agentleFS
iwesysiwesys/IWE/.claude/skills/w-reflection/SKILL.md

w-reflection

Skill0 starsChanged 24 days agoMITView on GitHub

Record a W-reflection (worldview slot RCS) in learning.w_reflections.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

W-Reflection — Recording the Worldview Indicator

Purpose: populate learning.w_reflections to calculate W.idx in the SR algorithm (FORM.089 §5). When to invoke: after a reflective session (dialogue with Diagnostician R28, individual self-analysis, review of a worldview error). Not for routine mood logging — this is calibration. Effect: W ≥ 4 is required for the Disciplined → Proactive transition (gate D→P).

When to use

Record a W-reflection (worldview slot RCS) in learning.w_reflections. Used by Diagnostician R28 (MIM.R.009) or invoked by the user after a reflective session. Affects the Disciplined → Proactive gate (FORM.089 §5.2).

Arguments

  • $1 = quality_score — 1..5 per rubric:
    • 1 — surface (statement without causes)
    • 2 — descriptive ("what happened" present, "why" absent)
    • 3 — analytical (causes, consequences)
    • 4 — systemic (self viewed as a system, agency)
    • 5 — meta-systemic (self viewed as a role within a Supersystem)
  • $2 = depth_level (optional, default 2) — 1..3:
    • 1 — surface
    • 2 — medium (standard)
    • 3 — deep (>30 min analysis)

Algorithm

Step 1. Invoke the routing Script

bash "$IWE_SCRIPTS/route-task.sh" --skill w-reflection --args "$ARGUMENTS"

The Script reads IWE_OWNER_ORY_UUID from the Environment (account_id) and writes to learning.w_reflections via the w_reflection_writer Role (Migration 112). If the writer URL is absent, it falls back to DATABASE_URL_LEARNING_DIRECT.

Step 2. Check the exit code

Exit codes and their meanings are described in the Output section below.

Step 3. Return the response to the pilot

On exit 0 — print the OK string from stdout. On a non-zero exit — print the error.

Output

  • exit 0 + [w-reflection] OK: account=... quality=N depth=M — success
  • exit 1 — invalid arguments
  • exit 2 — IWE_OWNER_ORY_UUID or DB URL is missing
  • exit 3 — database error (constraint violation, network)

Example

/w-reflection 3        # quality=3, depth=2 (default)
/w-reflection 4 3      # quality=4, deep

Dependencies

  • Migration 112-w-reflection-writer-grants.sql (in the Infrastructure Repository migrations directory)
  • Logic source: PD.FORM.089-learner-rcs.md §5
  • Reader: learning.stage_evaluator worker (WP-253 Block 2 Phase 1.3)
<!-- USER-SPACE --><!-- /USER-SPACE -->

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.