DB setup-gbrain
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)
Promises to set up gbrain with CLI, local PGLite or Supabase, MCP registration, and per-remote trust policies. Seven files, no critical issues, but code quality sits at 58 points. Four medium and low-severity findings suggest careless details—likely incomplete validation or skipped checks.
No model runs, no sandbox test. Wide platform coverage listed, but without actual verification it's wishful thinking. Install if you're ready to debug on the fly and patch things yourself.
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy.
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-agent-memory-dumpmemory.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensmemory.md
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write Edit Glob Grep AskUserQuestion
-
medium Exfiltration
net-credential-useSKILL.md:1012Credential used in a network call (verify the destination is the intended service)projects=$(curl -s -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:1024Credential used in a network call (verify the destination is the intended service)curl -s -X DELETE -H "Authorization: Bearer $SUPABASE_ACCESS_TOKEN" \
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 14887 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "preamble-tier" - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 75/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 14887 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 88 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 15 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
- low 39 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (18 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)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 154: enough signal without eating the budget
- +4Structure: 55 headings
- +3Step-by-step instructions: 88 items
- +3Output format is stated explicitly
- +4Has examples (29 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.