good-strategy-bad-strategy

Evaluate or develop strategy using Richard Rumelt's kernel of good strategy — Diagnosis, Guiding Policy, and Coherent Actions. Use when you need to cut through vague strategic plans and get to the hard choices, or when you suspect your "strategy" is actually just a list of goals.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is a well-structured, actionable instruction skill with clear sequenced workflows, self-check validation steps, and a genuine one-level-deep reference. Its only weakness is minor motivational padding in the framing prose that could be trimmed for token efficiency.

Suggestions

Trim the motivational lead-in ('Most strategies aren't strategies. They're goal lists...') and redundant framing sentences to tighten conciseness toward level 3.

Consider moving the large inline Prompt Template block into a referenced file or condensing it, keeping SKILL.md as a leaner overview.

Remove any framework explanation that duplicates content already in references/framework.md to avoid carrying the same material in two places.

Dimension	Reasoning	Score
Conciseness	The bulk is an actionable operational prompt that earns its place, but the lead-in ('Most strategies aren't strategies. They're goal lists...') and framing sentences add motivational padding Claude doesn't need, fitting the level-2 'mostly efficient but could be tightened' anchor rather than the lean level-3.	2 / 3
Actionability	Gives concrete executable guidance for an instruction-only skill: four named bad-strategy hallmarks with required outputs, a Strong/Weak/Missing scoring scheme, and explicit formats ('Write the diagnosis in 2-3 paragraphs', 'List 3-5 coherent actions'), matching the level-3 specific-examples anchor.	3 / 3
Workflow Clarity	Both paths are clearly numbered and sequenced (Detector -> Kernel Assessment -> Verdict -> Rewrite; Steps 1-5), with built-in checkpoints such as the 'Test the guiding policy' questions and the Strong/Weak/Missing assessment acting as validation feedback loops, matching the level-3 anchor.	3 / 3
Progressive Disclosure	The body is an overview that signals a single one-level-deep reference ('consult framework.md') for detailed definitions, and that file exists and is real (verified), matching the level-3 clear-overview-with-one-level-reference anchor rather than a monolithic or nested structure.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

The description is concise, third-person, and fully answers both what the skill does and when to use it, with natural trigger terms and a distinct niche anchored to Rumelt's framework. It meets every level-3 anchor with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Evaluate or develop strategy' — and itemizes the framework's three components ('Diagnosis, Guiding Policy, and Coherent Actions'), matching the level-3 anchor of multiple specific concrete actions rather than a single domain/action at level 2.	3 / 3
Completeness	Explicitly answers both what (evaluate/develop strategy via Rumelt's kernel) and when via an explicit 'Use when...' clause, satisfying the level-3 anchor rather than the level-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Includes natural phrasing users would actually say — 'vague strategic plans', 'list of goals', 'strategy' — plus the suggest_when field adds 'is this a good strategy' and 'strategic plan review', giving good coverage rather than the partial level-2 set.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly bounded by 'Richard Rumelt's kernel' and the three named elements, with triggers unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor rather than the overlapping level-2 case.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 2 days 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.