausibility |
|---|---|---|---|---|
|  |  |  |  | high / medium / low |

### 4. Working Diagnosis
- Best current explanation:
- Main alternative:
- Evidence that would change the ranking:
- Next check:

Quality Gate

  • Do not present the best explanation as proven.
  • Include at least one serious alternative explanation.
  • Look for evidence that discriminates between explanations, not only more confirming evidence.
  • Avoid overly complex explanations when a simpler one fits the evidence.
  • Name the risk if the working explanation is wrong.

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.

Check your setup, free