feedback-mastery

Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.

1.01x

Quality

92%

Does it follow best practices?

Impact

100%

1.01x

Average score across 3 eval scenarios

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.

This is a well-structured, actionable skill for feedback conversations with clear frameworks, concrete examples, and good progressive disclosure. The main weakness is verbosity—some explanatory content and statistics could be trimmed since Claude understands interpersonal dynamics. The checklists and example phrases are particularly strong.

Suggestions

Remove explanatory content Claude already knows, such as 'Why it works' explanations and the research statistic in the overview

Trim the 'When to Use This Skill' section—the keywords list and some bullet points are redundant with the skill's obvious purpose

Dimension	Reasoning	Score
Conciseness	The skill contains useful frameworks but is verbose in places, explaining concepts Claude likely knows (e.g., why SBI works, general advice about listening). The 'Core insight' statistic and some explanatory text could be trimmed without losing value.	2 / 3
Actionability	Provides highly concrete guidance with specific tables, checklists, example phrases, opening lines, and reframing examples. The SBI examples are copy-paste ready, and the scenario walkthroughs give clear step-by-step approaches.	3 / 3
Workflow Clarity	The Preparation-Delivery-Follow-up model provides a clear three-phase sequence. Each phase has explicit steps, checklists serve as validation checkpoints, and the follow-up phase includes documentation and check-in scheduling for accountability.	3 / 3
Progressive Disclosure	Well-structured with clear sections, tables for quick reference, and appropriate references to companion resources (feedback-sbi-model.md, difficult-conversation-scripts.md) that are one level deep and clearly signaled.	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.

This is a well-crafted skill description that excels across all dimensions. It provides specific capabilities with named frameworks, uses natural trigger terms that users would actually say, includes an explicit 'Use when...' clause, and carves out a distinct niche around difficult conversations and feedback delivery.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Navigate difficult conversations', 'deliver constructive feedback', and names specific frameworks (Preparation-Delivery-Follow-up model, SBI technique). These are concrete, actionable capabilities.	3 / 3
Completeness	Clearly answers both what (navigate difficult conversations, deliver feedback using structured frameworks) AND when (explicit 'Use when...' clause covering preparing for difficult conversations, giving feedback, or managing conflicts).	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'difficult conversations', 'feedback', 'conflicts', 'constructive feedback'. These are terms people naturally use when seeking help with interpersonal workplace challenges.	3 / 3
Distinctiveness Conflict Risk	Clear niche focused on interpersonal communication challenges with specific frameworks named (SBI, Preparation-Delivery-Follow-up). Unlikely to conflict with other skills due to the specific domain of difficult conversations and feedback delivery.	3 / 3
	Total	12 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: softaworks/agent-toolkit
Commit: 3027f20

Reviewed: 4 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.