agentleFS
Sign inStart free
fzfcleefzfclee/consulting-skills/skills/5w1h-analysis/SKILL.md

5w1h-analysis

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when a situation, request, problem, event, stakeholder issue, process, or plan needs basic fact clarification through who, what, when, where, why, and how. Use when applying 5W1H, 4W1H, fact clarification, situation framing, or first-pass problem understanding.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to clarify the basic facts of a situation before deeper analysis.

    line 9
  2. Very specific:

    If an input is missing, mark it as unknown and add a targeted question.

    line 28
  3. Very specific:

    Do not use as evidence grading, root-cause proof, or strategic diagnosis.

    line 32
  4. Very specific:

    Do not over-analyze before basic who/what/when/where/why/how are clear.

    line 75
  5. Distinctive:

    Keep questions specific and answerable.

    line 76
  6. Distinctive:

    Use 5W1H to prepare for deeper methods, not to replace them.

    line 77

≈ “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

5W1H Analysis

Use this skill to clarify the basic facts of a situation before deeper analysis.

Method Notes

  • 5W1H means Who, What, When, Where, Why, and How.
  • It is a simple clarification method, not a full diagnosis.
  • It is useful when the input is messy, missing basic context, or mixing facts and interpretations.
  • The method should produce clear missing-information questions and a sharper problem statement.

Required Inputs

Collect or infer these inputs before execution:

  • raw situation description
  • known stakeholders or actors
  • event, problem, decision, or plan
  • timing and location or context
  • current explanation or desired outcome

If an input is missing, mark it as unknown and add a targeted question.

When Not To Use

Do not use as evidence grading, root-cause proof, or strategic diagnosis. Use evidence-map when source quality and confidence matter; use five-whys-root-cause only after the observed problem is clear. Stop after the basic situation frame is complete.

Step-by-Step Execution

StepRequired inputHow to executeOutput
Clarify whoStakeholders, actors, owners, affected parties.Identify who is involved, who decides, who acts, and who is affected.Who map.
Clarify whatEvent, decision, problem, action, object.State what happened, what is being decided, or what must be done.What statement.
Clarify whenTiming, sequence, deadline, frequency.Record when it happened, when it changed, and when action is needed.Timing view.
Clarify whereLocation, channel, process step, market, context.State where the issue appears or where action must happen.Context boundary.
Clarify whyStated purpose, reason, motive, cause, expected value.Separate stated reason from inferred reason.Why view.
Clarify howProcess, mechanism, approach, resources.Describe how it happens now and how action could happen.How view.
Summarize gapsUnknown fields.Convert missing or weak fields into precise questions.Clarification questions.

Output Template

### 1. 5W1H Fact Frame
| Dimension | Current answer | Evidence strength | Missing / unclear |
|---|---|---|---|
| Who |  | strong / medium / weak / unknown |  |
| What |  | strong / medium / weak / unknown |  |
| When |  | strong / medium / weak / unknown |  |
| Where |  | strong / medium / weak / unknown |  |
| Why |  | strong / medium / weak / unknown |  |
| How |  | strong / medium / weak / unknown |  |

### 2. Sharpened Situation Statement
- In one sentence:

### 3. Clarification Questions
1.
2.
3.

### 4. Recommended Next Method
- If facts remain unclear:
- If facts are clear enough:

Quality Gate

  • Separate stated facts from inferred motives or causes.
  • Do not over-analyze before basic who/what/when/where/why/how are clear.
  • Keep questions specific and answerable.
  • Use 5W1H to prepare for deeper methods, not to replace them.
  • Mark unknowns plainly rather than guessing.

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