Install
$ agentstack add skill-0xrafasec-ai-workflow-adr ✓ 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
Create an Architecture Decision Record. Argument: $ARGUMENTS
Context
ADRs capture a single decision — the context, options considered, and the choice made. They're lightweight and accumulate over time. Each ADR is a separate numbered file.
Context Gathering
- Check
docs/adr/for existing ADRs — determine the next number. If no ADRs exist, start at0001. - Read recent ADRs (last 2-3) to match the project's style and voice.
- If the decision relates to architecture, read
docs/ARCHITECTURE.mdfor context.
Interview
Use AskUserQuestion to extract the decision. Keep it focused — an ADR is one decision, not a design doc.
- What's the decision? — What are you deciding? What triggered this decision?
- Context — What constraints, requirements, or pressures led to this? What's the current state?
- Options considered — What alternatives did you evaluate? What are the tradeoffs of each?
- Decision — What did you choose and why? What was the deciding factor?
- Consequences — What changes as a result? What are the known downsides you're accepting?
If the decision is straightforward (user already knows what they want and why), keep the interview to 1-2 questions to fill in gaps.
Write
Write to docs/adr/NNNN-.md:
# ADR-NNNN: [Title]
**Status:** Proposed | Accepted | Deprecated | Superseded by [ADR-XXXX]
**Date:** [date]
**Deciders:** [who was involved]
## Context
[What is the issue? What forces are at play? What constraints exist?]
## Decision
[What was decided. State it clearly in one sentence, then elaborate if needed.]
## Options Considered
### Option A: [Name]
- **Pros:** [benefits]
- **Cons:** [drawbacks]
### Option B: [Name]
- **Pros:** [benefits]
- **Cons:** [drawbacks]
### Option C: [Name] (if applicable)
- **Pros:** [benefits]
- **Cons:** [drawbacks]
## Consequences
### Positive
- [What improves]
### Negative
- [What gets harder or what risks are accepted]
### Neutral
- [What changes without clear positive/negative valence]
## Related
- [Links to related ADRs, specs, issues, or documents]
After Writing
- Present the ADR to the user for review.
- Ask if the status should be "Proposed" (needs team review) or "Accepted" (decided).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 0xrafasec
- Source: 0xrafasec/ai-workflow
- 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.