creating-issues
Skill548 starsChanged 8 days agoApache-2.0View on GitHub
Turns a single feature idea, improvement, or bug into ONE well-structured GitHub issue. TRIGGER when: the user wants to file/open/create an issue, turn a feature idea or improvement into a ticket, or capture something missing or broken as a ticket. DO NOT TRIGGER when: breaking work into multiple issues or planning a body of work → a planning skill; writing a full Product Requirements Document → creating-prd; the idea is still fuzzy and unhardened → grilling-ideas first.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- h3y6e/agent-skillstheir own version, first seen Oct 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- h3y6e/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository54 other files it gives its agents.
- AGENTS.mdAGENTS.md
- backend/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- backend/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- analyzing-ci-flakinessSkill
- audit-docsSkill
- commitSkill
- creating-changelog-entriesSkill
- creating-prdSkill
- grilling-ideasSkill
- harvesting-reviewSkill
- migrate-feature-pageSkill
- monitoring-pull-requestsSkill
- neo4j-cypher-guideSkill
- opsmill-dev-analyzing-bugsSkill
- opsmill-dev-fixing-bugsSkill
- opsmill-dev-test-driving-bugsSkill
- pre-ciSkill
- prSkill
- rebaseSkill
- reviewing-pull-requestsSkill
- speckit-agent-context-updateSkill
- speckit-analyzeSkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-critique-runSkill
- speckit-git-commitSkill
- speckit-git-featureSkill
- speckit-git-initializeSkill
- speckit-git-remoteSkill
- speckit-git-validateSkill
- speckit-implementSkill
- speckit-opsmill-autoSkill
- speckit-opsmill-extractSkill
- speckit-opsmill-implementSkill
- speckit-opsmill-prepSkill
- speckit-opsmill-retrospectSkill
- speckit-opsmill-summarySkill
- speckit-planSkill
- speckit-review-codeSkill
- speckit-review-commentsSkill
- speckit-review-errorsSkill
- speckit-review-runSkill
- speckit-review-simplifySkill
- speckit-review-testsSkill
- speckit-review-typesSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
- upgrading-infrastructure-dependenciesSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Treat $ARGUMENTS as the thing to file.
- Distinctive: line 45
If the repo provides an issue template, honour its structure as-is — the fields are there deliberately.
- Distinctive: line 104
Create the issue with the available tooling, for example:
- Distinctive: line 116
Prefer clarity over completeness — a short, sharp issue beats a padded one.
- Distinctive: line 118
Don't invent labels, milestones, or assignees that don't exist in the repo.
- Distinctive: line 119
Don't smuggle a solution into the "Need" or "Context" — if you catch yourself describing *how*, cut it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create GitHub Issue
User Input
$ARGUMENTSTreat $ARGUMENTS as the thing to file. If empty, ask the user what they want to capture before starting.
What this does
Turn a feature idea, improvement, or bug into a single well-structured GitHub issue that matches the repository's own conventions. Keep it small and centred on the need — what is missing or broken, who it affects, and why it matters. Do not propose a solution and do not write acceptance criteria for features — leave the "how" to whoever picks the issue up. Always show the draft and get explicit approval before creating anything.
Core principle
An issue states the need, not the answer. The person (or agent) who implements it decides the approach. For a feature or improvement that means no design, no task breakdown, no acceptance criteria — just a clear problem and its context. For a bug, the "need" is the misbehaviour itself, so reproduction details belong in the issue.
Workflow
1. Learn the repository's conventions
Probe whatever context the repo actually provides — don't assume a fixed layout:
- Read context docs if present:
AGENTS.md,CLAUDE.md,CONTEXT.md,README, or adev/directory. - Check for issue templates in
.github/ISSUE_TEMPLATE/and honour them if they exist. - List the repo's labels (
gh label list) and a few recent issues (gh issue list) to match title style, labels, and tone.
If the repo provides an issue template, honour its structure as-is — the fields are there deliberately. The only thing to hold back is prescribing a solution: fill the template's sections with the need and context, not with a design.
2. Classify
Decide whether this is a feature / improvement or a bug. When unsure, ask the user.
3. Draft (need-focused)
Feature / improvement — keep it lean:
## Need
[What's missing or could be better, who it affects, and why it matters now.]
## Context
[Only what's needed to understand the need: relevant area of the product, links to related discussion, constraints. No design.]
## References
- Related issue: #[number]
- Documentation / discussion: [url]Bug — capture the misbehaviour:
## What happens
[Observed behaviour.]
## What should happen
[Expected behaviour.]
## Steps to reproduce
1. ...
2. ...
## Environment
[Version, OS, configuration, or other relevant context.]
## References
- Related issue: #[number]
- Logs / screenshots: [link or `<details>` block]Draft a clear, searchable title using the repo's convention (e.g. feat:, fix:, or whatever recent issues use), and pick labels from the repo's existing set.
4. Get approval, then create
By default, present the full draft (title, labels, body) to the user and wait for explicit approval before creating the issue — even when you have permission to create it directly. The gate exists to stop silent creation from mere permission; it is not meant to override a direct instruction.
If the user has explicitly told you to file it without review (e.g. "just file it, don't ask"), honour that — but still echo the final title, labels, and body in your reply before (or as) you create it, so there's a record of what went out.
Create the issue with the available tooling, for example:
gh issue create --title "[TITLE]" --body "[BODY]" --label "[LABELS]"--label takes a comma-separated list (--label 'bug,enhancement') — a space-separated value is treated as a single label name.
Or the equivalent GitHub MCP call. Return the issue URL.
Guardrails
- Prefer clarity over completeness — a short, sharp issue beats a padded one.
- Resist scope creep: one need per issue. If the input contains several, surface that and ask whether to split.
- Don't invent labels, milestones, or assignees that don't exist in the repo.
- Don't smuggle a solution into the "Need" or "Context" — if you catch yourself describing how, cut it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

