agentleFS
madeordinarymadeordinary/serel-memory/.agents/skills/decision-log/SKILL.md

decision-log

Skill1 starsChanged 17 days agoMITView on GitHub

Record an architectural, product, workflow, or operational decision. Use when the user asks to log a decision, create an ADR, or preserve decision rationale.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use product-brief, pre-mortem and 8 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.
  • erik-kroonSkill

    product-brief

    Turn conversation context, codebase findings, and product intent into a PRD-style brief without assuming a specific issue tracker. Use when the user wants a PRD, product brief, feature spec, or implementation-ready product artifact.

    Also in 3 projects that use this

  • Ingramradical235Skill

    pre-mortem

    Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.

    Also in 3 projects that use this

  • MicrosoftSkill

    retrospective

    Review how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.

    Also in 4 projects that use this

  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 3 projects that use this

  • HashiCorpSkill

    changelog

    Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Effective bank: if memory-bank.local/ exists (upstream Serel Memory development only), all memory-bank reads and writes below target it …

    line 10
  2. Distinctive:

    If the user hasn't already stated the decision, or the decision is not clear, ask: "What's the decision you want to record?"

    line 16
  3. Very specific:

    Read memory-bank/systemPatterns.md, memory-bank/techContext.md, memory-bank/decisionLog.md, and .rules for related context.

    line 17
  4. Very specific:

    Check docs/decisions/ for existing ADRs to determine the next sequential number.

    line 18
  5. Distinctive:

    Wait for confirmation before writing.

    line 60
  6. Very specific:

    When approved, save the ADR to docs/decisions/NNN-<slug>.md, where NNN is the next sequential number padded to 3 digits (e.g., …

    line 61
  7. Very specific:

    After writing, ask the user whether memory-bank/systemPatterns.md should be updated to reference this decision under "Key decisions."

    line 62
  8. Distinctive:

    Do not silently overwrite an existing ADR or decision-log entry.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 39 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.

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

Decision Log

Record a durable architectural or design decision in standard ADR (Architecture Decision Record) format: an ADR in docs/decisions/ and a short index entry in memory-bank/decisionLog.md. Use this when a decision is significant enough that future-you (or a future teammate) will want to know why it was made.

Effective bank: if memory-bank.local/ exists (upstream Serel Memory development only), all memory-bank reads and writes below target it instead of the tracked templates. See "Resolving the effective bank" in docs/workflow-contract.md.

Scope: resolve which bank this targets per "Resolving scope" in docs/workflow-contract.md — an optional --scope <path> argument selects a project bank when the repo configures scopes; otherwise the root bank, as always.

Workflow

  1. If the user hasn't already stated the decision, or the decision is not clear, ask: "What's the decision you want to record?"
  2. Read memory-bank/systemPatterns.md, memory-bank/techContext.md, memory-bank/decisionLog.md, and .rules for related context.
  3. Check docs/decisions/ for existing ADRs to determine the next sequential number. If the directory is missing, plan to create it, and create it only when the ADR is approved.
  4. Draft the ADR and a short memory-bank/decisionLog.md entry. Use this structure for the ADR:
# [NNN]. [Short imperative title — e.g., "Use Postgres for state, not SQLite"]

## Status

Proposed | Accepted | Deprecated | Superseded by [NNN]

[Who decided: proposed by <who>, or user-directed / user-approved — source and date when known.]

## Context

[What's the situation that's forcing this decision? What constraints are in play? Be specific about what's actually true today.]

## Decision

[What did we decide? Be definitive. "We will use X" not "We're considering X."]

## Alternatives considered

- **[Alternative A]**: [brief description and why it was rejected]
- **[Alternative B]**: [brief description and why it was rejected]

## Consequences

**Positive**:
- [what this decision enables or makes easier]

**Negative**:
- [what this decision costs us or makes harder]

**Neutral**:
- [side effects that aren't clearly good or bad but should be known]

## References

- [link to relevant code, doc, discussion, ticket]
  1. Show the proposed ADR and the proposed memory-bank/decisionLog.md index entry.
  2. Wait for confirmation before writing.
  3. When approved, save the ADR to docs/decisions/NNN-<slug>.md, where NNN is the next sequential number padded to 3 digits (e.g., 001-use-postgres-for-state.md). Add the short entry to memory-bank/decisionLog.md.
  4. After writing, ask the user whether memory-bank/systemPatterns.md should be updated to reference this decision under "Key decisions."

Rules

  • ADRs are for real decisions — ones with alternatives that were genuinely considered, or with meaningful future consequences. Don't ADR trivial things ("we use 2-space indents").
  • Status starts as "Proposed" unless the user directed or already approved the decision; being implemented is not approval. Only the user makes it "Accepted" — never accept your own suggestion, and don't ask again for approval already given (a user who changes a Proposed draft to Accepted in review has approved it). Record who decided in the ADR and the index entry (contract "Memory writes").
  • Alternatives section should be honest. If you didn't seriously consider others, say so — that's also useful context.
  • Consequences should be balanced. If you can't think of negatives, you probably haven't thought hard enough about the decision.
  • Do not silently overwrite an existing ADR or decision-log entry.

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.