AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Memory Promote

skill-ladyiceberg-openclaw-memory-quality-memory-promote · by ladyiceberg

Pre-promotion quality audit for OpenClaw short-term memory candidates — checks the top-N entries before Dreaming promotes them to MEMORY.md, detects deleted source files, low-value snippets (imports/comments/debug code), already-promoted duplicates, and false-positive signals. Optional LLM long-term value advisory. Use this skill whenever the user wants to audit memories before Dreaming runs, che…

↗ Repository
— No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-ladyiceberg-openclaw-memory-quality-memory-promote

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Memory Promote? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Memory Promote

Pre-promotion quality audit. Run before OpenClaw's Dreaming process promotes short-term memories to MEMORY.md.

Steps

  1. Determine parameters:
  • top_n: user specified number, or default 10
  • use_llm: user said "--llm" or "with LLM" → True, otherwise False
  1. Call memory_promotion_audit_oc(top_n=N, use_llm=...)
  2. Summarize in one sentence, then show the full report

Summary format

> Top 10 candidates: 7 pass, 2 suggested skip (1 source deleted, 1 import-only), 1 flagged (low avg score).

What users can do with results

This tool outputs recommendations only — it doesn't block Dreaming. Options for the user:

  • Ignore and let Dreaming run normally
  • Manually remove unwanted entries from the short-term memory file
  • Run /memory-cleanup first to remove low-quality entries before Dreaming

LLM mode adds

Long-term value advisory for each passing/flagged entry:

  • long_term_knowledge — abstract knowledge or stable design facts, good to keep
  • one_time_context — one-off context with low long-term value, consider skipping
  • uncertain — not enough context to judge

Advisory doesn't affect Dreaming — it's informational only.

Notes

Score shown is approximate (±10%, consolidation dimension excluded). Read-only — never modifies any files. LLM mode requires an API key.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML