Install
$ agentstack add skill-vijayjoshi24-ea-agent-skills-adr-writer ✓ 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
ADR Writer
Capture architectural decisions as durable, structured ADRs. A decision not documented is a decision that will be re-litigated — usually at the worst moment.
Step 1 — Extract the Decision Context
From the user's description, identify:
- The decision — what was chosen or what needs to be chosen
- The context — what forces, constraints, and requirements drove this
- The options — what alternatives were considered (ask if not provided)
- The deciders — who made or will make this call
- The consequences — what becomes easier, harder, or different as a result
If the user is still deliberating (hasn't decided yet), run the options comparison in Step 2 first, then write the ADR once they confirm a direction.
Step 2 — Options Comparison (when deciding)
If the user has multiple options to evaluate, produce a comparison table:
| Criterion | Option A | Option B | Option C | |---|---|---|---| | Fit for use case | | | | | Operational complexity | | | | | Team skill match | | | | | Cost | | | | | Vendor/lock-in risk | | | | | Time to implement | | | | | Verdict | | | |
Score each cell: ✅ Strong / ⚠️ Acceptable / ❌ Weak End with a clear recommendation and one-sentence rationale.
Step 3 — Write the ADR
Use this exact format. Do not skip sections.
# ADR-NNN: {Concise title — what was decided, not just the topic}
**Date:** {YYYY-MM-DD}
**Status:** Proposed | Accepted | Deprecated | Superseded by ADR-NNN
**Deciders:** {names or roles}
**Tags:** {technology | pattern | platform | integration | security}
## Context
{What situation, constraint, or requirement makes this decision necessary?
What would happen if we made no decision? 2–4 sentences max.}
## Decision
{Active voice: "We will adopt / use / implement / reject..."
State the decision unambiguously in 1–2 sentences.}
## Options considered
| Option | Summary | Key trade-off |
|--------|---------|---------------|
| {A} | | |
| {B} | | |
## Consequences
### Positive
- {What becomes easier, faster, or safer}
### Negative
- {What becomes harder, more constrained, or more expensive}
### Risks and mitigations
| Risk | Likelihood | Mitigation |
|------|-----------|------------|
## Related decisions
- Supersedes: —
- Related to: —
- Enables: —
Step 4 — File Placement Guidance
Tell the user where to save the ADR:
docs/decisions/ADR-NNN-{kebab-case-title}.md
Offer to auto-increment the ADR number if they share their existing ADR list.
Quality Gate
- [ ] Title states the decision, not just the topic ("Use Azure Service Bus" not "Message Queue Selection")
- [ ] Context explains why a decision was needed, not just what options exist
- [ ] Decision is in active voice and unambiguous
- [ ] At least 2 options listed in the table, even if one was quickly eliminated
- [ ] Both positive and negative consequences present — no ADR has only upsides
- [ ] Status field is set
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: vijayjoshi24
- Source: vijayjoshi24/ea-agent-skills
- 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.