Hand-Compute

Trust Score 95/100

A technique skill that guides agents to execute system flows step-by-step with explicit state to find race conditions and state bugs.

triggers:walk through the flowwhy is this brokenracestate bugdebugging stepsstress test

GitHub SKILL.md

What it does

Hand-Compute trains an agent to become a human 'computer': it executes a system manually, writing explicit actor state at each transition to reveal races, stale snapshots, and sequencing bugs. It provides structured shapes for new work, debugging, and scoping features.

When to use it

Use for debugging regressions, race conditions, client/server sequencing bugs, recovery paths, or when scoping a feature onto an existing stateful system. Trigger on intents like "why is this broken", "walk through the flow", or "stress test this plan".

What's included

Scripts: none bundled, but the skill recommends inspecting code and references as part of the walk
References: checklists and failure modes, plus examples for different shapes (new work, debugging, scoping)
Instructions: concrete step-by-step methodology (hand-compute broken flow, propose fix, re-walk fixed flow, and check adjacent phases) and an explicit checklist for completion.

Compatible agents

Ideal for code-capable assistants and reviewers (Copilot/GitHub-code assistants, Codex-style agents) that can read source files and synthesize concrete state traces.

Audit Summary

Pure methodology skill with no scripts — teaches agents to hand-compute system execution with explicit state to find race conditions and state bugs. SKILL.md is exceptionally well-written with concrete state-trace examples, three distinct usage shapes (new work, debugging, scoping), a failure-modes table, and a completion checklist. No security concerns as there is no executable code.

Watch Out

No scripts to test — this is a documentation-only methodology skill

Notes

Outstanding writing quality. The state-trace examples (especially the optimistic save race condition) are genuinely educational. One of the better methodology skills — specific triggers, clear failure modes, actionable checklist.

Information

Repository: hand-compute
Stars: 37
Installs: 0

Trust Score

Overall95

Security100

Code Quality92

Architecture88

Usefulness82

Related Skills

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Maestro Orchestrate

Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

OpenTestAI

Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.

Blender Build-Go (bgo)

Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.

Overnight — Autonomous Long-Running Coding

Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges

EventKit Integration (iOS/macOS)

Expert EventKit patterns for iOS/macOS: permissions, bidirectional sync, zero-width identity signatures, batch operations, and zombie-task handling.

Back to Skills