agentleFS
itseffiitseffi/agentic-os/.agents/skills/crux-diagnosis/SKILL.md

crux-diagnosis

Skill114 starsChanged 10 months agoMITView on GitHub

Identify the pivotal obstacle between current state and desired future. Use when developing strategy.

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:

    When developing strategy or facing complex strategic decisions.

    line 12
  2. Distinctive:

    Create a causal graph:

    line 31
  3. Distinctive:

    Leverage potential: If solved, how much unlocks?

    line 42
  4. Distinctive:

    Create 4-7 options aimed at the crux:

    line 55
  5. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 71

≈ “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

Strategic Crux Diagnosis

Identify the pivotal obstacle between current state and desired future.

When to Use

When developing strategy or facing complex strategic decisions.

The Concept

Crux: The smallest set of obstacles that, if solved, makes everything else tractable or unnecessary.

Required Inputs

Gather before analysis:

  • Current state (baseline metrics, capabilities)
  • Desired future (time-bound outcome, targets)
  • Constraints (budget, headcount, tech, compliance)
  • Available assets (data, channels, IP, partnerships)
  • Key risks and non-negotiables

The Process

1. Map Current to Future

Create a causal graph:

  • Start: Current state
  • End: Desired future
  • List all blockers in between

2. Score Each Blocker

Evaluate on:

  • Causal centrality: How much else depends on this?
  • Bottleneck severity: How much does it slow everything?
  • Solvability: Can we actually fix it?
  • Leverage potential: If solved, how much unlocks?
  • Time to impact: How fast could we see results?
  • Evidence strength: How sure are we this is the problem?

3. Identify the Crux

Find the blocker(s) where:

  • Solving it unlocks the most downstream progress
  • It's actually solvable given constraints
  • Time to impact is acceptable

4. Generate Strategic Options

Create 4-7 options aimed at the crux:

  • Include at least one non-obvious approach
  • Include at least one constraint-relaxation option
  • Evaluate against decision criteria

Output

  • Executive summary (situation, crux, approach)
  • Evidence pack (facts, assumptions, uncertainties)
  • Crux definition with scoring
  • Options comparison table
  • Chosen strategy with rationale
  • Strategic moves (3-5) with owners and timelines

When Not to Use

Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

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.