Skip to content
Agentmart
Submit a tool

adr

Capture qualifying architecture decisions as ADRs in the right HQ or repo location.

Skill by indigoai-us

IndexedMIT
Write a review

Chalk Labs

Need help deploying adr?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/indigoai-us-adr

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.

We use your email only for this newsletter. Privacy

About

Capture qualifying architecture decisions as ADRs in the right HQ or repo location.

No 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

Tools it pre-approves 7

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Grep,
  • Glob,
  • Bash,
  • Write,
  • Edit,
  • AskUserQuestion

What's inside

Skill name
adr
Description
Capture qualifying architecture decisions as ADRs in the right HQ or repo location.
License
MIT
Allowed tools
Read,, Grep,, Glob,, Bash,, Write,, Edit,, AskUserQuestion
Instructions
164 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# ADR

Architectural Decision Records — minimal, dated, sequentially numbered. The point is recording **that** a decision was made and **why**, not filling out template sections.

Pattern adapted from `mattpocock/skills` (`grill-with-docs/ADR-FORMAT.md`).

## Step 0 — Resolve company + scope

`$ARGUMENTS` may include:

- `[company]` slug — fall back to manifest / handoff / cwd inference if absent
- `[repo|hq]` scope — pick home directory
- `<one-line decision summary>` — used as title and slug seed

If scope is ambiguous, ask via `AskUserQuestion`:

| Choice | Home | When |
|---|---|---|
| `repo` | `<repo>/docs/adr/` | Decision is bound to specific code; reviewers will read it alongside the code |
| `hq` | `companies/{co}/knowledge/adrs/` | Decision is org-level (e.g. "we use Linear, not Jira"; "all auth via Cognito") |

If no company resolves and scope is `hq`, default to `core/knowledge/public/adrs/` (rare — most ADRs have a tenant).

## Step 1 — Three-condition gate (HARD BLOCK)

Ask the user three yes/no questions via a single `AskUserQuestion` call:

1. **Hard to reverse** — would changing your mind later cost meaningful effort? (refactor, migration, contract renegotiation)
2. **Surprising without context** — would a future reader look at the result and wonder "why on earth did they do it this way?"
3. **Result of a real trade-off** — were there genuine alternatives, and did you pick this one for specific reasons?

If **any** answer is no → DO NOT WRITE THE ADR. Offer alternatives:

| Failed condition | Alternative |
|---|---|
| Easy to reverse | Skip — you'll just reverse it later |
| Not surprising | Skip — nobody will wonder |
| No real trade-off | Add to `GLOSSARY.md` glossary instead, or skip |

Re-prompt: "Skip ADR / Add to GLOSSARY.md / Force-write anyway (rarely correct)". Only `Force-write` proceeds; record reasoning in the ADR body so the override is explicit.

## Step 2 — Locate or create target directory

```bash
# repo scope
mkdir -p <repo>/docs/adr/

# hq scope
mkdir -p companies/{co}/knowledge/adrs/
```

Lazy-create only when the first ADR is needed.

## Step 3 — Compute next number

```bash
ls <target>/[0-9][0-9][0-9][0-9]-*.md 2>/dev/null \
  | sed 's|.*/\([0-9]*\)-.*|\1|' \
  | sort -n \
  | tail -1
```

Increment by 1. Default to `0001` if no existing ADRs. Format: `NNNN` (4-digit zero-padded).

Slug from the user's title:

- Lowercase
- Spaces / underscores → `-`
- Strip non-alphanumeric except `-`
- Cap at 60 chars

Final filename: `NNNN-slug.md`

## Step 4 — Walk the user through 1–3 sentences

Single `AskUserQuestion` (or sequential prompts) collecting:

- **Title** — short noun phrase, sentence case, ≤60 chars
- **Body** — 1–3 sentences answering: what's the context, what did we decide, why this over alternatives

That's the minimum. The value is in *recording* the decision, not in completing a template.

## Step 5 — Optional sections (offer, don't force)

Ask via `AskUserQuestion` (multiSelect) which (if any) to include:

- **Status frontmatter** (`proposed | accepted | deprecated | superseded by ADR-NNNN`) — useful when decisions are likely to be revisited
- **Considered Options** — only when rejected alternatives are worth remembering
- **Consequences** — only when non-obvious downstream effects need calling out

If user picks none, the ADR is just title + 1–3 sentences. Good.

## Step 6 — Write ADR

Template (use only the sections selected in Step 5):

```markdown
---
status: <accepted|proposed|...>          # only if Status was selected
date: <YYYY-MM-DD>
related: []                              # ADR numbers, optional
---

# <Title>

<1-3 sentences: context, decision, why.>

## Considered Options                    <!-- optional -->

- <Option A> — <why rejected>
- <Option B> — <why rejected>

## Consequences                          <!-- optional -->

- <non-obvious downstream effect>
```

## Step 7 — Cross-link

From indigoai-us/hq-pack-core-skills, MIT.

More from indigoai-us/hq-pack-core-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from indigoai-us

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get adr running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying adr?

CallGet help
Cite this page

adr skill. Agent Mart. https://agentmart.dev/skills/indigoai-us-adr (last updated 2026-10-24)