agent-response-style

Default response behavior for AI coding agents: professional, factual, neutral tone with calibrated critical evaluation. Baseline for every task: implementation, code review, debugging, planning, research, evaluation, Q&A.

Quality

65%

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 ./.claude/skills/agent-response-style/SKILL.md

Quality

Content

77%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 actionable with a clear workflow and verification checkpoints, but it is padded with overlapping restatements and keeps all content in one inline file rather than using progressive disclosure.

Suggestions

Trim the repeated peer-review vs. teacher-voice framing into a single authoritative statement to reduce token cost.

Consider splitting the lengthy teaching-coach section into a referenced bundle file to improve progressive disclosure.

Remove explanation of concepts Claude already understands (e.g., basic design-review framing) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive and avoids jargon, but ~95 lines restate the peer-review vs. teacher-voice distinction in several overlapping places and explain framing Claude already grasps, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It gives concrete, executable directives ("present 2 to 4 credible alternatives", "Quiz them with... AskUserQuestion", "run it through the humanizer skill"), which is fully actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The 'Suggested Response Workflow' is a clear 5-step sequence, and the teaching section adds explicit verification checkpoints (quiz, restate understanding, confirm before moving on), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Content is a single monolithic SKILL.md with all material inline and only an external reference to the unbundled 'humanizer' skill; sections are well-organized but content that could be split out stays inline, landing on the middle anchor.	2 / 3
	Total	10 / 12 Passed

Description

52%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 is specific about behaviors and task scope but is overly broad as a default-everywhere skill, lacks an explicit trigger clause, and uses somewhat abstract framing rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' trigger clause so users know when to load this skill.

Narrow the scope so it does not claim to be a baseline for every task, reducing conflict with specialized skills.

Lead with the colloquial trigger terms users naturally say (e.g., 'code review', 'push back on a design') rather than abstract phrasing like 'calibrated critical evaluation'.

Dimension	Reasoning	Score
Specificity	Description names concrete behaviors ("professional, factual, neutral tone", "calibrated critical evaluation") and enumerates multiple specific task domains ("code review, debugging, planning, research, evaluation, Q&A"), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does (response behavior/tone) and lists applicable task types, but it lacks an explicit "Use when..." trigger clause, which per the rubric guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant task-mode terms users would say ("code review, debugging, planning, research"), but frames them around abstract concepts ("AI coding agents", "calibrated critical evaluation") and misses common colloquial trigger variations, so it lands on the middle anchor.	2 / 3
Distinctiveness Conflict Risk	It positions itself as a "baseline for every task" response style, which is maximally broad and would overlap or conflict with virtually every other skill, matching the very-generic anchor.	1 / 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: SRombauts/SQLiteCpp
Path: .claude/skills/agent-response-style/SKILL.md
Commit: 736fb31

Reviewed: 6 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.