decision-frameworks

Structures difficult decisions using Annie Duke's probabilistic thinking and Ben Horowitz's hard decisions frameworks. Use when facing tough choices, applying expected value thinking, or reducing decision paralysis with regret minimization and pre-mortems.

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid decision-making skill with excellent actionability through concrete templates and worked examples. The main weaknesses are minor verbosity (quotes section adds little value for Claude) and missing guidance on handling conflicting framework outputs or iterating on probability estimates.

Suggestions

Remove the 'Key Quotes' section - Claude doesn't need motivational quotes to apply frameworks

Add guidance for when frameworks conflict (e.g., high EV but high regret, or reversible but negative EV)

Include a validation step: 'Sanity check your probability estimates - are they based on data or intuition?'

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary elements like the quotes section and could tighten the regret minimization explanation. The expected value formula and example are well-presented without over-explanation.	2 / 3
Actionability	Provides concrete, copy-paste ready templates with specific examples including actual numbers. The decision matrix template is immediately usable with clear placeholders and the EV calculation example shows exactly how to apply the framework.	3 / 3
Workflow Clarity	The decision checklist provides a sequence but lacks explicit validation checkpoints or feedback loops. There's no guidance on what to do if the analysis reveals conflicting signals between frameworks, or how to iterate if initial estimates prove wrong.	2 / 3
Progressive Disclosure	For a skill of this size (~80 lines), the content is well-organized with clear sections: frameworks, templates, quick reference. No external references needed and the structure allows easy navigation from concepts to actionable templates.	3 / 3
	Total	10 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a well-crafted description with strong trigger terms and explicit 'Use when' guidance that clearly distinguishes it from other skills. The main weakness is the lack of specific concrete actions - it tells us the frameworks used but not the specific outputs or steps Claude will perform (e.g., probability estimates, decision matrices, pre-mortem reports).

Suggestions

Add 2-3 specific concrete actions to improve specificity, e.g., 'Calculates expected value, runs pre-mortem analysis, builds decision matrices' before the 'Use when' clause

Dimension	Reasoning	Score
Specificity	Names the domain (difficult decisions) and references specific frameworks (Annie Duke's probabilistic thinking, Ben Horowitz's hard decisions), but doesn't list concrete actions beyond 'structures' - missing specifics like 'calculates expected value', 'runs pre-mortem analysis', etc.	2 / 3
Completeness	Clearly answers both what (structures difficult decisions using specific frameworks) and when (explicit 'Use when...' clause covering tough choices, expected value thinking, decision paralysis, regret minimization, and pre-mortems).	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'tough choices', 'expected value thinking', 'decision paralysis', 'regret minimization', 'pre-mortems'. These are terms users would naturally use when seeking decision-making help.	3 / 3
Distinctiveness Conflict Risk	Clear niche with distinct triggers - the specific framework names (Annie Duke, Ben Horowitz) and specialized terms (probabilistic thinking, regret minimization, pre-mortems) make this unlikely to conflict with generic decision or productivity skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: menkesu/awesome-pm-skills
Commit: 53530ef

Reviewed: 3 months ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.