methodical
CommunityPrevent scope reduction and skipped evidence.
Software Engineering#intellectual honesty#anti-hallucination#agent reliability#completeness verification#audit reporting#evidence receipts
Authorjacob-balslev
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Methodical execution prevents agents from silently skipping steps, filtering negative findings, and replacing complete reporting with summaries that hide omissions.
Core Features & Use Cases
- Step-by-step completeness discipline: forces enumeration, counting, and step-level evidence receipts instead of end-only summaries.
- Generation/criticism separation: runs a structured self-critique after generation to catch what was omitted or softened.
- Anti-pattern detection for intellectual honesty: blocks common failure modes like summary-first fabrication, assumed verification, and “deferral as completion”.
- Use cases: audits, diagnostic/health reports, verification of acceptance criteria, and creating task items from findings where completeness matters more than brevity.
Quick Start
Use the methodical skill when producing an audit report of your current workspace so every step includes observable evidence and the final output states an explicit completeness coverage claim.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: methodical Download link: https://github.com/jacob-balslev/skill-graph/archive/main.zip#methodical Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.