SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ghostclaw

Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture, suggesting refactors aligned with tech stack best practices, monitoring repositories for vibe health, or opening PRs with architectural improvements. Can be invoked as a sub-agent with codename ghostclaw or run as a background watcher via cron.

ClawHub Agent Skills author: Ev3lynx727 v1.0.0 MIT-0 80 files · 4 scripts body ≈ 1 228 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 28/100 · Will not run — References files that are not bundled: references/stack-patterns/

AnalyzerSoftware developmenttype 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
B
79/100
safety, quality, tests
Safety 60%
84
Quality 40%
71
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: references/stack-patterns/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: ghostclaw (ClawHub)

What is at stake

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

Dangerous commands 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 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. 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 · 8

✓ No critical or high findings

Medium and low: 8
  • medium Dangerous commands cmd-privilege docs/LINUX_DAEMON.md:50
    Privilege escalation / world-writable permissions
    sudo cp scripts/ghostclaw.service /etc/systemd/system/
  • medium Dangerous commands cmd-privilege docs/LINUX_DAEMON.md:57
    Privilege escalation / world-writable permissions
    sudo chmod 644 /etc/systemd/system/ghostclaw.service
  • low Dangerous commands cmd-background-process docs/LINUX_DAEMON.md:41
    Starts a background / autostarted process (quoted — discussed, not commanded)
    4. Runs `systemctl daemon-reload && systemctl enable --now ghostclaw.service`.
    quoted
  • low Dangerous commands cmd-background-process docs/LINUX_DAEMON.md:59
    Starts a background / autostarted process
    sudo systemctl enable --now ghostclaw.service
  • low Dangerous commands cmd-background-process docs/LINUX_DAEMON.md:71
    Starts a background / autostarted process
    sudo systemctl enable ghostclaw.service
  • low Dangerous commands cmd-privilege scripts/install_service.sh:39
    Privilege escalation / world-writable permissions (security demo / example)
    sudo cp "$TEMP_FILE" "$TARGET"
    demo
  • low Dangerous commands cmd-privilege scripts/install_service.sh:40
    Privilege escalation / world-writable permissions (security demo / example)
    sudo chmod 644 "$TARGET"
    demo
  • low Dangerous commands cmd-background-process scripts/install_service.sh:46
    Starts a background / autostarted process
    sudo systemctl enable "$SERVICE_FILE"

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

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/stack-patterns/

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: references/stack-patterns/
  • 0Tools and files. 1 referenced file(s) missing: references/stack-patterns/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 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. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (ghostclaw) differs from the folder (ghostclaw-clone)
  • 100Steps. 39 steps
  • 100Execution cost. Instruction body is 1228 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
  • -411 reference files, but SKILL.md never points to them: the model will not open them
  • -310 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 401: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
Ghostclaw looks like a real architecture review tool, but it needs Review because it can execute repo-local plugins, modify or publish repository content, self-update, and run persistent services.
LLM: suspicious (high) · VirusTotal: · 29 May 2026