CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-creation

Structured workflow for drafting NEW GitHub issues with codebase research, duplicate detection, and testing approach. Always asks clarifying questions and shows the draft for approval before creating. For searching, listing, viewing, or updating existing issues, use the "issues" skill instead.

60

Quality

68%

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 ./.claude/skills/issue-creation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

The body is a well-sequenced, actionable workflow with strong approval gates and feedback loops, and it is appropriately self-contained with no bundle files. Its main weakness is repetition of the anti-prescription principle across the Important note and three separate rules.

Suggestions

Consolidate the 'focus on the problem, not the solution / research informs scope' guidance into a single rule; the Step 2 Important note plus Rules 2, 3, and 4 all restate the same idea.

Consider moving the duplicate-search command variants into a short reference snippet so Step 3 reads more cleanly.

DimensionReasoningScore

Conciseness

The body is mostly lean and imperative, but the 'problem not solution / research informs scope not implementation' principle is restated four times (Step 2 Important note plus Rules 2, 3, and 4), which is noticeable padding that could be consolidated.

3 / 5

Actionability

Provides copy-paste-ready gh commands (search, list, create with full flags), a concrete issue template, and named tools (Grep, Glob, Read, Explore, AskUserQuestion); minor gaps remain in the templated placeholders like '<issue body from step 5>'.

4 / 5

Workflow Clarity

Six steps are explicitly sequenced with hard validation checkpoints ('Do NOT proceed to Step 2 until the user has answered', 'Do NOT create the issue until the user approves') and a feedback loop (apply edits then re-show the draft), satisfying the validation requirement for an outward-facing action.

5 / 5

Progressive Disclosure

No bundle files exist, so all content lives in one well-sectioned SKILL.md with clear headers (When to use, Process, Rules) and no nested references; at ~125 lines it is slightly beyond the simple-skill exception, keeping it just below a 5.

4 / 5

Total

16

/

20

Passed

Description

63%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.

The description is specific and action-rich and draws a clear boundary against the sibling 'issues' skill, but it lacks a positive 'Use when...' trigger clause and the natural user phrases ('report a bug', 'request a feature') that would surface it at the right moment.

Suggestions

Add an explicit positive trigger clause, e.g. 'Use when the user asks to create an issue, report a bug, request a feature, or track new work.'

Surface natural trigger terms like 'create an issue', 'report a bug', and 'request a feature' in the description rather than only in the body.

Lead with the trigger ('Use when creating new GitHub issues...') before the capability list so the 'when' is as prominent as the 'what'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'drafting NEW GitHub issues with codebase research, duplicate detection, and testing approach', 'asks clarifying questions', 'shows the draft for approval before creating' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

The 'what' is clear, but there is no positive 'Use when...' trigger clause — only a negative boundary ('For searching, listing, viewing, or updating existing issues, use the issues skill instead'), which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It names 'GitHub issues' and 'drafting' but omits the natural phrases users actually say ('create an issue', 'report a bug', 'request a feature'), which only appear in the body, not the description; common variations are missing.

3 / 5

Distinctiveness Conflict Risk

The explicit boundary directing searching/listing/viewing/updating to the 'issues' skill gives it a clear niche with minimal conflict risk, though it shares the 'GitHub issues' surface with that closely related skill.

4 / 5

Total

15

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mckinsey/agents-at-scale-ark
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.