CtrlK
BlogDocsLog inGet started
Tessl Logo

github-issue-creator

Transform messy input (error logs, voice notes, screenshots) into clean, actionable GitHub issues.

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/github-issue-creator/SKILL.md

The canonical home for this skill is github-issue-creator in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%Scale 1-5

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 instruction-only skill with clear output formatting, good examples demonstrating the input→output transformation, and efficient guidelines. Its main weaknesses are the lack of an explicit workflow sequence with validation checkpoints (e.g., checking that all required fields are populated before writing the file) and a throwaway 'When to Use' section. The two concrete examples are the skill's strongest asset, clearly showing how messy input becomes structured output.

Suggestions

Add an explicit workflow sequence: 1. Parse input for facts, 2. Map to template fields, 3. Identify missing/ambiguous fields and flag or infer them, 4. Validate all required sections are populated before writing the file.

Remove or replace the generic 'When to Use' section — it currently adds no value and wastes tokens.

Consider adding a brief checklist of required vs. optional fields in the template to serve as a validation checkpoint before finalizing the issue.

DimensionReasoningScore

Conciseness

Generally efficient with minimal fluff. The severity table and guidelines are tight. Minor over-explanation in places like 'This skill is applicable to execute the workflow or actions described in the overview' (adds nothing) and some guideline descriptions could be trimmed, but overall respects token budget well.

4 / 5

Actionability

Provides a concrete output template, clear naming convention, specific directory location, and two detailed input→output examples that demonstrate the transformation. However, it lacks any executable code or commands (e.g., no `gh issue create` integration or script for file creation), and the guidance is purely instructional rather than tool-integrated.

4 / 5

Workflow Clarity

The skill describes a single transformation task with clear output format, but there's no explicit workflow sequence (e.g., 1. Parse input, 2. Identify missing fields, 3. Generate issue, 4. Validate completeness). For a skill that handles messy/ambiguous input, a validation step or checklist to verify all required fields are populated would strengthen reliability. The process is implicit rather than explicitly sequenced.

3 / 5

Progressive Disclosure

Well-structured with clear sections (template, guidelines, examples, output location). For a standalone skill with no bundle files, the content is appropriately organized and not monolithic. The examples are appropriately inline since they're essential to understanding the transformation. Minor gap: the 'When to Use' section is generic filler that adds no value.

4 / 5

Total

15

/

20

Passed

Description

61%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.

The description is concise and communicates a clear value proposition—transforming unstructured inputs into structured GitHub issues. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to reliably select this skill. Adding trigger guidance and a few more natural synonyms would significantly improve it.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user wants to create a GitHub issue from raw input such as error logs, voice transcripts, screenshots, or unstructured notes.'

Include additional natural trigger terms and synonyms such as 'bug report', 'ticket', 'file an issue', 'create issue', or 'issue template' to improve keyword coverage.

DimensionReasoningScore

Specificity

Names the domain (GitHub issues) and describes a concrete action (transform messy input into clean issues), but doesn't elaborate on specific sub-actions like labeling, assigning, formatting, or template usage.

3 / 5

Completeness

The 'what' is clear (transform messy input into GitHub issues), but there is no explicit 'when' clause or trigger guidance. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes good natural keywords like 'error logs', 'voice notes', 'screenshots', 'GitHub issues' that users would naturally mention. Missing some variations like 'bug report', 'issue creation', 'ticket', or 'file an issue'.

4 / 5

Distinctiveness Conflict Risk

The combination of specific input types (error logs, voice notes, screenshots) and specific output (GitHub issues) creates a fairly distinct niche. Minor overlap risk with general GitHub skills or general issue-tracking skills.

4 / 5

Total

14

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.