agentleFS
Sign inStart free
timdevaitimdevai/proteus/skills/decision-recorder/SKILL.md

decision-recorder

Skill1 starsChanged 5 months agoMITView on GitHub

When you say "we decided to go with X over Y," this skill writes an ADR (Architecture Decision Record) so you don't have to remember why six months later. Trigger phrases: we decided, go with, chose, picked X over Y, let's settle on, final answer. Listen passively during planning conversations. When a real decision is reached, surface: "Save this as an ADR?" /adr [decision summary] — manually trigger an ADR for a decision the model may have missed. Conversation: User:…

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask "Save as ADR-NNNN-<slug>.md?"

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

decision-recorder

When you say "we decided to go with X over Y," this skill writes an ADR (Architecture Decision Record) so you don't have to remember why six months later.

When to activate

Trigger phrases: we decided, go with, chose, picked X over Y, let's settle on, final answer.

Listen passively during planning conversations. When a real decision is reached, surface: "Save this as an ADR?"

Output template (Michael Nygard format, lightly modified)

# ADR-NNN: <Decision title>

Date: <YYYY-MM-DD>
Status: Accepted | Superseded by ADR-NNN | Deprecated

## Context
<What forces led to this decision? 2-4 sentences.>

## Decision
<One-paragraph statement of what we're doing.>

## Alternatives considered
- <Option A>: <why not>
- <Option B>: <why not>
- <Option C>: <why not — if any>

## Consequences

### Positive
- <good thing>
- <good thing>

### Negative
- <real tradeoff>
- <real tradeoff>

### Neutral
- <thing that just is>

Numbering

  • Find existing docs/adr/ (or docs/decisions/, architecture/decisions/)
  • Auto-number the next file: ADR-0001, ADR-0002, etc.
  • Filename: docs/adr/ADR-NNNN-<slug>.md

Process

  1. Detect decision moment from conversation
  2. Extract: context, decision, alternatives mentioned, tradeoffs
  3. Generate draft ADR
  4. Ask "Save as ADR-NNNN-<slug>.md?"
  5. On approval, write the file
  6. Suggest committing it via commit-curator

Inputs

  • Conversation context where decision was made
  • Existing docs/adr/ (for numbering)

Outputs

  • New ADR file
  • ADR number used

Slash command

/adr [decision summary] — manually trigger an ADR for a decision the model may have missed.

Example

Conversation:

User: should we use Postgres or DynamoDB? Claude: <analysis>... User: ok let's go with Postgres, the relational queries we need outweigh the scaling concerns Skill: Detected decision. Drafting ADR-0007: "Use Postgres as primary datastore." (shows draft) User: y Skill: Wrote docs/adr/ADR-0007-postgres-primary-datastore.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free