CtrlK
BlogDocsLog inGet started
Tessl Logo

create-issue

Create a GitHub issue in camunda/camunda with the correct template, component label, and parent link. Use when asked to create, file, or open an issue — for bugs, features, tasks, tech debt, or CVEs.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-sequenced procedure with strong validation gates around an irreversible create. The main gap is progressive disclosure: the skill is a single inline file with no reference split, so some detailed mapping tables and graphql snippets live in the main body.

Suggestions

Move the path-prefix → component-label table and the Zeebe label-split detail into a references/component-labels.md file, keeping only a short pointer and the fallback rule inline.

Trim the justifying clause for the grill-me invocation ("it builds shared understanding of impact, root cause, and reproduction path, making field inference much more accurate") to a single sentence or a bare pointer.

Drop the intro paragraph ("Creates a well-formed GitHub issue ... Prevents missing parent links, wrong component labels, and skipped required fields.") since it duplicates the frontmatter description.

DimensionReasoningScore

Conciseness

The body is mostly lean executable guidance, but a few passages over-explain (e.g. justifying the grill-me invocation, the intro sentence restating what the description already covers), so it is efficient with minor trim opportunities rather than maximally lean.

4 / 5

Actionability

Every step ships copy-paste-ready commands (`ls`, `cat`, `git diff`, `gh issue view/create`, `gh api` graphql, mktemp body-file pattern) plus concrete label/path mapping tables covering the common cases.

5 / 5

Workflow Clarity

Seven clearly sequenced steps include an explicit approval gate ("Do NOT call gh issue create yet"), parent verification, and a revise-and-retry loop, providing validation checkpoints and error-recovery feedback for an irreversible outward-facing action.

5 / 5

Progressive Disclosure

Content is well-sectioned into prerequisites and a numbered procedure with clearly signaled external pointers (grill-me, AGENTS.md), but with no bundle files and ~215 lines, some inline reference material (label tables, graphql type-resolution) could be split into a one-level-deep reference file.

4 / 5

Total

18

/

20

Passed

Description

87%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 strong, specific description that answers both what and when with concrete trigger phrases and a narrow niche. It is just short of top marks on specificity and trigger coverage, where a few more natural synonyms or listed actions would round it out.

DimensionReasoningScore

Specificity

"Create a GitHub issue in camunda/camunda with the correct template, component label, and parent link" names the domain and three concrete correctness concerns, but stops short of comprehensive coverage (e.g. issue type, severity labels) so it sits at 4 rather than 5.

4 / 5

Completeness

It explicitly states the what ("Create a GitHub issue ... with the correct template, component label, and parent link") and pairs it with a concrete "Use when ..." trigger clause, matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

"Use when asked to create, file, or open an issue — for bugs, features, tasks, tech debt, or CVEs" supplies verb synonyms and a full type list, but a few natural variants ("report", "ticket", "log a bug") are missing, keeping it below a 5.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow and repo-specific (issue creation in camunda/camunda) with distinct triggers, giving minimal overlap risk with other skills.

5 / 5

Total

18

/

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
camunda/camunda
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.