engineer-prompts-for-reasoning

Guide to writing prompts for reasoning models (Gemini Pro, GPT-4o, Claude Sonnet), focused on structure and context. Use when the user is writing or tuning prompts for a reasoning or smart model.

Quality

60%

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 ./plugins/flowai-engineering/skills/engineer-prompts-for-reasoning/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The content is a clear, actionable beginner guide with a usable template and worked example. Its main weaknesses are moderate verbosity (re-explaining familiar concepts) and an inlined monolithic structure with no progressive disclosure into separate references.

Suggestions

Cut explanations of concepts Claude already knows (the 'briefing a senior colleague' analogy, the rationale for XML tags) to tighten the token budget.

Move the full templates and the worked example into separate referenced files (e.g., TEMPLATES.md, EXAMPLES.md) and keep SKILL.md as a concise overview pointing to them.

Add an explicit verification step to the checklist (e.g., 'review the generated prompt against the success criteria before sending').

Dimension	Reasoning	Score
Conciseness	The guide is mostly efficient and well-organized with copy-paste templates, but it restates concepts Claude already knows (e.g. explaining that reasoning models 'need Context and Structure to stay on track', the 'briefing a senior colleague' analogy) and could be trimmed to be leaner.	3 / 5
Actionability	Provides a concrete, copy-paste-ready BEGINNER TEMPLATE plus a fully worked code-refactoring example with specific role, rules, and instructions; only minor gaps versus a maximally executable reference.	4 / 5
Workflow Clarity	A clear numbered framework and a closing pre-flight checklist sequence the steps well, and the 'ask for a plan first' technique acts as a checkpoint; it is not a destructive/batch skill so no validation cap applies, but explicit verification checkpoints are somewhat light.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single inlined guide; sections are organized, but the full templates and example are inlined rather than split into referenced files, so structure could be better separated.	3 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 clearly states what the skill does and when to use it with an explicit trigger clause, placing it above average. It could be stronger by listing more concrete actions and richer natural trigger terms users actually say.

Suggestions

List concrete actions the skill performs (e.g., 'structures prompts with XML tags, adds context/goal/constraints, requests plans before output').

Add natural trigger terms and synonyms users actually say, such as 'prompt engineering', 'chain-of-thought prompt', or specific model names.

Tighten the 'Use when' clause with concrete scenarios (e.g., 'when the user asks to improve, structure, or debug a prompt').

Dimension	Reasoning	Score
Specificity	Names the domain (writing/tuning prompts for reasoning models) and a couple of concrete actions ('writing or tuning prompts'), but does not enumerate multiple specific actions like structuring, tagging, or planning, so coverage is partial.	3 / 5
Completeness	Has a clear 'what' (guide to writing prompts for reasoning models focused on structure and context) and an explicit 'when' ('Use when the user is writing or tuning prompts for a reasoning or smart model'), though the when could be slightly more specific.	4 / 5
Trigger Term Quality	Includes some natural terms ('prompts for reasoning models', 'tuning prompts', 'smart model') but lacks common variations/synonyms users say (e.g. 'prompt engineering', 'chain of thought', model names like GPT/Claude), so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	Scoped to prompt-writing for reasoning models, which is a fairly distinct niche with only minor overlap risk against a generic prompt-engineering or code-review skill.	4 / 5
	Total	14 / 20 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: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/engineer-prompts-for-reasoning/SKILL.md
Commit: b4ba256

Reviewed: ~21 hours 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.