agentleFS
roborracleroborracle/agent-workflow-kit/skills/github-issues-manager/SKILL.md

github-issues-manager

Skill0 starsChanged 3 months agoMITView on GitHub

Automatically create GitHub issues for every quantifiable task during planning and development. Use when breaking down features, planning sprints, organizing work, or any time work needs to be tracked.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ensure every unit of work has a trackable GitHub issue with proper labels, acceptance criteria, and relationships.

    line 10
  2. Distinctive:

    When breaking down a feature into multiple issues:

    line 58
  3. Distinctive:

    One issue per deployable unit: - If it can be merged independently, it's one issue

    line 71
  4. Distinctive:

    Update, don't abandon: - If scope changes, update the issue

    line 74

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub Issues Manager

Ensure every unit of work has a trackable GitHub issue with proper labels, acceptance criteria, and relationships.

Issue Creation Protocol

Before creating issues, gather context:

gh repo view                    # Verify repository
gh milestone list               # Check existing milestones
gh label list                   # Review label taxonomy

For each quantifiable task, create an issue:

gh issue create \
  --title "[TYPE] Brief description" \
  --body "$(cat <<EOF
## Description
[What needs to be done]

## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3

## Context
[Why this is needed, related features]

## Technical Notes
[Implementation hints, gotchas]

## Related
- Depends on: #XX
- Blocks: #YY
- Part of: #ZZ
EOF
)" \
  --label "type/[TYPE]" \
  --label "priority/[P0|P1|P2]" \
  --label "area/[AREA]" \
  --milestone "[MILESTONE]"

Issue Types

Labels follow the taxonomy in rules/git-workflow.md § Label Taxonomy: every issue carries one type/* (type/feature, type/bug, type/chore, type/refactor, type/docs), one priority/* (priority/P0 blocking, priority/P1 high, priority/P2 medium/low), and at least one area/*. Run gh label list and reuse what exists.

Batch Issue Creation

When breaking down a feature into multiple issues:

# Create parent epic/feature issue first
PARENT=$(gh issue create --title "[feat] Feature Name" --body "..." --label "type/epic")

# Create child issues referencing parent
gh issue create --title "[feat] Subtask 1" --body "$(printf 'Part of %s\n\n...' "$PARENT")"
gh issue create --title "[feat] Subtask 2" --body "$(printf 'Part of %s\n\n...' "$PARENT")"

Rules

  1. One issue per deployable unit - If it can be merged independently, it's one issue
  2. Clear acceptance criteria - Anyone should verify completion
  3. Link everything - Issues, PRs, commits reference each other
  4. Update, don't abandon - If scope changes, update the issue
  5. Close with context - Note what was done when closing
  6. Create issues BEFORE starting implementation

Additional Resources

  • For issue creation templates (standard, epic, bug report), see templates/issue-template.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.