SKILLEMALL.ai
GitHub ↗ RU Sign in

BF universal-skills-manager

The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization across Claude Code, Gemini CLI, Google Anti-Gravity, OpenCode, and other AI tools. Handles User-level (Global) and Project-level (Local) scopes.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 10 828 tokens Open the sourcegithub.com↗ analyzed 3 d ago

The master coordinator for AI skills.

As a process F 52/100 · Will not run — References files that are not bundled: scripts/validate_frontmatter.py

IntegrationGitHubAI 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
B
84/100
safety, quality, tests
Safety 60%
93
Quality 40%
71
Run on models
none yet
Process rating
F
52/100
Will not run
References files that are not bundled: scripts/validate_frontmatter.py
Tools and files w 18
0
Inputs and preconditions w 11
0
Execution cost w 6
40
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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration net-credential-use SKILL.md:209
    Credential used in a network call (verify the destination is the intended service)
    # Step 2: Use ${API_KEY} in curl commands
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:70
    Pipe-to-shell installer from a well-known host (still executes remote code) (detector / deny-list definition)
    **Workaround:** Use Claude Code CLI instead, which has unrestricted network access and works with all three skill sources. You can install via: `curl -fsSL https://raw.githubusercontent.com/jacob-bd/u
    detector
  • low Exfiltration net-credential-use SKILL.md:204
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    -   **IMPORTANT:** Always capture the API key into a local variable first, then use it. Direct `$SKILLSMP_API_KEY` expansion in curl can fail in some shell contexts:
    quoted

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 10828 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/validate_frontmatter.py

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: scripts/validate_frontmatter.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/validate_frontmatter.py
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 10828 tokens: crowds the task out of the window
  • 60Steps. 113 steps, 4 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Failures and branches. 18 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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

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 302: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 113 items
  • +3Output format is stated explicitly
  • +4Has examples (34 code blocks)

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