agentleFS
Sign inStart free
fzfcleefzfclee/consulting-skills/skills/evidence-map/SKILL.md

evidence-map

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when facts, claims, assumptions, missing evidence, and confidence levels need to be separated before diagnosis. Use when applying an evidence map, evidence ledger, fact-versus-assumption review, proof inventory, or evidence-strength assessment.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 turn mixed user input into a clear evidence base before making a recommendation.

    line 9
  2. Very specific:

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

    line 27
  3. Very specific:

    Do not use when the facts are already clean and the main need is choosing among options.

    line 31
  4. Distinctive:

    Do not treat seniority, confidence, repetition, or relationship closeness as proof by itself.

    line 76
  5. Distinctive:

    Keep wording professional and plain enough that a smart non-specialist can use it.

    line 79

≈ “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

Evidence Map

Use this skill to turn mixed user input into a clear evidence base before making a recommendation.

Method Notes

  • Evidence mapping separates what is known, inferred, assumed, missing, and contradicted.
  • It is most useful early in a diagnostic, before strong hypotheses or action plans are formed.
  • The goal is not to demand perfect proof; it is to prevent weak evidence from carrying strong conclusions.

Required Inputs

Collect or infer these inputs before execution:

  • decision or diagnostic question
  • raw statements, observations, documents, or claims
  • source of each statement when available
  • current conclusion or proposed action
  • decision deadline or consequence if relevant

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 the facts are already clean and the main need is choosing among options. Use decision-matrix, weighted-scorecard, or effort-impact-matrix instead.

Step-by-Step Execution

StepRequired inputHow to executeOutput
Define the decision questionDecision, objective, current recommendation.State the question the evidence must support or disprove.Evidence question.
Extract evidence itemsRaw notes, claims, observations, artifacts.Split compound statements into atomic items. Keep one fact or claim per row.Evidence inventory.
Classify item typeEach evidence item, source, timing.Label each item as fact, direct observation, document, inference, assumption, hearsay, estimate, contradiction, or missing evidence.Evidence type map.
Rate strength and relevanceSource quality, recency, directness, decision linkage.Rate strength as strong / medium / weak / missing and relevance as high / medium / low. Explain why.Evidence rating table.
Identify evidence gapsDesired confidence, decision risk, weak or missing rows.Name the 3-5 gaps most likely to change the conclusion.Evidence gap list.
Convert gaps into testsEvidence gaps, available access, timeline.Define the fastest practical way to confirm, disconfirm, or reduce uncertainty.Validation actions.

Output Template

### 1. Evidence Question
- Decision / diagnosis to support:
- Current conclusion being tested:
- Decision consequence:

### 2. Evidence Map
| Evidence item | Type | Source | Strength | Relevance | Supports / weakens which claim | Notes |
|---|---|---|---|---|---|---|
|  | fact / observation / document / inference / assumption / hearsay / missing |  | strong / medium / weak / missing | high / medium / low |  |  |

### 3. Evidence Gaps
| Gap | Why it matters | Fastest way to check | Owner / actor | Deadline |
|---|---|---|---|---|
|  |  |  |  |  |

### 4. Confidence Readout
- Strongly supported:
- Plausible but not proven:
- Risky assumption:
- Do not conclude yet:

### 5. Next Diagnostic Move
- Next question or test:
- What result would change the recommendation:

Quality Gate

  • Split mixed statements instead of giving one vague evidence grade.
  • Do not treat seniority, confidence, repetition, or relationship closeness as proof by itself.
  • Separate fact evidence strength from inference confidence.
  • Highlight contradictions rather than smoothing them over.
  • Keep wording professional and plain enough that a smart non-specialist can use it.

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