Skip to content
Back to skills

Engram Evomap

ASecurity

The AEIF-based long-term memory hub for AI Agents to prevent repeating bugs.

  • 33 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 5, 2026
ai-agentsrust

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add dvcrn/openclaw-skills-marketplace --skill engram-evomap --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Engram Evomap?

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

Security grade badge for Engram Evomap
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/dvcrn-engram-evomap/badge)](https://www.skillsdirectory.com/skills/dvcrn-engram-evomap)

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: engram-evomap
description: "The AEIF-based long-term memory hub for AI Agents to prevent repeating bugs."
---

# 🧬 engram β€” Agent Long-Term Experience Memory Hub

## πŸ€– System Mind
You are equipped with an external long-term memory store based on the **AEIF v1.0** (Agent Experience Interchange Format) protocol. 
- **Consult first**: Before tackling a recurring error or a complex problem, search your memory for existing solutions.
- **Commit success**: After successfully resolving a significant challenge, "geneticize" the experience and store it immediately.

## 🎯 Automatic Trigger Rules
- **Error Interception (Auto-Consult)**: When detecting signals such as `error`, `failed`, `SSL`, `404`, `EACCES`, or `timeout`, the system automatically retrieves and injects `[EvoMap Advice]`.
- **Task Distillation (Auto-Commit)**: After completing a multi-step complex task successfully, trigger `!exp commit` to preserve the logic for future sessions.

## πŸ› οΈ Command Set
| Command | Action |
|---------|--------|
| `!exp consult '<problem>'` | Performs a semantic search for historical solutions. Returns Top-3 matches. |
| `!exp commit` | Asynchronously distills current session history into a universal AEIF capsule. |
| `!exp list` | Displays memory statistics and a list of recently stored capsules. |
| `!exp score <id> --bad` | Provides negative feedback to a capsule, decreasing its TrustScore. |

## πŸ“¦ Output Specification
- Advice should be injected as a system observation wrapped in `---` separators.
- Focus on providing actionable `[PATCH]`, `[CONFIG]`, or `[WORKAROUND]` steps.
- Do not modify user-validated paths unless explicitly requested.

Files in this skill

  • README.md2 KB
  • SKILL.md1.6 KB
  • aeif-manifest.d.ts1.5 KB
  • bin/cli.js2.4 KB
  • data/seeds/seeds.json6.6 KB
  • index.js1.2 KB
  • package.json778 B
  • src/api/commands.js2.5 KB
  • src/config/aeif-schema.json2.3 KB
  • src/core/context-injector.js1.6 KB
  • src/core/distill-manager.js2.3 KB
  • src/core/embedding-service.js3.7 KB
  • src/core/embedding-worker.js1.9 KB
  • src/core/engram-core.js3.4 KB
  • src/core/env-checker.js1.2 KB
  • src/core/gene-processor.js3.3 KB
  • src/core/verification-engine.js2.3 KB
  • src/hooks/exception-hook.js2.5 KB
  • src/storage/capsule-store.js3.9 KB
  • src/storage/validator.js1.1 KB

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…