gentle-ai-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 ./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 has good trigger terms and completeness with an explicit trigger clause, but suffers from vague capability language—'issue-first checks' is unexplained jargon. It would benefit from clarifying what 'Gentle AI' refers to and what concrete actions the skill performs beyond just 'creating' issues.
Suggestions
Clarify what 'issue-first checks' means by describing the concrete actions performed (e.g., 'validates duplicates before creating', 'applies templates', 'checks existing issues').
Explain what 'Gentle AI' refers to—is it a project name, a repo, or a methodology?—so the skill is more clearly scoped and distinguishable from generic GitHub issue skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('GitHub issues') and some actions ('bug reports, feature requests'), but 'issue-first checks' is vague and unexplained. It doesn't list multiple concrete actions like filling templates, labeling, or assigning. | 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: 'creating GitHub issues', 'bug reports', 'feature requests'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | 'Gentle AI issues' provides some specificity to a particular project/context, but 'GitHub issues' and 'bug reports' are broad enough to potentially overlap with general GitHub workflow skills. The 'issue-first checks' concept is unclear, reducing distinctiveness. | 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 well-crafted, highly actionable skill with clear workflows and explicit validation gates (the status:approved checkpoint). Its main weakness is length — the label system reference tables and redundant representations of the workflow (text, ASCII diagram, and decision tree) inflate the token cost without proportional benefit. Splitting reference material into a separate file would improve both conciseness and progressive disclosure.
Suggestions
Move the full label system tables (Status, Type, Priority) into a separate LABELS.md reference file and link to it from the main skill.
Consolidate the three representations of the workflow (numbered steps, maintainer approval ASCII diagram, and decision tree) into one or two, removing redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some content that could be trimmed. The full label system tables (priority labels, type labels for PRs) go beyond what's needed for issue creation. The decision tree and maintainer approval workflow ASCII diagrams, while nice, partially duplicate information already stated in the Critical Rules and Workflow sections. | 2 / 3 |
Actionability | Highly actionable with concrete, copy-paste-ready `gh` CLI commands for searching, creating bug reports, and creating feature requests. Required fields are clearly enumerated in tables, valid scopes are listed, and template paths are specified. The examples are executable and specific. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (search → choose template → submit → wait → PR) with an explicit stop-gate after step 3 and a clear validation checkpoint (status:approved required before any work begins). The maintainer approval flowchart and decision tree reinforce the sequence. The duplicate-check step serves as a validation checkpoint before submission. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a long monolithic file (~180 lines of content) with no references to external files. The label system tables and maintainer workflow details could be split into a separate reference file, keeping the SKILL.md focused on the core issue creation task. | 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.