gentle-ai-issue-creation

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

Quality

91%

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

92%

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

The skill is lean, highly actionable, and has a clear workflow with explicit stop/validation checkpoints. The only weakness is progressive disclosure: substantial reference material (label and priority tables, dual flow diagrams) is inline in SKILL.md rather than split into a referenced file.

Suggestions

Move the full Label System tables and/or Maintainer Approval Workflow diagram into a `references/labels.md` file, leaving SKILL.md with a concise summary and a single "See references/labels.md for the full label matrix" pointer to improve progressive disclosure.

Consider consolidating the maintainer-approval ASCII diagram and the Decision Tree into one reference to reduce inline reference bulk while keeping the core workflow in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely operational content (templates, fields, commands, label tables) with no padding explaining concepts Claude already knows; every section earns its place, though the inline label/priority reference tables are borderline reference material kept tight.	3 / 3
Actionability	It provides concrete, executable `gh issue create`/`gh issue list`/`gh issue view` commands with real flags, template filenames, web-form URLs, and required-field tables, all copy-paste ready.	3 / 3
Workflow Clarity	A clear numbered 5-step workflow is paired with an explicit STOP checkpoint ("STOP after step 3 ... Do NOT open a PR until status:approved") and a duplicate-check step, plus a maintainer-approval flow diagram, giving explicit validation checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist, so the single-file skill leans on inline reference material (full label/priority tables and two ASCII workflow diagrams) that could arguably live in a separate reference file; while well-organized, some content that could be separate is inline rather than one-level-deep references.	2 / 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 and well-structured, answering both what it does and when to trigger it with natural user language. Only specificity is slightly below top because it names a single composite action rather than enumerating several discrete capabilities.

Suggestions

Optionally expand the action clause to list a few concrete capabilities (e.g., "search for duplicates, file bug reports and feature requests via templates") to lift specificity to a 3.

Dimension	Reasoning	Score
Specificity	"Create Gentle AI issues with issue-first checks" names a concrete action and domain, but does not list multiple distinct actions like the score-3 anchor; it is stronger than the single-action score-2 example yet still names only one primary action.	2 / 3
Completeness	It explicitly answers both "what" ("Create Gentle AI issues with issue-first checks") and "when" (an explicit "Trigger:" clause), satisfying the score-3 anchor's requirement for explicit triggers on both halves.	3 / 3
Trigger Term Quality	"Trigger: creating GitHub issues, bug reports, or feature requests" provides natural phrasing a user would actually say (open an issue, report a bug, request a feature), with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoping to "Gentle AI issues" plus the repo-specific "issue-first checks" gate gives it a clear niche, making it unlikely to trigger for unrelated issue-handling 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: skills/issue-creation/SKILL.md
Commit: e01b114

Reviewed: about 13 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.