CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-issue

Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.

Quality

82%

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

92%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 lean, well-sequenced workflow with concrete commands, file paths, labels, and an explicit user-approval checkpoint before submission. Its only weaknesses are small actionability gaps: the draft filename slug is undefined and the `gh issue list --search` command lacks its query argument.

DimensionReasoningScore

Conciseness

The ~70-line body is lean with no explanations of concepts Claude already knows, no filler, and every section carrying actionable content ('Search for relevant code...', specific template paths, exact label values), matching anchor 5 ('lean and efficient; assumes Claude's competence; every token earns its place'). Not 4 because there is no over-explanation to trim — the intro, rules, and bilingual block template are all operationally necessary.

5 / 5

Actionability

Concrete executable guidance dominates: template file paths (`.github/ISSUE_TEMPLATE/feature_request.yml`), a ready `gh issue create --title "..." --body-file .qwen/issues/draft-<slug>.md` command, exact labels (`type/feature-request`, `status/needs-triage`), and a copy-paste collapsible-block snippet — matching anchor 4 ('mostly executable guidance; concrete code or commands with minor gaps'). Not 5 because of the minor gaps: `<slug>` is never defined, `gh issue list --search` is given without its query argument, and no example title/draft is shown; not 3 because the guidance is genuinely executable, not pseudocode.

4 / 5

Workflow Clarity

Six clearly sequenced steps (Classify → Investigate → Read template → Draft → Review → Submit) with an explicit validation checkpoint — 'Present the draft. Iterate on feedback until the user is satisfied. Do not submit until the user explicitly approves.' — and a feedback loop on the draft, matching anchor 5 ('clear sequence with explicit validation steps; feedback loops for error recovery'). Not 4 because the approval gate before the risky outward-facing action (issue creation) is fully explicit, not implicit. No destructive/batch-operation cap applies, and the approval checkpoint is present regardless.

5 / 5

Progressive Disclosure

This is a short, single-purpose skill with no bundle files present; nothing in the body needs to live in a separate file, and the body itself is well-organized under clear ## / ### headers matching each workflow step. Per the rubric's simple-skill guidance ('under 50 lines with no need for external references, progressive disclosure can score 5 with just well-organized sections') and the ~70-line self-contained body with zero inline bloat, this fits anchor 5's intent: easy navigation, everything appropriately placed. Not 4 because there is no organization gap — no content that should be split out, and all internal references (template paths, `gh` commands) are to files/tools, not to missing bundle documents.

5 / 5

Total

19

/

20

Passed

Description

66%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 states a clear, concrete 'what' with domain-specific natural trigger terms, but completely lacks a 'when to use' clause, which caps its completeness. Adding an explicit trigger sentence and common user phrasings like 'feature request', 'report a bug', or 'open an issue' would materially improve it.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when the user asks to create, open, or file a GitHub issue, or to report a bug or request a feature' — this directly addresses the completeness cap at 3.

Include common natural phrasings and synonyms users actually say ('open an issue', 'file an issue', 'report a bug', 'feature request') to lift trigger-term coverage from good to comprehensive.

Optionally mention the investigation/approval loop ('investigates the codebase, drafts for review, submits after approval') so the description's action list covers the workflow the body actually implements.

DimensionReasoningScore

Specificity

"Draft and submit a GitHub issue" plus "with bilingual body and correct labels" names the domain and several concrete actions, matching anchor 4 ('lists several specific actions; minor gaps in coverage'). Not 5 because it omits capabilities the body actually has (investigating the codebase, applying type/status labels by classification); not 3 because the action set goes well beyond a single generic verb like 'Processes PDF files'.

4 / 5

Completeness

The 'what' is clear ('Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels'), but there is no 'when' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the 'what' is fully articulated rather than vague; not 4 because 'when' is not merely implicit — it is entirely absent, so the anchor-4 condition ('when' present but could be more explicit) is unmet.

3 / 5

Trigger Term Quality

"GitHub issue", "draft", "submit", and "bug description" are natural phrases a user would say, matching anchor 4 ('good keyword coverage; a few natural terms missing'). Not 5 because common variants users actually use — "file an issue", "open an issue", "report a bug", "feature request" — are absent; not 3 because the terms present are domain-specific and genuinely natural rather than generic filler like 'Works with files'.

4 / 5

Distinctiveness Conflict Risk

GitHub issue drafting/submission with bilingual body and label requirements is a fairly distinct niche with minimal overlap, matching anchor 4 ('mostly distinct; minor overlap risk'). Not 5 because it could still overlap with adjacent skills such as general bug-reporting triage or issue-editing/commenting skills; not 3 because the specificity of 'GitHub issue' + 'submit' + label conventions keeps it well above generic 'Works with document files' territory.

4 / 5

Total

15

/

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

QwenLM/qwen-code

Path

.qwen/skills/create-issue/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.