Skip to content
Back to skills

Context Refresh

ASecurity

Use when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.

  • 6 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 6, 2026
ai-agentsrustgo

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add ihabkhaled/AI-Psychiatry --skill context-refresh --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context Refresh?

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

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

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-refresh
description: Use when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.
---

# Context Refresh

## Core principle

Refresh preserves facts, decisions, blockers, and state while dropping speculation and reloading only changed authoritative sources.

## Procedure

1. Summarize goal, completed, remaining, decisions, evidence, blocker, and next action.
2. Discard abandoned hypotheses and repetitive output.
3. Check source hashes, versions, or modification evidence.
4. Reload only stale or changed sources.
5. Resolve conflicts in favor of current source.
6. Update compact task context and resume.

## Required output

Compressed state, refreshed sources, retired stale facts, and next action.

## Limits

Two identical reloads without source change trigger attention reset.

## Common mistakes

Do not reread the entire repository or trust stale summaries over source.

## Stop condition

Stop when current context is small, fresh, and sufficient for the next action.

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.