CtrlK
BlogDocsLog inGet started
Tessl Logo

comment-writer

Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is comment-writer in Gentleman-Programming/gentle-ai

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-crafted, compact instruction skill: dense voice rules in a scannable table, a concrete formula, and realistic examples that model the exact tone being taught. The only improvements are trimming the trigger list that duplicates the description and adding one non-PR example to cover the declared Slack/Discord use cases.

DimensionReasoningScore

Conciseness

The body is lean with no re-taught concepts and every rule earns its place ('Start with the actionable point', 'No em dashes'), but the 'When to Use' bullet list re-states trigger contexts already given in the description, a minor redundancy that could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready guidance throughout: a comment formula template, three full example comments, and an executable 'gh pr view' command. Minor gap: Slack/Discord/async updates are declared use cases but have no example, unlike the PR-focused cases.

4 / 5

Workflow Clarity

This is a simple single-task skill and the single action is unambiguous: apply the voice rules, follow the three-part comment formula, and mirror the examples. No destructive or batch operations exist that would require validation checkpoints.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; all content (voice rules, formula, examples, one command) belongs in SKILL.md, and the clean section headers ('When to Use', 'Voice Rules', 'Comment Formula', 'Examples', 'Commands') make navigation trivial.

5 / 5

Total

18

/

20

Passed

Description

78%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 description that explicitly answers both what the skill does and when to use it with concrete trigger contexts. Its weakest point is specificity: it names a single action (write comments) rather than enumerating capabilities, and a few natural trigger variations are missing.

Suggestions

Expand the capability statement to enumerate 2-3 concrete actions, e.g. 'Write and edit PR review comments, maintainer replies, and async updates with a warm, direct teammate voice.'

Add missing natural trigger variations users would actually say, such as 'code review feedback', 'respond to reviewer comments', or 'Discord messages'.

Sharpen distinctiveness from adjacent review skills by scoping the trigger to comment/communication tone (e.g. 'when writing feedback messages humans will read') rather than the broad term 'reviews'.

DimensionReasoningScore

Specificity

The description names the domain ('collaboration comments') with one concrete action ('Write warm, direct collaboration comments') but does not list several distinct actions, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the 'lists several specific actions' anchor above.

3 / 5

Completeness

Both 'what' ('Write warm, direct collaboration comments') and 'when' ('Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments') are explicitly stated with concrete trigger phrases, matching the top anchor; the 'Trigger:' clause is equivalent explicit trigger guidance to a 'Use when...' clause.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('PR feedback, issue replies, reviews, Slack messages, or GitHub comments') but a few common terms users would say are missing, such as 'code review', 'respond to comments', or 'Discord'.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (human-facing collaboration comment tone) but the 'reviews' and 'PR feedback' triggers overlap with code-review and review-adjacent skills, so it is mostly distinct with minor overlap risk rather than a clear niche with minimal conflict.

4 / 5

Total

16

/

20

Passed

Validation

100%

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
Gentleman-Programming/gentle-ai
Reviewed

Table of Contents

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.