SKILLEMALL.ai
GitHub ↗ RU Sign in

AC memory-governor

Memory governance kernel for AI agents that complements the OpenClaw 2026.6.x memory stack (Dreaming, Active Memory, Memory Wiki, People Wiki, Skill Workshop / Workboard) with explicit correction staging, target-class routing, compiled-surface boundaries, scope/privacy rules, and safer manual hardening rules.

ClawHub Agent Skills author: Saken v0.3.2 MIT-0 60 files · 1 script body ≈ 2 001 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

ProcedureSoftware developmentAI and agentsInfrastructuretype 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
90/100
safety, quality, tests
Safety 60%
95
Quality 40%
83
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Broad scope meta-agent-memory-dump examples/generic-host/memory/learning-candidates.md
      Agent memory / workspace files bundled with the skill (5) — likely a workspace dump with personal data or tokens
      examples/generic-host/memory/learning-candidates.md, examples/generic-host/memory/long-term.md, examples/generic-host/memory/proactive-state.md, examples/generic-host/memory/reusable-lessons.md, examp

    Files scanned: 59. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "slug"
    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "changelog"

    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
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 70 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2001 tokens
    • low 12 top-level sections: this looks like several domains in one skill

    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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -34 of 4 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 310: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 70 items
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (17 of 23)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: clean
    This skill is a disclosed memory-governance aid that stores or checks local memory files only when the host or user explicitly integrates it.
    LLM: benign (high) · VirusTotal: · 22 Jun 2026