think-harder

4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/think-harder/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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 lean, well-sequenced thinking framework with a clear output contract and no unnecessary padding. Its main weakness is actionability: directives are concrete but somewhat high-level and lack a worked example illustrating the full analysis in practice.

Suggestions

Add a short worked example showing one task run through all 4 phases with the matching 6-item output, to lift actionability from abstract directives to copy-paste-ready guidance.

Tighten abstract bullets like 'Reconcile contradictions' into concrete checks (e.g. 'List contradictions found and state which evidence prevails and why').

Clarify the cryptic 'Vibe Integration' line ('M/L pre-routing analysis entry') into plain guidance on when this skill pairs with code-reviewer, so the integration is as actionable as the phases.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and assumes Claude's competence, listing only the 4 phases, output contract, and integration notes with no concept padding, matching the score-3 anchor of every token earning its place.	3 / 3
Actionability	It gives concrete directives ('Run pre-mortem: what can fail, how, and impact') and a 6-item Output Contract, but bullets like 'Reconcile contradictions' are abstract and there are no worked examples showing the framework applied, fitting score-2's 'some concrete guidance but incomplete / missing key details'.	2 / 3
Workflow Clarity	The 4 phases are explicitly numbered and sequenced, phase 3 (Critical Evaluation with pre-mortem) acts as an explicit error-anticipation checkpoint, and the Output Contract serves as a checklist, matching the score-3 anchor of a clear sequence with checkpoints.	3 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into well-signaled sections (4-Phase Analysis, Output Contract, Vibe Integration), which per the simple-skills note earns a 3 without bundle files.	3 / 3
	Total	11 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 conveys a clear niche and structure but relies on internal jargon and omits any explicit 'Use when...' trigger guidance, capping completeness at 2. It is distinguishable but not sharply differentiated from other analysis-oriented skills.

Suggestions

Rewrite the description in third-person natural language a user would actually say, e.g. 'Performs a 4-phase structured analysis (clarify, analyze, evaluate, synthesize) before implementation. Use when a task needs deeper reasoning, tradeoff analysis, or a pre-mortem.'

Replace jargon ('vibe pre-routing', 'claude-code-settings think-harder semantics') with plain trigger terms users would say, or move the compatibility note to the body.

Add an explicit 'Use when...' clause naming concrete triggers (deeper reasoning, tradeoff analysis, pre-mortem, multi-dimensional evaluation) to lift completeness and distinctiveness to 3.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and action ('4-phase structured analysis wrapper for vibe pre-routing') but does not enumerate multiple specific actions like the score-3 anchor; it is more than the vague score-1 example but not comprehensive.	2 / 3
Completeness	It states what the skill does but includes no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 even though the body later adds usage context.	2 / 3
Trigger Term Quality	'think-harder' and 'structured analysis' are keywords a user might say, but they are diluted by internal jargon ('vibe pre-routing', 'claude-code-settings think-harder semantics'), matching the score-2 anchor of some relevant keywords missing common variations rather than full natural coverage.	2 / 3
Distinctiveness Conflict Risk	The pre-routing analysis niche and 'think-harder' identity give it some specificity, but 'structured analysis' is generic enough to overlap with other analysis skills and the description lacks explicit distinct triggers, fitting the score-2 anchor.	2 / 3
	Total	8 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/think-harder/SKILL.md
Commit: f627ab5

Reviewed: 8 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.