Skip to content
Back to skills

Context

ASecurity

File project knowledge the user shares conversationally into the correct .ai/ files - purpose, rules, database, dependencies, conventions, decisions - and close the memory loop at the end of tasks and sessions. Use when the user shares project context, decisions, or conventions, or when finishing a task in an initialized project.

  • 5 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 3, 2026
ai-agentsdatabase

Security analysis

A100/100

Scanned October 3, 2026

npx -y skills add SrRenks/prometheus-ai --skill context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Context
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/srrenks-context/badge)](https://www.skillsdirectory.com/skills/srrenks-context)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: context
description: 'File project knowledge the user shares conversationally into the correct .ai/ files - purpose, rules, database, dependencies, conventions, decisions - and close the memory loop at the end of tasks and sessions. Use when the user shares project context, decisions, or conventions, or when finishing a task in an initialized project.'
---
Act as the project's knowledge manager. File what the user tells you into the correct local markdown files:
- Purpose / business rules / glossary -> .ai/context/domain.md
- Architecture / modules / data flow -> .ai/context/architecture.md
- Database schema / storage decisions -> .ai/context/database.md (only if this project has a database)
- External services / load-bearing dependencies -> .ai/context/dependencies.md
- Local conventions -> .ai/context/conventions.md (short rules -> .ai/project.md)
- Stack / build / test commands -> .ai/project.md
- Decisions -> .ai/assumptions.md (numbered entries)

Rules: resolve the open questions in each topic file; never edit .ai/context/index.md (machine-owned); create a topic file if missing; keep files lean.

Close the loop before finishing a task or session in a project that has .ai/:
1. Update .ai/session.md: last updated, current objective, files changed, decisions made, tests run, remaining tasks.
2. Append each new decision to .ai/assumptions.md as a numbered entry.
3. Prune: remove scratchpad notes that are done, and context facts that the code itself now states (keep context curated and lean - stale context dilutes future sessions).
Then report exactly what you filed where and what remains unknown.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.