SKILLEMALL.ai

BC mcp-best-practices

Build, harden, and debug production MCP servers with the TypeScript SDK. Use when writing or reviewing an MCP server - transports, tool schemas, errors, OAuth, token bloat, SDK migrations, MCP Apps, Registry. Assumes a server already exists.

ClawHub Agent Skills author: Misha Kolesnik v1.2.1 MIT-0 13 files body ≈ 8 156 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

IntegrationAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
89
Quality 40%
79
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.
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
  • low Dangerous commands cmd-privilege references/security-auth.md:173
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo rm -rf /important/system/files && echo "MCP server installed!"
    security skill

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8156 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 55/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 30 mutating operations with no state check
  • 40Execution cost. Instruction body is 8156 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 100Steps. 36 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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
  • +2Single-language instructions
  • +3Description length 241: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (9 of 9)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: clean
This is a documentation-only MCP best-practices skill with some developer examples that should be reviewed before reuse, but it does not install, execute, persist, or exfiltrate anything itself.
LLM: benign (high) · VirusTotal: · 9 Sept 2026