Install
$ agentstack add skill-siarhei-belavus-agent-public-prd-to-issues ✓ 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.
About
Your job is to convert a PRD into a set of well-scoped implementation issues that can be picked up independently.
The output should favor tracer-bullet vertical slices over broad horizontal phases. Each issue should produce visible progress, reduce risk, and leave the system in a coherent state.
Process
- Read the PRD carefully
Understand:
- the problem being solved
- the key user flows
- constraints and non-goals
- the highest-risk or least-certain parts
If the PRD path is not given explicitly, infer the PRD slug from the provided PRD artifact and use that slug consistently.
- Identify vertical slices
Break the work into slices that:
- are end-to-end where practical
- exercise meaningful user value early
- reduce uncertainty quickly
- can be validated independently
- avoid producing a pile of disconnected infrastructure work
Do not split work purely by layer such as backend/frontend/database unless that is genuinely the safest shape.
- Create issue files
Write issue files under:
.prd//issues/
Use ordered filenames:
.prd//issues/01-.md.prd//issues/02-.md
Create the issues/ directory if it does not exist.
- Write each issue
Each issue should use this structure:
#
## Parent PRD
.prd//prd.md
## Goal
What this slice delivers and why it exists.
## Scope
- In scope item 1
- In scope item 2
## Out of Scope
- Out of scope item 1
- Out of scope item 2
## Implementation Notes
- Important constraints
- Relevant modules or boundaries
- Risks or edge cases to watch
## Validation
- How to verify the slice works
- Tests, manual checks, or observability needed
## Dependencies
- Optional dependency on another issue or artifact
Keep each issue independently understandable. Avoid hidden assumptions that require rereading the full PRD to make progress.
5. Sequence the work
Order issues so that:
- the earliest slices reduce the most important uncertainty
- later slices build on proven capability
- the sequence is practical, not just conceptually neat
Call out explicit dependencies only when necessary.
6. Final response
In your final response:
- summarize how many issues were created
- list the created file paths
- briefly explain the sequencing logic
## Communication
Honor active caveman mode for user-facing replies per `../../references/communication-mode.md`. Keep durable artifacts normal unless the human asks otherwise. Drop caveman for safety/clarity when needed, then resume.
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [siarhei-belavus](https://github.com/siarhei-belavus)
- **Source:** [siarhei-belavus/agent-public](https://github.com/siarhei-belavus/agent-public)
- **License:** MIT
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.