SKILLEMALL.ai
GitHub ↗ RU Sign in

BD mcp-dependency-review

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or other repo-scoped MCP config.

The skillemall take

The skill parses MCP configs and catches mutable package references—those that update without explicit version pinning. It checks `.mcp.json` and IDE configs before the agent runs discovered servers.

Found 2 files with 2484 tokens of code. No critical or high-severity findings. Quality score 85, process score 43 (likely due to lack of automation). No lint errors, references intact.

In practice: the agent will verify that MCP server setup won't pull an unexpected package version instead of the pinned one. Useful for those who lock dependencies tight and fear CI surprises. Worth installing if you work with MCP and want version control enforced.

affaan-m/ECC Agent Skills author: affaan-m MIT 2 files body ≈ 2 484 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers.

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerVS CodeDockerGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
85
Run on models
none yet
Process rating
D
43/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

The same skill appears in 2 more places: ECC, everything-claude-code

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 · 0

    ✓ No critical or high findings

    Files scanned: 2. 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 43/100

    • 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. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2484 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
    • +2Single-language instructions
    • +3Description length 229: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (3 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.