Skip to main content
samuelfaj
GitHub creator profile

samuelfaj

Repository-level view of 33 collected skills across 4 GitHub repositories.

skills collected
33
repositories
4
updated
Sep 3, 2026
repository explorer

Repositories and representative skills

sam-gauntlet-loop
computer-occupations-all-other

Compile a host-safe quality-bar loop prompt and return it for the user to copy, edit, and paste. Never start the loop. Use when the user runs /sam-gauntlet-loop, says gauntlet loop, gauntlet this, or asks to loop until the work beats a real reference.

Aug 16, 2026
sam-goal
computer-occupations-all-other

Finish a software goal completely with the smallest correct change: write checkable gates first, split independent units onto workers when the gate opens, verify every unit yourself, and never add a dependency. Use when the user runs /sam-goal, $sam-goal, or…

Aug 16, 2026
sam-grok-worker
software-developers

Delegate a bounded implementation task to the fixed Grok worker (grok-4.6) under workspace sandbox and headless execution. Use when a host agent or user needs Grok to implement, fix, or verify a scoped coding task; default effort high unless explicitly…

Aug 15, 2026
sam-orchestrate-claude-grok
software-developers

Claude-controller hybrid orchestration: Grok 4.6 workers for routine and deep slices (medium LIGHT / high STANDARD / xhigh DEEP), Claude opus high independent review, opus xhigh only for stall/multi-round capability escalation, and opus max for optional…

Aug 15, 2026
sam-orchestrate-codex-grok
software-developers

Codex-controller hybrid orchestration: Grok 4.6 workers for routine and deep slices (medium LIGHT / high STANDARD / xhigh DEEP), Codex gpt-5.6-sol medium independent review, and Sol high only for stall/multi-round capability escalation. Use when the user runs…

Aug 15, 2026
sam-orchestrate
software-developers

Coordinate complex work as a controller-only orchestrator using cost- and risk-aware capability routing, explicit task dependencies and ownership, skeptical proof verification, and an independent review gate. Use when the user asks for delegated execution,…

Aug 15, 2026
sam-plan
software-developers

Conduct task study and emit a machine freeze plan (goal, thesis, steps, evidence, status) plus a required light-theme HTML pack for humans; assertive investigation first, council only on risk triggers. Use when the user runs /sam-plan, asks for an…

Aug 4, 2026
sam-claude-advisor
computer-occupations-all-other

Consult Claude as a read-only advisor for a focused assumption, tradeoff, architecture question, security concern, difficult diagnosis, or high-risk decision. The calling agent binds model and reasoning effort from the sam-orchestrate host-runtime-matrix…

Jul 29, 2026
Showing 8 of 22 collected skills.
Showing 4 of 4 repositories
All repositories loaded