reasoning-framework_skill

This skill helps you reason and plan complex requests by applying a structured framework for task analysis, risk assessment, and hypothesis formation.

58

GitHub Stars

1

Bundled Files

3 weeks ago

Catalog Refreshed

2 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstart where the catalogue uses aiagentskills.

npx veilstart add skill ahonn/dotfiles --skill reasoning-framework

SKILL.md2.9 KB

Overview

This skill is a reasoning and planning framework that I apply automatically before performing complex tasks. It enforces a consistent priority order for constraints, assesses risk, and structures hypothesis-driven troubleshooting. The goal is clearer decisions, safer actions, and concise justifications for each step taken.

How this skill works

Before any external action, the framework runs an internal checklist: validate rules and constraints, verify operation order and reversibility, and identify missing prerequisites. It classifies operations by risk, forms 1–3 hypotheses for ambiguous problems, and selects and verifies the most likely one. After proposing changes it self-checks results against constraints and updates plans if premises change.

When to use it

Complex multi-step tasks where order, reversibility, or side effects matter
High-risk changes (data migration, history rewrites, API or infra updates)
Troubleshooting ambiguous failures or intermittent errors
Design or architecture decisions requiring trade-off analysis
Automated agents or scripts that must avoid unsafe actions

Best practices

State explicit hard constraints and rules up front so they take top priority
Provide necessary prerequisites; only request clarification when it meaningfully alters choices
Prefer reversible steps and document rollback paths for risky operations
Offer 1–3 hypotheses and verify the most likely first to save time
When conflicts arise, resolve by the prescribed priority order (readability, correctness, requirements, performance, brevity)

Example use cases

Refactoring a large codebase while preserving history and minimizing downtime
Designing a migration plan that balances data integrity and rollout speed
Debugging flaky CI failures by forming hypotheses about environment, tests, and code
Choosing between alternative implementations where maintainability and performance trade off
Automating administrative tasks with clear risk assessment and rollback procedures

FAQ

Only when missing details would significantly change the chosen solution or risk profile.

How do you handle risky operations?

I clearly state risks, propose safer alternatives, prefer reversible steps, and require explicit confirmation for destructive actions.