Install
$ agentstack add skill-pekral-cursor-rules-create-issues-from-text ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Create Issues from Text
Purpose
Split a complex assignment into multiple clear, structured issues.
Constraints
- Preserve original assignment (store in parent or first issue)
- Do not implement code
- Assign all issues to current user
- Use CLI tools
Execution
1. Analyze Assignment
- Understand scope and dependencies
- Identify logical implementation steps
2. Propose Breakdown
- List steps with short descriptions
- Proceed directly to step 3; do not gate on a confirmation round when the breakdown is unambiguous
3. Create Issues
- One issue per step
- Ensure each is independently deliverable
4. Output
- Return list of created issues with URLs
Issue Structure
Use the template defined in templates/issue-structure.md.
EPIC parent & sub-issues
Use this when the assignment is a cross-cutting mix of requirements spanning multiple parts of the application (e.g. backend + frontend + mobile, or schema + API + UI). Instead of a flat list of peer issues, build a parent → children tree so the whole effort is trackable from one place.
- Pick (or create) the parent. When the assignment already has a tracker item, that item becomes the EPIC parent. When the assignment is a described task with no tracker item, create the parent issue first, carrying the full original assignment in its body.
- Label the parent
EPIC. Apply theEPIClabel to the parent. Create the label once if the repository does not have it yet (gh label create EPIC --description "Tracks a cross-cutting effort split into sub-issues" --color 5319e7), then ignore the "already exists" outcome on subsequent runs. - Create one sub-issue per application area. Each sub-issue is an independently deliverable assignment (same
templates/issue-structure.mdstructure) scoped to a single area; do not bundle two areas into one sub-issue. - Link every sub-issue back to the parent (both directions).
- In each sub-issue body, reference the parent with
Part of #so the relationship is visible from the child. - In the parent body, keep a checkable task list of the children —
- [ ] #per sub-issue — under a## Sub-issuesheading, so the parent shows the full breakdown and progress.
- Order. Fill each sub-issue's
## Dependenciesso a resolving run (e.g.daidalos) can pick a dependency-aware order — dependencies before dependents. - Output. Return the
EPIC-labelled parent URL plus the list of linked sub-issue URLs and the planned resolve order.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: pekral
- Source: pekral/cursor-rules
- License: MIT
- Homepage: https://pekral.cz
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.