SKILLEMALL.ai
GitHub ↗ RU Sign in

AC wip-memory-crystal

Search and manage the shared memory crystal. Use when user says "do you remember", "search memory", "remember this", "forget that", "memory status", "what do you know about", or needs to recall past discussions, store facts, or check what's in memory.

ClawHub Agent Skills author: Parker Todd Brooks v0.7.38 MIT-0 80 files · 2 scripts body ≈ 3 684 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI 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
93/100
safety, quality, tests
Safety 60%
96
Quality 40%
89
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Dangerous commands cmd-cron-mention _trash/finder-duplicates-2026-04-16/src/doctor 2.ts:211
      Mentions editing / listing crontab (quoted — discussed, not commanded)
      const crontab = execSync('crontab -l 2>/dev/null', { encoding: 'utf-8' });
      quoted
    • low Dangerous commands cmd-cron-mention _trash/finder-duplicates-2026-04-16/src/doctor 2.ts:294
      Mentions editing / listing crontab (quoted — discussed, not commanded)
      const crontab = execSync('crontab -l 2>/dev/null', { encoding: 'utf-8' });
      quoted
    • low Dangerous commands cmd-cron-mention _trash/finder-duplicates-2026-04-16/src/installer 2.ts:141
      Mentions editing / listing crontab (quoted — discussed, not commanded)
      const crontab = execSync('crontab -l 2>/dev/null', { encoding: 'utf-8' });
      quoted
    • low Exfiltration read-dotenv README-old.md:162
      Reads a .env file
      cp .env.example ~/.openclaw/memory-crystal/.env

    Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, read, node) that frontmatter does not declare
    • 85Steps. 37 steps, 2 vague phrases
    • 100Failures and branches. 21 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3684 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 top-level sections: this looks like several domains in one skill
    • low The skill ranks results itself: that belongs to the system behind the tool, not the model

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +3Description length 251: enough signal without eating the budget
    • +4Structure: 35 headings
    • +3Step-by-step instructions: 37 items
    • +4Has examples (33 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This is a disclosed local memory system that captures and indexes AI conversations, with sensitive access that is expected for its purpose.
    LLM: benign (medium) · VirusTotal: · 29 May 2026