SKILLEMALL.ai
GitHub ↗ RU Sign in

CC builder-smoke-test

Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree). Covers workspace reconciliation, stored agents/skills CRUD, ownership, visibility, stars, registry/library Copy flow, picker allowlists, model policy, RBAC role gating, role impersonation UI, builder defaults, infrastructure diagnostics, channels, and Studio + Agent Builder UI. Trigger when validating the agent-builder feature branch, PRs that touch packages/server, packages/playground, packages/playground-ui agent-builder routes, or builder EE code paths.

mastra-ai/mastra Agent Skills author: mastra-ai NOASSERTION 27 files · 9 scripts body ≈ 11 148 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree).

As a process C 53/100 · Has gaps — References files that are not bundled: examples/agent, references/<section>.md, examples/agent-builder

IntegrationAI 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
C
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
67
Run on models
none yet
Process rating
C
53/100
Has gaps
References files that are not bundled: examples/agent, references/<section>.md, examples/agent-builder
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Exfiltration net-redirectable-api-key assets/template/src/mastra/index.ts:45
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment

Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 11148 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: examples/agent
  • warning missing-ref reference to a missing file: references/<section>.md
  • warning missing-ref reference to a missing file: examples/agent-builder

Process rating: all ten parameters 53/100

Will not run. References files that are not bundled: examples/agent, references/<section>.md, examples/agent-builder
  • 0Tools and files. 3 referenced file(s) missing: examples/agent, references/<section>.md, examples/agent-builder
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 40Execution cost. Instruction body is 11148 tokens: crowds the task out of the window
  • 60Failures and branches. 2 branches
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 81 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 600: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 81 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (15 of 15)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.