SKILLEMALL.ai
GitHub ↗ RU Sign in

AF cortex

Local-first agent memory with Ebbinghaus decay, hybrid search, and MCP tools. Import files, extract facts, search with BM25 + semantic, track confidence over time. Zero dependencies, single Go binary, SQLite storage. Use when you need persistent memory beyond OpenClaw's built-in MEMORY.md — especially for multi-agent setups, large knowledge bases, or when compaction keeps losing your important context. Don't use for: conversation history (use memory_search), exact string matching (use ripgrep), or web lookups.

ClawHub Agent Skills author: marquise v4.0.0 4 files · 2 scripts body ≈ 2 033 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 39/100 · Will not run — References files that are not bundled: scripts/cortex.sh

ReferenceAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
100
Quality 40%
78
Run on models
none yet
Process rating
F
39/100
Will not run
References files that are not bundled: scripts/cortex.sh
Tools and files w 18
0
Result and completion w 14
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/cortex.sh
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: scripts/cortex.sh
  • 0Tools and files. 1 referenced file(s) missing: scripts/cortex.sh
  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (cortex) differs from the folder (hurttlocker-cortex)
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 25 steps
  • 100Execution cost. Instruction body is 2033 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 515: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 25 items
  • +4Has examples (16 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
Cortex appears to be a legitimate memory tool, but it needs review because it installs an external binary, can run ongoing sync, modifies shell startup files, and may centralize sensitive data.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026