Skip to main content
ntholm86
Profil créateur GitHub

ntholm86

Vue par dépôt de 16 skills collectés dans 3 dépôts GitHub.

skills collectés
16
dépôts
3
mis à jour
19 août 2026
explorateur de dépôts

Dépôts et skills représentatifs

destination
non classé

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…

19 août 2026
orient
non classé

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.…

19 août 2026
intent
non classé

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…

19 août 2026
improve
non classé

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…

16 août 2026
trail
non classé

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…

13 août 2026
improve-layered-prototype
Autres occupations informatiques

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.

2 août 2026
probe
Scientifiques des données

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,…

2 août 2026
hansei
Analystes en gestion

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…

23 avr. 2026
Affichage de 8 skills collectés sur 14.
3 dépôts affichés sur 3
Tous les dépôts sont affichés