adr-writer
MADR-format Architectural Decision Records: context, decision drivers, considered options with pros/cons, decision outcome, consequences, and the supersedes…
Skill by Cloud-Byte-Consulting
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cloud-byte-consulting-adr-writer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adr-writer
What's inside
- Skill name
adr-writer- Description
- MADR-format Architectural Decision Records: context, decision drivers, considered options with pros/cons, decision outcome, consequences, and the supersedes chain. Use when documenting or proposing design decisions in docs/research/platform-catalyst-agents-evaluation.md or docs/ADR/.
- License
- BSD-3-Clause
- Instructions
- 109 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
<!-- Vendored from: platform-catalyst/skills/adr-writer/SKILL.md (BittahCriminal/platform-catalyst, BSD-3-Clause). Adapted for Catalyst: PLAN.md/CLAUDE.md/DECISIONS.md scrubbed; ADR-008->ADR-001, ADR-009->ADR-002. -->
## Role
ADR author for the Catalyst IDP. You draft, review, and maintain Architectural
Decision Records that serve as institutional memory for the platform. Per
Platform Engineering for Architects Ch 9, ADRs are "documents for the
afterworld" — they capture the why behind decisions so future maintainers
(and interview evaluators) understand the reasoning without archaeology.
## Instructions
### MADR structure
Every ADR follows this template:
```markdown
## ADR-{NNN}: {Title}
**Status:** Proposed | Accepted | Deprecated | Superseded by ADR-{NNN}
### Context
What is the issue that we are seeing that motivates this decision or change?
State the forces at play (technical, business, compliance, operational).
### Decision Drivers
- {driver 1}: one-line description
- {driver 2}: one-line description
- {driver 3}: one-line description
### Considered Options
1. **{Option A}**
- Pro: {benefit}
- Pro: {benefit}
- Con: {drawback}
2. **{Option B}**
- Pro: {benefit}
- Con: {drawback}
- Con: {drawback}
3. **{Option C}** (if applicable)
- Pro: {benefit}
- Con: {drawback}
### Decision Outcome
Chosen option: **{Option X}**, because {one-sentence justification linking
back to the decision drivers}.
### Consequences
- **Positive:** {what improves}
- **Negative:** {what gets harder or is deferred}
- **Neutral:** {what stays the same but is worth noting}
### Links
- Supersedes: ADR-{NNN} (if applicable)
- Related: ADR-{NNN}, {external URL}
```
### Existing ADR chain
Canonical ADR files live under `docs/ADR/` in this repository. New ADRs must:
- Use the next sequential number based on the current highest `ADR-XXX` file in `docs/ADR/`.
- Reference related existing ADRs in the Links section.
- If superseding an existing ADR, update the superseded ADR's status to
"Superseded by ADR-{NNN}" in the same PR.
### Superseding pattern
When a decision changes:
1. Do not delete or edit the body of the original ADR.
2. Update only the **Status** line of the original to "Superseded by ADR-{NNN}."
3. The new ADR's Context section must explain what changed since the original
decision.
4. The new ADR's Links section must include "Supersedes: ADR-{NNN}."
### Writing quality
- Context section: 3-5 sentences. State the problem, not the solution.
- Decision Drivers: 2-4 drivers, each one line.
- Considered Options: 2-3 options minimum. Include the "do nothing" option
when it is a viable choice.
- Decision Outcome: one sentence. If it takes more, the decision is not clear.
- Consequences: at least one positive and one negative. Honest negatives build
credibility.
## Output
- Complete MADR-format ADR ready to append to `docs/research/platform-catalyst-agents-evaluation.md` or place in
`docs/ADR/` as a standalone file.
- Updated status line for any superseded ADR.
- One-line summary suitable for a **`type/kaizen`** GitHub Issue body (and optional markdown archive mirror if the repo has one).
## Guardrails
- Never delete or substantively edit a previously accepted ADR. Supersede it.
- Never write an ADR without at least two considered options.
- Never omit negative consequences. Every decision has trade-offs.
- Never use an ADR to document implementation details. ADRs capture the why
and the what, not the how.
- Never propose an ADR that contradicts an existing accepted ADR without
explicitly superseding it.From Cloud-Byte-Consulting/Catalyst, BSD-3-Clause.
More from Cloud-Byte-Consulting/Catalyst
- 0.474score
bedrock-converse-client
Cloud-Byte-Consulting
Bedrock runtime Converse/ConverseStream API patterns: message structure, model ID selection, token limits, system prompts, retry with tenacity, error…
SkillCFreshness: CClaude Code +9 - 0.474score
ai-output-validation
Cloud-Byte-Consulting
Pydantic v2 schemas for AI model responses: FindingsReport, StyleReport, SynthesisReport, the parse-retry-drop pattern, confidence scoring, and structured…
SkillCFreshness: CClaude Code +9 - 0.474score
bedrock-binding
Cloud-Byte-Consulting
Bedrock model binding for the Catalyst PR reviewer pipeline, surfaced as a thin stdio MCP server with two tools: bedrock_invoke_converse and…
SkillCFreshness: CClaude Code +9 - 0.474score
fastapi-control-plane
Cloud-Byte-Consulting
FastAPI service patterns for catalyst-api: router organization, pydantic v2 request/response models, construct-scoped path design, IAM auth middleware…
SkillCFreshness: CClaude Code +9 - 0.474score
git-commit-practices
Cloud-Byte-Consulting
Git commit and branch practices for Catalyst that satisfy the challenge's "good Git practices" requirement and the 10% docs/commit-history evaluation…
SkillCFreshness: CClaude Code +9 - 0.474score
async-orchestration
Cloud-Byte-Consulting
Event-driven orchestration patterns for Catalyst: SQS FIFO with dedup, EventBridge rules and schedules, DLQ strategies, Step Functions state machines, retry…
SkillCFreshness: CClaude Code +9 - 0.474score
ai-observability
Cloud-Byte-Consulting
Observability for Bedrock AI calls: EMF metrics (BedrockTokensIn, BedrockTokensOut, BedrockLatencyMs), X-Ray subsegments per model call, cost dimension…
SkillCFreshness: CClaude Code +9 - 0.474score
checkov-cloud-image-static-analysis
Cloud-Byte-Consulting
Designs Checkov-based static analysis for Terraform/OpenTofu IaC and Dockerfile/container hardening in Catalyst.
SkillCFreshness: CClaude Code +9 - 0.474score
clean-python-code
Cloud-Byte-Consulting
Maintainable Python for Catalyst: tooling discipline, idiomatic patterns, separation of concerns, SOLID boundaries, thin decorators, pragmatic use of advanced…
SkillCFreshness: CClaude Code +9 - 0.474score
container-hardening
Cloud-Byte-Consulting
Multi-stage Dockerfiles, distroless final images, non-root USER, read-only root filesystem, health checks, no :latest tags, vulnerability scanning, and ECS…
SkillCFreshness: CClaude Code +9 - 0.474score
deployment-strategies
Cloud-Byte-Consulting
Blue/green ECS via CodeDeploy, Lambda weighted alias shifting (canary), rollback triggers (alarm-based), pre/post traffic hooks, bake periods, and the…
SkillCFreshness: CClaude Code +9 - 0.474score
devsecops-integration
Cloud-Byte-Consulting
Shift-left security in Catalyst's CI/CD pipelines: SBOM generation, dependency scanning (pip-audit, npm audit, govulncheck), secret scanning (gitleaks…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 57
- Last commit (this folder)
- May 21, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- BSD-3-Clause
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Cloud-Byte-Consulting
- 0.474score
clean-python-code
Cloud-Byte-Consulting
Maintainable Python for Catalyst: tooling discipline, idiomatic patterns, separation of concerns, SOLID boundaries, thin decorators, pragmatic use of advanced…
SkillCFreshness: CClaude Code +9 - 0.474score
bedrock-binding
Cloud-Byte-Consulting
Bedrock model binding for the Catalyst PR reviewer pipeline, surfaced as a thin stdio MCP server with two tools: bedrock_invoke_converse and…
SkillCFreshness: CClaude Code +9 - 0.474score
ai-output-validation
Cloud-Byte-Consulting
Pydantic v2 schemas for AI model responses: FindingsReport, StyleReport, SynthesisReport, the parse-retry-drop pattern, confidence scoring, and structured…
SkillCFreshness: CClaude Code +9 - 0.474score
ai-observability
Cloud-Byte-Consulting
Observability for Bedrock AI calls: EMF metrics (BedrockTokensIn, BedrockTokensOut, BedrockLatencyMs), X-Ray subsegments per model call, cost dimension…
SkillCFreshness: CClaude Code +9 - 0.474score
checkov-cloud-image-static-analysis
Cloud-Byte-Consulting
Designs Checkov-based static analysis for Terraform/OpenTofu IaC and Dockerfile/container hardening in Catalyst.
SkillCFreshness: CClaude Code +9 - 0.474score
container-hardening
Cloud-Byte-Consulting
Multi-stage Dockerfiles, distroless final images, non-root USER, read-only root filesystem, health checks, no :latest tags, vulnerability scanning, and ECS…
SkillCFreshness: CClaude Code +9
Cite this page
adr-writer skill. Agent Mart. https://agentmart.dev/skills/cloud-byte-consulting-adr-writer (last updated 2026-10-24)