issue-creation

Create Gentle AI issues with issue-first checks. Trigger: creating GitHub issues, bug reports, or feature requests.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable, with complete copy-paste CLI examples, field tables, and a clearly sequenced workflow featuring explicit checkpoints. Its main weakness is moderate redundancy — the Commands and Label System sections repeat information already presented inline.

Suggestions

Remove or trim the standalone "Commands" section, since its gh issue create/edit invocations are already shown in full in the Bug Report, Feature Request, and Maintainer Approval examples above.

Drop the "Applied Automatically on Issue Creation" sub-table in Label System — the auto-labels are already stated per template (e.g. "Auto-labels: bug, status:needs-review") — or keep only one of the two presentations.

If retaining both the Workflow and the Maintainer Approval Workflow, cross-reference them instead of re-deriving the needs-review → approved progression in two places.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-padding and is mostly efficient, but the standalone "Commands" section duplicates the inline gh examples and the "Label System / Applied Automatically" table restates the per-template auto-labels already shown above, so it could be tightened.	2 / 3
Actionability	Copy-paste-ready `gh issue create --template ... --body "..."` examples with complete field values, plus concrete `gh issue edit --add-label` commands and explicit field tables, match the fully-executable anchor at 3.	3 / 3
Workflow Clarity	The numbered Workflow sequences creation through approval, with explicit checkpoints — a duplicate search (step 1), pre-flight checkbox checklist in templates, and an approval gate (step 6) before any PR — giving clear sequencing with validation steps.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the skill is a single self-contained file with well-organized sections (When to Use, Critical Rules, Workflow, Issue Templates, Label System, Decision Tree) and easy navigation, which qualifies for 3 under the no-external-references scoring note.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 concise, third-person, and clearly pairs a capability statement with an explicit trigger clause covering natural user terms. Its only weakness is modest action specificity, leaning on the slightly vague 'issue-first checks' phrase rather than enumerating concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes "Create Gentle AI issues" and "issue-first checks" — it names the domain and one concrete action but 'issue-first checks' is vague and no further specific actions are enumerated, so it falls short of the multi-action anchor at 3.	2 / 3
Completeness	It answers both 'what' ("Create Gentle AI issues with issue-first checks") and 'when' (explicit "Trigger: ..." clause), satisfying the explicit-trigger requirement that would otherwise cap completeness at 2.	3 / 3
Trigger Term Quality	"Trigger: creating GitHub issues, bug reports, or feature requests" gives good coverage of the natural terms a user would actually say, matching the score-3 anchor for natural keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The "Gentle AI issues" niche plus the bug-report/feature-request triggers carve a clear, distinct scope that is unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/issue-creation/SKILL.md
Commit: e01b114

Reviewed: about 15 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.