SKILLEMALL.ai
GitHub ↗ RU Sign in

FC adam-framework

5-layer persistent memory and coherence architecture for OpenClaw agents. Solves AI amnesia and within-session drift. Built and validated over 353 sessions on a live business. No CS degree required.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: strangeadvancedmarketing v1.0.1 MIT-0 49 files · 2 scripts body ≈ 631 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

AnalyzerGitHubInfrastructureAI 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
F
26/100
safety, quality, tests
Safety 60%
0
Quality 40%
64
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 24

  • high Dangerous commands cmd-persistence docs/SETUP.md:250
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask `
  • high Dangerous commands cmd-persistence docs/SETUP.md:260
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    cp engine/com.adamframework.sentinel.plist ~/Library/LaunchAgents/
  • high Dangerous commands cmd-persistence docs/SETUP.md:262
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.adamframework.sentinel.plist
  • high Dangerous commands cmd-persistence docs/SETUP.md:265
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    **Linux (cron @reboot):**
  • high Dangerous commands cmd-persistence docs/SETUP.md:269
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    @reboot /bin/bash ~/.openclaw/SENTINEL.sh >> ~/.openclaw/sentinel.log 2>&1
  • high Dangerous commands cmd-persistence SETUP_AI.md:159
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName "AISentinel" -Action $action -Trigger $trigger -RunLevel Highest -Force
  • high Dangerous commands cmd-persistence SETUP_AI.md:165
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    cp engine/com.adamframework.sentinel.plist ~/Library/LaunchAgents/
  • high Dangerous commands cmd-persistence SETUP_AI.md:167
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.adamframework.sentinel.plist
  • high Dangerous commands cmd-persistence SETUP_AI.md:173
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "@reboot /bin/bash ~/.openclaw/SENTINEL.sh >> ~/.openclaw/sentinel.log 2>&1") | crontab -
  • high Dangerous commands cmd-persistence SETUP_HUMAN.md:171
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName "AISentinel" -Action $action -Trigger $trigger -RunLevel Highest -Force
  • high Dangerous commands cmd-persistence SETUP_HUMAN.md:176
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    cp engine/com.adamframework.sentinel.plist ~/Library/LaunchAgents/
  • high Dangerous commands cmd-persistence SETUP_HUMAN.md:178
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.adamframework.sentinel.plist
  • high Dangerous commands cmd-persistence SETUP_HUMAN.md:183
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "@reboot /bin/bash ~/.openclaw/SENTINEL.sh >> ~/.openclaw/sentinel.log 2>&1") | crontab -
Medium and low: 11
  • medium Dangerous commands cmd-execpolicy-bypass docs/SETUP.md:214
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.openclaw\SENT…ps1"
  • medium Dangerous commands cmd-persistence ROADMAP.md:54
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    `Register-ScheduledTask` command block included with all required parameters.
    quoted
  • medium Dangerous commands cmd-execpolicy-bypass SETUP_AI.md:135
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.openclaw\SENT…ps1"
  • medium Dangerous commands cmd-execpolicy-bypass SETUP_HUMAN.md:144
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.openclaw\SENT…ps1"
  • low Dangerous commands cmd-execpolicy-bypass docs/SETUP.md:246
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    -Argument "-ExecutionPolicy Bypass -WindowStyle Hidden -File `"$env:USERPROFILE\.openclaw\SENT…ps1`""
    detector
  • low Dangerous commands cmd-cron-mention docs/SETUP.md:267
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-execpolicy-bypass SETUP_AI.md:157
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    $action = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-ExecutionPolicy Bypass -WindowStyle Hidden -File `"$env:USERPROFILE\.openclaw\SENT…ps1`""
    detector
  • low Dangerous commands cmd-cron-mention SETUP_AI.md:173
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "@reboot /bin/bash ~/.openclaw/SENTINEL.sh >> ~/.openclaw/sentinel.log 2>&1") | crontab -
  • low Dangerous commands cmd-cron-mention SETUP_AI.md:175
    Mentions editing / listing crontab (detector / deny-list definition)
    Success condition: `crontab -l | grep SENTINEL` → shows the entry
    detector
  • low Dangerous commands cmd-execpolicy-bypass SETUP_HUMAN.md:169
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    -Argument "-ExecutionPolicy Bypass -WindowStyle Hidden -File `"$env:USERPROFILE\.openclaw\SENT…ps1`""
    detector
  • low Dangerous commands cmd-cron-mention SETUP_HUMAN.md:183
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "@reboot /bin/bash ~/.openclaw/SENTINEL.sh >> ~/.openclaw/sentinel.log 2>&1") | crontab -

Files scanned: 49. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (python, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 10 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 631 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -410 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +3Description length 198: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 10 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
The skill is a coherent memory framework, but it should stay in Review because it bundles persistent startup, broad local tool access, and an open Telegram configuration that could expose private memory if copied as-is.
LLM: suspicious (high) · VirusTotal: · 29 May 2026