SKILLEMALL.ai
GitHub ↗ RU Sign in

AB skill-forge

Detect repeated capability gaps, convert recurring user needs into candidate skills, scaffold new OpenClaw-compatible skills, and validate them before installation. Use when an agent repeatedly fails the same task, sees recurring feature requests, notices repetitive manual workflows, or wants to propose a new skill instead of solving the same problem ad hoc.

ClawHub Agent Skills author: SheepXu v1.4.0 MIT-0 49 files body ≈ 3 717 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency

AnalyzerInfrastructureAI 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
92/100
safety, quality, tests
Safety 60%
90
Quality 40%
94
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Exfiltration exfil-webhook-url scripts/install/telegram_approval.py:23
      Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
      return f"https://api.telegram.org/bot{token}/{method}"
      quoted
    • medium Exfiltration exfil-webhook-url scripts/somnia/reporting.py:48
      Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
      f"https://api.telegram.org/bot{token}/sendMessage",
      quoted

    Files scanned: 49. 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 67/100

    • 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
    • 40Consistency. Frontmatter name (skill-forge) differs from the folder (skills-forge)
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 107 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Execution cost. Instruction body is 3717 tokens
    • 100Running it twice. Mutating operations check current state
    • low 11 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 360: enough signal without eating the budget
    • +4Structure: 23 headings
    • +3Step-by-step instructions: 107 items
    • +3Output format is stated explicitly
    • +4Has examples (15 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 15 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.

    External checks

    ClawHub: clean
    This is a powerful but coherent skill-building tool with disclosed local file, install, scheduling, and Telegram approval behavior, and I found no hidden exfiltration or automatic destructive install path.
    LLM: benign (high) · VirusTotal: · 29 May 2026