Menu
SkillsMP has collected 14 skills from ntholm86/principles-of-earned-autonomy-skills-suite. Open a skill to review its source and details.
Showing 14 of 14 collected skills.
Automatic direction-consolidation service. Improve schedules it when accumulated work makes cross-run direction useful; it surfaces sourced guesses about durable direction as questions the operator can confirm, correct, or reject. Manual invocation remains…
Automatic orientation service. Improve or Destination schedules it when accumulated evidence makes the current orientation stale; it reads the trail as a single document, forms arc-level claims, and refreshes .acm/orientation.md without changing the target.…
Automatic ingress service for substantive work. Apply Operator's Intent to the user's own prompt before acting: interpret what the user is trying to achieve, narrate it, and honor the operator's explicit supervision or delegation boundary. The operator should…
The improvement skill. Understand the ask, examine the target, challenge the first read, decide on one change (or argue for redesign, or declare silence), honor the operator's supervision or delegation boundary, act, reflect, record, and report the result…
Automatic egress service for substantive work. Append a structured entry to .acm/audit-trail.md IN THE TARGET REPO ROOT — recording the interpretation, examination, decisions, actions, and reflection. Destination, Improve, Orient, and Probe apply Trail…
Experimental layered Improve contract. Reason from target purpose, make one highest-leverage change or a bounded redesign/silence decision, verify it, reflect, and record. Not part of the installed suite.
Optional scientific instrumentation for measuring Autonomous Reasoning Fidelity (ARF). Construct a controlled novelty probe that distinguishes genuine situated reasoning from pattern-matching against a checklist. Not required by Destination, Orient, Improve,…
Reflect on the improvement loop itself. Examine the trail, surface recurring findings, blind spots, methodology effectiveness, and what the loop has been ignoring. Meta-improvement - improving the improvement process. USE WHEN: reflect, retrospective, what…
Apply Commander's Intent to the user's own prompt before acting. Interpret what the user is trying to achieve, not what they literally wrote. Narrate the interpretation so the user can correct drift before work begins. USE WHEN: any substantive user request…
Radical redesign evaluation. When incremental improvement has converged too low or the architecture is fundamentally wrong, Kaikaku determines whether to redesign and produces a migration plan if warranted. USE WHEN: redesign, start over, rethink, rewrite,…
Incremental improvement - diagnose, challenge blind spots, prioritize by impact, implement, verify. The core improvement cycle. Includes diagnostic vocabulary for unevenness, overburden, and waste. USE WHEN: audit, review, rate, improve, make impressive,…
Orchestrate an improvement cycle: diagnose, select methodology, execute, record, persist. The meta-pattern that connects all skills into a coherent workflow. USE WHEN: improve, audit, review, full treatment, kata, run the loop, comprehensive improvement, what…
Evidence trail management. Start sessions, record decisions during work, close sessions, index decisions, validate trail integrity. The implementation of Observable Autonomy (Principle 2). USE WHEN: start session, record trail, kiroku, audit trail, evidence,…
Construct novelty probes that distinguish genuine situated reasoning from pattern-matching. Builds examination scenarios where routine execution fails but interpretation succeeds. Measures Autonomous Reasoning Fidelity. USE WHEN: test reasoning quality,…