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

82%

Does it follow best practices?

Impact

100%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

81%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.

A highly actionable, well-sequenced instruction skill with copy-paste scripts, templates, and checklists backed by real one-level-deep reference files. The main weakness is conciseness — motivational statistics and some inlined examples could be trimmed or moved to references.

Suggestions

Remove the unfalsifiable statistics ('60% more likely', 'reduces cognitive processing by 30%') and the 'Core insight' framing; they pad tokens without adding actionable guidance.

Move some of the inlined SBI examples and opening-line tables into references/feedback-sbi-model.md and references/difficult-conversation-scripts.md, keeping only one representative example inline in SKILL.md.

Tighten the Common Difficult Scenarios section by reducing each scenario's example dialogue, since the reference scripts file already covers detailed scripts.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient actionable tables and examples, but includes unnecessary motivational padding Claude does not need ('60% more likely to reach a positive resolution', 'reduces cognitive processing by 30%') and several example-heavy sections that could be trimmed.	3 / 5
Actionability	Provides copy-paste ready guidance throughout — exact opening lines, full SBI example quotes, an accusatory-to-constructive reframing table, a sample follow-up message template, and worked scenario scripts covering common cases.	5 / 5
Workflow Clarity	The Preparation-Delivery-Follow-up model gives a clearly sequenced multi-step process, reinforced by Before/During/After and per-phase checklists that serve as explicit checkpoints for the conversation workflow.	5 / 5
Progressive Disclosure	References are well-signaled and one level deep ('For more examples: See references/...', plus a Companion Resources section), and all three referenced files exist; however, a substantial amount of detailed example content is inlined in SKILL.md that could live in those reference files.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A strong, well-structured description that clearly states capabilities and provides an explicit 'Use when' trigger with natural keywords and named frameworks. Minor gains are possible by adding more concrete action verbs and a few additional synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Navigate difficult conversations and deliver constructive feedback') plus two named frameworks (Preparation-Delivery-Follow-up, SBI), but the verbs remain somewhat high-level rather than a comprehensive list of specific actions.	4 / 5
Completeness	Explicitly answers both 'what' (navigate difficult conversations, deliver feedback via named frameworks) and 'when' with a concrete 'Use when preparing for difficult conversations, giving feedback, or managing conflicts' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('difficult conversations', 'giving feedback', 'managing conflicts') with some synonym coverage, but omits common variations like '1:1' or 'performance review' that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	The feedback/difficult-conversation niche is clearly distinguishable with distinct triggers, though there is minor overlap risk with general communication or conflict-resolution skills.	4 / 5
	Total	17 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: softaworks/agent-toolkit
Path: skills/feedback-mastery/SKILL.md
Commit: 3027f20

Reviewed: 4 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.