brain-maintenance
Tools to update llms.txt, categorize new documentation, and log architectural decisions within the agent's knowledge repository.
Install
mkdir -p .claude/skills/brain-maintenance && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19296" && unzip -o skill.zip -d .claude/skills/brain-maintenance && rm skill.zipInstalls to .claude/skills/brain-maintenance
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Tools for maintaining and indexing the Agent Brain (.agent/knowledge).Key capabilities
- →Update llms.txt index files
- →Organize documentation into skill directories
- →Log architectural decisions and rationales
How it works
This skill maintains the agent's knowledge base by indexing new documentation files into llms.txt and appending major architectural decisions to a centralized log.
Inputs & outputs
When to use brain-maintenance
- →Add new documentation to the agent's brain
- →Update llms.txt index after adding new skill references
- →Log major architectural decisions and rationales
About this skill
Brain Maintenance Skill
Use this skill to update the llms.txt index or organize knowledge when new documentation is added.
Instructions
1. Update Index (llms.txt)
When new files are added to any Skill's references/ directory, run this sequence to update the index.
- List Skills: Run
find_by_nameforreferencesinside.agent/skills. - Generate Entry: Format the new file as
- [Title](../skills/<SkillName>/references/<File>): Description.. - Append: Use
replace_file_contentto add it to.agent/skills/project-context/references/llms.txt.
2. Knowledge Ingestion
When the user asks to "learn" a new doc:
- Categorize: Select the most appropriate Skill (e.g.,
ai-engineering,system-architecture). - Move: Move the file to
references/within that Skill. - Index: Update
llms.txt.
3. Decisions Log
When a major architectural decision is made:
- Log: Append a new entry to
.agent/skills/project-context/references/decisions.mdwith Date, Decision, and Rationale.
How it compares
It automates the specific file-path and formatting requirements for agent knowledge management instead of requiring manual file organization.
Compared to similar skills
brain-maintenance side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| brain-maintenance (this skill) | 0 | 5mo | No flags | Beginner |
| marker | 22 | 6mo | Review | Beginner |
| markdown-converter | 5 | 2mo | Review | Beginner |
| enhance-claude-memory | 11 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by lguibr
View all by lguibr →You might also like
marker
benchflow-ai
Convert PDF documents to Markdown using marker_single. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.
markdown-converter
steipete
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.
enhance-claude-memory
avifenesh
Use when improving CLAUDE.md or AGENTS.md project memory files.
doc-sync
solatis
Synchronizes docs across a repository. Use when user asks to sync docs.
wiki-sync
zoraxl
Use to sync the wiki from a merged PR or from a source doc/file path. Two modes — PR mode (post-merge: creates ADR if needed, flips ADR to accepted, updates wiki pages, appends log, records idempotency, archives related plan/source files) and doc mode (ingests existing implemented knowledge from a f
docs-governance
hakon1233
Before creating, renaming, or moving any `.md` file outside `src/`, or when the user says \"stray docs\", \"docs governance\", \"where should this doc live\", or runs the stray-doc auditor: invoke `Skill('docs-governance')` and place the file using its vault-synced allowlist and filename-heuristic t