Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems.
SkillScore73Maintained
Automatic
◆Knowledge Management pack
Last verified 8/12/2026
What it changes
Passed 11 of 15 test cases with the skill, and 7 of 15 without it.
Without skill45%
With skill73%
Checks it passed that the model alone missed
Specifies target argument drift for command execution
Requests user approval for each batch before continuing
Recommends invoking /reseed instead of applying incremental patches
and 8 more in the full report
8 fixed8 passed either way4 still failing2 broke
Pass-rate lift
+27 pp
Tokens
+371%
Agent turns
0%
Response time
-36%
Model gemini-3.6-flashMeasured 8/12/2026v116 of 22 cases passed with skill · 15 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
When ops/config.yaml is not present in the workspace, what is the default tension count threshold before rethink is suggested?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses 5 as default tension threshold when ops/config.yaml is missing
Missed
Passed
case-16 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md649 linessingle file
Runtime Configuration (Step 0 — before any processing)
Read these files to configure domain-specific behavior:
self_evolution.observation_threshold: number of pending observations before suggesting rethink (default: 10)
self_evolution.tension_threshold: number of pending tensions before suggesting rethink (default: 5)
ops/methodology/ — existing methodology notes (read all to understand current system self-knowledge)
If these files don't exist (pre-init invocation or standalone use), use universal defaults.
The command name itself transforms per domain. The derivation manifest maps the universal name to domain-native language. If no manifest exists, use "rethink" as the command name.
EXECUTE NOW
Target: $ARGUMENTS
Parse immediately:
If target is empty: run full six-phase rethink (Phase 0 drift check + five evidence phases) on all pending observations and tensions
If target is "triage": run Phase 1 only (triage and methodology updates, no pattern detection)
If target is "patterns": skip triage, run Phases 3-5 only (analyze existing evidence for patterns)
If target is "drift": run Phase 0 only (drift check without triage or pattern detection)
If target is a specific observation or tension filename: triage that single item interactively
START NOW. Reference below defines the six-phase workflow.
Philosophy
The system is not sacred. Evidence beats intuition.