adr
Skill17 starsChanged 50 days agoMITView on GitHub
Write Architecture Decision Records following HikmaAI format. Use when user says write ADR, architecture decision, ADR, or decision record. Orchestrates refinement, research, writing, vault storage, and review. Not for implementation plans (use plan mode) or retrospectives (use learning-docs).
- Commits and pushes
90 other projects use a version of this.
Adopted by
Most recently taken up by
- GustavoAlecio/claude-setuptheir own version, first seen Nov 8, 2026
- computerlovetech/skillstheir own version, first seen Nov 8, 2026
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- axodouble/skillstheir own version, first seen Nov 8, 2026
- RodrigoAnciaes/golem-sddtheir own version, first seen Nov 8, 2026
- n1kben/agentstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use fdr, runbook and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
thiagofgfSkillfdr
Use when creating, changing, reviewing, retiring, auditing, or backfilling implemented user-visible feature behavior, permissions, feature-specific rationale, tradeoffs, or relationships to architectural decisions.
Also in 3 projects that use this
AnthropicSkillrunbook
Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.
Also in 5 projects that use this
drewdrewthisSkillsweep
Search for similar patterns, anti-patterns, or issues elsewhere in the codebase after a fix or feature. Use after implementing a fix to catch the same bug in other places, or proactively to audit for a known pattern.
Also in 4 projects that use this
vndeeSkillproduct-spec
Use when starting a new feature, product, or project — before any architecture or code, to define what to build and why
Also in 3 projects that use this
OpenAISkillthreat-model
Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Also in 6 projects that use this
montymiSkilltech-spec
Parse and review Technical Specification documents for completeness, consistency, and implementation readiness
Also in 3 projects that use this
Other versions90 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 90
- CrowdDotDev/crowd.dev★ 3.4ksame name
- chattocorp/chatto★ 2.9ksame name
- Cosmian/kms★ 372same name
- linuxfoundation/insights★ 288same name
- rvdbreemen/OTGW-firmware★ 213same name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- irahardianto/awesome-agv★ 157same name
- jellydn/my-ai-tools★ 127same name
- EmeaAppGbb/spec2cloud★ 100same name
80 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- android-kotlinSkill
- apple-swiftSkill
- autoresearch-promptSkill
- blog-writerSkill
- cloud-infrastructureSkill
- commitSkill
- cover-imageSkill
- freezeSkill
- gemini-reviewSkill
- golangSkill
- harness-mechanicSkill
- harness-traceSkill
- humanizerSkill
- ios-debuggerSkill
- knowledge-syncSkill
- learning-docsSkill
- learning-loopSkill
- obsidianSkill
- orchestratorSkill
- plan-forgeSkill
- process-clippingsSkill
- project-analyzerSkill
- project-checksSkill
- pr-reviewSkill
- pythonSkill
- railsSkill
- react-nextjsSkill
- refine-requirementsSkill
- releasing-softwareSkill
- rubySkill
- scoreSkill
- second-opinionSkill
- skill-forgeSkill
- source-controlSkill
- terraformSkill
- test-design-reviewerSkill
- verify-frontendSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 4 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 75 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Every claim should be backed by evidence (code, docs, benchmarks)
- Distinctive: line 15
Do not skip the refinement step for ambiguous topics
- Very specific: line 21
Before writing, clarify scope using AskUserQuestion:
- Distinctive: line 45
The Linear ticket number IS the ADR number: No separate counter. Gaps in numbering are expected.
- Very specific: line 47
Before calling any mcp__linear-server__* tool (here and in Step 10), verify it exists in the current session.
- Very specific: line 80
Follow the HikmaAI ADR format exactly (full section-by-section template in references/adr-format.md).
- Very specific: line 84
Add a row to the ADR Index table in hikma-system-design/README.md:
- Very specific: line 90
If the README's Conventions section gives an ADR filename pattern other than ADR-NNN-kebab-title.md, update it to match.
- Very specific: line 105
Run dx-reviewer agent on the ADR file, focusing on:
- Very specific: line 162
Update ADR status to Status: Accepted (follow-up commit or part of next PR)
- Distinctive: line 195
No em dashes; use commas, colons, semicolons, or parentheses
“Common” is measured: kept by at least 6 in 10 of the 75 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ABOUTME: Full ADR lifecycle: Linear ticket, branch, write, vault, review, commit, PR
ABOUTME: Follows HikmaAI format and ADR guidelines (Linear ticket = ADR number)
Architecture Decision Records
Quality Notes
- ADRs are permanent records; accuracy matters more than speed
- Every claim should be backed by evidence (code, docs, benchmarks)
- Do not skip the refinement step for ambiguous topics
Workflow
Step 1: Refine Requirements
Before writing, clarify scope using AskUserQuestion:
- What decision is being made? (single clear question)
- What options are on the table?
- What constraints apply?
- Who are the stakeholders?
Skip if user provided a fully specified request or said "just write it."
Step 2: Research
Launch research-analyst agent to gather:
- Prior art (existing ADRs in vault, LEARNING.md, MEMORY.md)
- External references (competing approaches, industry patterns)
- Current codebase state (relevant files, existing patterns)
For HikmaAI projects, always check:
- Vault:
Projects/HikmaAI/HLD/for existing ADRs - CLAUDE.md for architecture context
- Relevant source code for current implementation
Step 3: Create Linear Ticket (reserves the ADR number)
The Linear ticket number IS the ADR number. No separate counter. Gaps in numbering are expected.
Before calling any mcp__linear-server__* tool (here and in Step 10), verify it exists in the current session; MCP tool names change, so fall back to the Linear web UI if it is absent.
mcp__linear-server__save_issue:
title: "ADR: {Decision Title}"
team: "Hikmaai"
project: "ADR Lifecycle"
state: "In Progress"
assignee: "me"
priority: 2 (or as appropriate)
description: "One-line summary.\n\nRepo: hikma-system-design\nBranch: adr/{NNN}-{kebab-title}"Note the ticket identifier (e.g., HIK-249): the numeric part (249) is the ADR number.
Step 4: Create Branch
cd ~/Development/hikmaAI/hikma-system-design
git checkout -b adr/{NNN}-{kebab-title} mainExample: adr/249-mirsad-cryptographic-decision-trail
Step 5: Write the ADR
- Copy
adr/TEMPLATE.mdtoadr/ADR-{NNN}-{kebab-title}.md - Fill in all sections following the template guidance
- Set frontmatter fields:
**Status:** Drafting**Linear:** [HIK-{NNN}](https://linear.app/hikmaai/issue/HIK-{NNN})**Obsidian:** [[{NNN}-{kebab-title}]]
Follow the HikmaAI ADR format exactly (full section-by-section template in references/adr-format.md).
Step 6: Update README.md
Add a row to the ADR Index table in hikma-system-design/README.md:
| {NNN} | {project} | {Title} | Drafting |If the README's Conventions section gives an ADR filename pattern other than ADR-NNN-kebab-title.md, update it to match.
Step 7: Store in Vault
Save using the obsidian skill:
obsidian create name="Projects/HikmaAI/HLD/ADR-{NNN}-{Title}" content="..." silentFallback (direct file access):
Write to /Users/maroffo/Library/Mobile Documents/iCloud~md~obsidian/Documents/Projects/HikmaAI/HLD/ADR-{NNN}-{Title}.md
Step 8: Review
Run dx-reviewer agent on the ADR file, focusing on:
- Completeness (all sections present)
- Clarity (decisions unambiguous)
- Evidence (claims backed by data/code)
- Actionability (enough detail to implement)
This launch cannot pass isolation: "worktree": the ADR file is still uncommitted here (Step 9 commits it), and a reviewer worktree materialises at the default branch, where the file does not exist. Open the brief with the first line ISOLATION-EXEMPT: ADR review, the target file is uncommitted and the reviewer only reads it, which is what reviewer-isolation-guard reads; the reviewer then stays read-only agent-side, which is all this step wants.
Alternatively, if the ADR is short and straightforward, skip the agent and self-review against the checklist above.
Step 9: Commit, Push, PR
Commit:
git add adr/ADR-{NNN}-{kebab-title}.md README.md [any other changed files]
git commit -m "docs: ADR-{NNN} {Title} (HIK-{NNN})
{One-line summary of the decision.}
Co-Authored-By: Claude <model> <noreply@anthropic.com>"Replace <model> with the current model name (e.g. the model running this session); do not hardcode a specific version.
Push + PR:
git push -u origin adr/{NNN}-{kebab-title}
gh pr create \
--title "ADR-{NNN}: {Title}" \
--body "## Summary
- **ADR-{NNN}**: {Decision summary}
**Linear:** [HIK-{NNN}](https://linear.app/hikmaai/issue/HIK-{NNN})
## Test plan
- [ ] Review ADR content for technical accuracy
- [ ] Verify README index entry
🤖 Generated with [Claude Code](https://claude.com/claude-code)"Step 10: Update Linear Status
Move the ticket to "In Review" and attach the PR link:
mcp__linear-server__save_issue:
id: "HIK-{NNN}"
state: "In Review"
links: [{"url": "{PR_URL}", "title": "PR: ADR-{NNN}"}]After Merge (manual or automated)
- Move Linear ticket to Done:
state: "Done" - Update ADR status to
**Status:** Accepted(follow-up commit or part of next PR) - GitHub Action syncs to Notion automatically
ADR Status Lifecycle
| Status | Linear State | Meaning |
| Proposed | Todo | Number reserved, idea captured |
| Drafting | In Progress | ADR being written on feature branch |
| In Review | In Review | PR opened, team reviewing |
| Accepted | Done | PR merged, decision final |
| Superseded | Canceled | Replaced by a newer ADR (link to successor) |
Numbering
| Rule | Detail |
| Source | Linear ticket number (NNN from HIK-NNN) |
| Legacy ADRs | 001-032 keep their original numbers |
| New ADRs | Use the Linear ticket number (249, 250, ...) |
| Gaps | Expected and acceptable (rejected ADRs consume a number) |
| Immutable | Once assigned, the number never changes regardless of status |
Naming Conventions
| Element | Convention | Example |
| Filename | ADR-NNN-kebab-title.md | ADR-249-mirsad-cryptographic-decision-trail.md |
| Branch | adr/NNN-kebab-title | adr/249-mirsad-cryptographic-decision-trail |
| Linear ticket | ADR: Title | ADR: Mirsad Cryptographic Decision Trail |
Style Rules
- No em dashes; use commas, colons, semicolons, or parentheses
- Tables for structured comparisons (always)
- Code blocks for API schemas, configs, deployment patterns
- Bold for core decisions and key terms
---horizontal rules between major parts- ASCII diagrams for architecture flows (no Mermaid in ADRs)
Anti-patterns
| Bad | Good |
| "We should probably..." | "Decision: X. Rationale: ..." |
| Options without trade-offs | Each option with pros/cons |
| Vague consequences | Specific, testable outcomes |
| Missing context | Name the trigger explicitly |
| Monolithic wall of text | Parts + tables + code blocks |
| Time estimates in ADR | Phases with dependencies only |
| Manual ADR numbering | Linear ticket = ADR number |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

