agentleFS
fzfcleefzfclee/consulting-skills/skills/critical-uncertainties/SKILL.md

critical-uncertainties

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when a decision depends on a few uncertain variables whose direction could materially change the plan. Use when applying critical uncertainties, uncertainty mapping, scenario driver selection, strategic uncertainty review, or signpost planning.

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 identify which unknowns matter most and how to monitor them.

    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 for ordinary risks with known mitigation paths.

    line 31
  4. Distinctive:

    Do not confuse uncertainty with general risk.

    line 71
  5. Distinctive:

    Keep output concrete enough to guide monitoring and next action.

    line 76

≈ “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

Critical Uncertainties

Use this skill to identify which unknowns matter most and how to monitor them.

Method Notes

  • A critical uncertainty is both highly uncertain and highly consequential.
  • The method prevents false confidence when one forecast is not enough.
  • It can feed scenario planning, validation plans, stakeholder strategy, and risk control.

Required Inputs

Collect or infer these inputs before execution:

  • decision question or strategic choice
  • possible uncertainties
  • decision time horizon
  • consequences of different outcomes
  • early indicators or data sources when available

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 for ordinary risks with known mitigation paths. Use risk-matrix or pre-mortem instead.

Step-by-Step Execution

StepRequired inputHow to executeOutput
Define the decision horizonDecision question, time horizon, action deadline.State how far ahead the uncertainty matters.Decision horizon.
List uncertaintiesUnknowns, external variables, stakeholder unknowns, market shifts.Write each uncertainty as a variable that can move in more than one direction.Uncertainty list.
Rate uncertainty and impactEvidence, volatility, consequence, controllability.Rate uncertainty and impact as high / medium / low; retain a source or labeled assumption and brief rating rationale for each material judgment.Uncertainty-impact table.
Select critical uncertaintiesRating table.Choose the 1-3 uncertainties with high impact and high uncertainty.Critical uncertainty set.
Define poles or outcomesCritical uncertainties.For each, define plausible opposite states or outcome ranges.Uncertainty poles.
Create signpostsEvidence sources, leading indicators, stakeholder signals.Define early signs that show which way the uncertainty is moving; retain signpost sources or evidence gaps. Explain material conflicts and why outdated information is superseded, or why the conflict remains unresolved.Signpost list.
Link to actionsCurrent plan, options, thresholds.Decide what to do under each signal.Contingent action logic.

Output Template

### 1. Decision Frame
- Decision question:
- Time horizon:
- Why uncertainty matters:

### 2. Uncertainty Map
| Uncertainty | Impact | Uncertainty | Controllability | Why it matters | Critical? |
|---|---|---|---|---|---|
|  | high / medium / low | high / medium / low | high / medium / low |  | yes / no |

### 3. Critical Uncertainties
| Critical uncertainty | Possible direction A | Possible direction B | Signposts to watch | Action if A | Action if B |
|---|---|---|---|---|---|
|  |  |  |  |  |  |

### 4. Decision Implication
- Robust action regardless of uncertainty:
- Action to delay until signal improves:
- Decision gate:

Quality Gate

  • Do not confuse uncertainty with general risk.
  • A useful uncertainty must have more than one plausible outcome.
  • Focus on variables that would change the plan.
  • Include signposts, not just abstract possibilities.
  • Preserve material rating rationale and provenance, signpost sources/gaps, and the basis for resolving or retaining substantive contradictions; newer information does not automatically supersede evidence from a different scope.
  • Keep output concrete enough to guide monitoring and next action.

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.