Get the FREE Ultimate OpenClaw Setup Guide →

decision-lens

Scanned
npx machina-cli add skill WE3io/lightweight-ai-development-agent-skills/decision-lens --openclaw
Files (1)
SKILL.md
3.6 KB

Decision Lens

Overview

Surface potential decisions early by spotting patterns that may constrain future options. Provide neutral, brief signals only. When a decision is intentionally recorded, it is expected to exist as a standalone decision artefact (one decision per artefact), not as an entry in a shared or append-only file.

Workflow

  1. Discovery first

    • Inspect the repository for existing decision-record conventions (e.g., docs/adr/, architecture decision files, historical patterns).
    • If conventions exist, align to them.
    • If none exist, propose a minimal default (e.g., docs/adr/ with one file per decision) as a suggestion only, and ask for confirmation before creating anything.
  2. Scan for decision signals

    • Changes to public interfaces or APIs
    • Persistent data or schema changes
    • Coupling that constrains future changes
    • Irreversible or long-lived technology choices
    • Avoid flagging stylistic changes, refactors that preserve contracts, or purely local implementation details.
  3. Classify neutrally

    • Describe what appears to be changing.
    • Avoid judging quality or correctness.
    • Avoid recommendations unless asked.
  4. Surface the signal

    • Use phrasing like: “This might be a decision because…”
    • If nothing stands out, say so plainly.
  5. Mode and persistence

    • Ephemeral mode (default): surface the decision signal only; no files are written.
    • Persistent mode (opt-in): draft a minimal decision artefact stub when explicitly requested.
    • Never persist automatically or append decisions to shared logs like DECISIONS.md.
  6. Optional decision artefact prompt

    • If appropriate, suggest capturing the decision in a standalone artefact.
    • Optionally draft a stub with:
      • Context
      • Decision question (not the answer)
    • Default template (use only if no repository format exists):
      • ADR <number>: <title>

      • Context

      • What problem or decision is being addressed?
      • Decision

      • What is the decision being made?
      • Consequences

      • What are the tradeoffs and follow-on effects?
    • The template is a default, not mandatory; align to existing ADR formats when present and do not auto-number.
  7. Stop cleanly

    • Present the decision signal (if any) and why it appears decision-like.
    • If the human explicitly defers recording, acknowledge and stop without revisiting.
    • Pause and await instruction to persist, revise, or discard.
    • Do not follow up or persist state.

Output format

Return a brief advisory assessment with one of:

  • No decision signal detected.
  • Possible decision detected:
    • What appears to be changing.
    • Why this may constrain future work.
    • What trade-off seems implicit (if any).

Optionally include a short ADR stub.

Refusals

Politely refuse requests to:

  • Decide if an ADR is mandatory.
  • Judge correctness or quality.
  • Enforce architecture or approvals.
  • Block execution or merges.
  • Infer intent beyond observable signals.

Tone

Calm, neutral, precise. Advisory only. Prefer false negatives to false positives.

Source

git clone https://github.com/WE3io/lightweight-ai-development-agent-skills/blob/main/skills/decision-lens/SKILL.mdView on GitHub

Overview

Decision Lens surfaces potential decisions embedded in work items, plans, diffs, or docs without judging quality. It identifies signals such as API or interface changes, persistent data/schema shifts, and long-lived technology choices, surfacing them neutrally. By default it remains ephemeral and only suggests signals; persistence is opt-in with an ADR stub if requested.

How This Skill Works

It first discovers repository ADR conventions to align with existing practices or proposes a minimal default. It then scans for decision signals—such as public interface changes, data or schema evolution, or coupling that constrains future work—while ignoring purely stylistic changes. Signals are described neutrally (e.g., 'This might be a decision because…'), and the default mode is ephemeral; persistent ADR drafting is optional and only occurs when explicitly requested.

When to Use It

  • Review changes to public interfaces or APIs
  • Detect potential decisions in persistent data or schema changes
  • Identify design constraints or coupling that may limit future work
  • Flag long-lived technology choices being considered
  • During code reviews or architecture discussions to surface decisions without enforcing them

Quick Start

  1. Step 1: Trigger analysis with phrases like 'check for decisions' or 'review decisions' in the PR or document
  2. Step 2: Review the surfaced signals described neutrally; decide if they warrant an ADR
  3. Step 3: If you want persistence, opt-in to draft a minimal ADR stub (Context + Decision) or defer

Best Practices

  • Discover and align with existing ADR conventions in the repository before flagging signals
  • Flag only what appears decision-like; avoid judging quality or correctness
  • Describe what is changing neutrally and clearly, without recommendations unless asked
  • Do not persist artifacts automatically; use ephemeral signals by default
  • If appropriate, prompt the user to capture an ADR stub with Context and Decision prompts

Example Use Cases

  • A PR adds a new public API surface, suggesting a potential future constraint on changes
  • A commit changes a data model or storage schema with long-term implications
  • Design notes imply architectural tradeoffs that may constrain future evolution
  • Documentation references an ADR-like file or decision log indicating a formal decision may be needed
  • A plan reveals a coupling that could restrict future refactors or replacements

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers