CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github-issue-creator

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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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

75%Weight 40%Scale 1-5

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

A well-structured, actionable body for a simple formatting skill: complete output template, clear file conventions, severity rubric, and two strong input/output examples. Weakest spots are the vacuous When to Use section, the unexplained `!Description` image format, and the absence of a screenshot example despite screenshots being a claimed input type.

Suggestions

Replace the circular "When to Use" section with concrete applicability guidance (e.g., when the user supplies raw logs/notes/screenshots and expects an issue file), or delete it.

Clarify the image-handling directive: spell out what `!Description` means (e.g., inline reference format and where the attachment lives) or show one worked example.

Add a brief screenshot-input example to cover the third claimed input type alongside voice dictation and error paste.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: a copy-paste output template, terse guidelines, and two input/output examples with no concept explanations. One trimmable instance remains — the "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview") is circular filler — matching anchor 4's 'minor instances of over-explanation that could be trimmed' rather than anchor 5's 'every token earns its place.'

4 / 5

Actionability

Concrete, executable guidance throughout: a full markdown output template, a file location and naming convention ("/issues/" with "YYYY-MM-DD-short-description.md"), a severity rubric, and two complete input→output examples. Minor gaps: the screenshot input type (one of the three claimed inputs) lacks a worked example, and the image-handling spec "Format: `!Description`" is cryptic, so it stops short of anchor 5's 'specific examples cover the common cases.'

4 / 5

Workflow Clarity

As a single-task skill the action is largely unambiguous — what the output looks like (template), where it goes (/issues/), and how it is named. Minor ambiguities remain: no explicit transformation sequence (extract facts → fill template → write file), unclear image-reference format, and placeholder guidance like "Region/Version" without elaboration. This fits anchor 4's 'minor validation gaps' tier; no destructive/batch validation cap applies since writing one file is neither.

4 / 5

Progressive Disclosure

Well-organized sections (Output Template, Output Location, Guidelines, Examples) with everything appropriately inline for a simple single-file skill — no nested or buried references, and no content that clearly belongs in a separate file. Minor organization gaps (the vacuous When to Use section, and examples sitting after guidelines) keep it at anchor 4 rather than 5's 'easy navigation' with a fully tight structure.

4 / 5

Total

16

/

20

Passed

Description

61%Weight 40%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.

A crisp, specific description with good natural trigger terms and a distinct niche, but it omits any explicit 'Use when...' trigger clause, capping completeness, and describes only one core action. Adding a when-to-use clause with concrete trigger phrases would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user pastes an error log, dictates a bug report, or asks to create/file a GitHub issue from screenshots or rough notes."

Enumerate 1-2 more concrete actions (e.g., 'extract reproduction steps, classify severity') to strengthen the single 'transform' action verb.

Include common user synonyms such as 'bug report' or 'file an issue' alongside 'GitHub issues' to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("GitHub issues") and one concrete action ("Transform messy input ... into clean, actionable GitHub issues") with specific input types ("error logs, voice notes, screenshots"), but offers only a single action verb rather than several specific actions. Anchor 4 requires 'several specific actions,' which this does not meet, while anchor 2's 'minimal or generic' actions undersells the concrete transformation described.

3 / 5

Completeness

The 'what' is clear (transform messy input into GitHub issues), but there is no 'Use when...' clause or equivalent explicit trigger guidance; timing is only weakly implied by the input types. The judging guidelines explicitly cap completeness at 3 in this case, and anchor 4's 'when could be more explicit' presumes a when-clause exists at all.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "GitHub issues", "error logs", "voice notes", "screenshots". Missing a few natural variations and synonyms such as "bug report", "file an issue", or "ticket", so it falls short of anchor 5's comprehensive synonym/extension coverage but exceeds anchor 3's 'missing common variations' by a clear margin.

4 / 5

Distinctiveness Conflict Risk

"Transform messy input ... into clean, actionable GitHub issues" carves out a clear niche with distinct triggers. Minor overlap risk remains with closely related skills (e.g., screenshot-analysis or bug-triage skills) via the generic "screenshots" and "error logs" terms, keeping it below anchor 5 but comfortably above anchor 3's broader overlap.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

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

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.