issue-creation
Create Gentle AI issues with issue-first checks. Trigger: creating GitHub issues, bug reports, or feature requests.
66
79%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./internal/assets/skills/issue-creation/SKILL.mdQuality
Discovery
82%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 provides adequate trigger terms and covers both what and when, but lacks specificity about what 'issue-first checks' means and what concrete actions the skill performs beyond creating issues. The 'Gentle AI' qualifier adds some distinctiveness but 'issue-first checks' is unexplained jargon that weakens clarity.
Suggestions
Expand the 'what' portion to list specific concrete actions (e.g., 'checks for duplicate issues before creating, applies labels, formats with templates') instead of the vague 'issue-first checks'.
Clarify what 'Gentle AI' refers to — if it's a specific project or tool, make that explicit so Claude can better distinguish when to use this skill vs. a general GitHub issue skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub issues) and mentions some types (bug reports, feature requests), but 'issue-first checks' is vague and the description doesn't list concrete actions beyond 'create'. | 2 / 3 |
Completeness | Answers both 'what' (create Gentle AI issues with issue-first checks) and 'when' (explicit 'Trigger:' clause listing creating GitHub issues, bug reports, or feature requests). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'GitHub issues', 'bug reports', 'feature requests', and 'creating'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | 'Gentle AI issues' provides some specificity to a particular project/tool, but 'GitHub issues' and 'bug reports' are broad enough to potentially overlap with general GitHub workflow skills. The 'issue-first checks' concept is unclear and doesn't strongly differentiate. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with clear workflows and excellent concrete examples. Its main weakness is length — there's meaningful redundancy between sections (critical rules vs. label system vs. maintainer workflow) and the full CLI examples with complete bodies make it token-heavy. The content would benefit from being split into an overview plus reference files for the detailed template specifications and examples.
Suggestions
Consolidate redundant information: the critical rules, label system, and maintainer approval workflow sections overlap significantly — merge them into a single concise reference.
Consider extracting the full CLI examples and template field tables into a separate reference file (e.g., TEMPLATES.md), keeping only a brief summary and one short example in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy — the decision tree repeats information already covered, the label system table partially restates what's in the template sections, and the maintainer approval workflow repeats the critical rules. The full CLI examples with complete body text are lengthy but arguably necessary for copy-paste use. | 2 / 3 |
Actionability | Excellent actionability with fully executable `gh` CLI commands, complete example issue bodies with all required fields filled in, and specific bash commands for searching, creating, and managing issues. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear sequential workflows for both issue creation and maintainer approval, with explicit validation checkpoints (search for duplicates first, fill ALL required fields, pre-flight checkboxes, wait for approval before opening PR). The decision tree provides clear routing logic. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's a long monolithic document (~170 lines of content) with no references to external files. The detailed template field tables and full CLI examples could be split into separate reference files, with the SKILL.md serving as a concise overview. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- sergiodvillegas-art/gentle-ai
- Commit
3bfa934
- 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.