agents-md-refactor
AGENTS.md Refactor
Goal
Restructure agent instruction files into a small, universal root plus linked, self-contained topic docs.
Guardrails
- Resolve contradictions before reorganizing content.
- Keep root file short (target under ~80 lines).
- Put specifics (language, testing, style) in linked docs, not the root.
- Prefer a hidden folder
.agents/unless the repo already uses another convention.
Workflow (short)
- Scan for contradictions and ask for precedence.
- Extract root essentials and links only.
- Group remaining guidance into 3–8 topic docs.
- Create files and link from root.
- Prune vague or redundant statements.
- Verify links, coverage, and self-contained topics.
References (load when needed)
agents-md-refactor/references/templates.md: root and topic doc templates.agents-md-refactor/references/checklist.md: execution and verification checklist.agents-md-refactor/references/triage.md: contradiction patterns and resolution prompts.
More from aleister1102/skills
codeql
>-
26ffuf-web-fuzzing
Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis
24brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
24skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
23docs-cleaner
Dedupe and consolidate redundant docs (multiple sources of truth, overlapping guides, or docs over 500 lines). Use when merging/splitting to a canonical doc. Do not use for typo-only edits, code-driven doc updates (run update-docs first), or when archives must be preserved without change.
20tech-stack-evaluator
Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
20