SKILLEMALL.ai
GitHub ↗ RU Sign in

CA pair-agent

Pair a remote AI agent with your browser. (gstack)

The skillemall take

The skill promises to pair a remote AI agent with your browser via gstack. One file with 10k tokens of instructions, no scripts, no critical errors. A quality score of 55 means the documentation is either sparse or vague—no concrete code examples or step-by-step walkthrough. Process score 83 suggests structure is fine but content is thin. One medium-level finding hints at inaccuracy or a missing step in the instructions. Safety is solid at 95, but that doesn't fix the lack of clarity. You'll get a set of directions you'll need to patch yourself or supplement from gstack's own docs.

Install if you're prepared to fill in the gaps and figure out implementation details on your own.

garrytan/gstack Agent Skills author: garrytan MIT 1 file body ≈ 10 552 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Pair a remote AI agent with your browser.

As a process A 83/100 · Runs to the end — weak spots: execution cost

AnalyzerAI 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
79/100
safety, quality, tests
Safety 60%
95
Quality 40%
55
Run on models
none yet
Process rating
A
83/100
Runs to the end
Execution cost w 6
40
When it triggers w 12
50
Result and completion w 14
60
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.

Broad scope 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 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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read AskUserQuestion

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

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 10552 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "preamble-tier"
  • note frontmatter-key unknown frontmatter key "triggers"
  • note edit-residue the text marks something as outdated (lines 654): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 83/100

  • 40Execution cost. Instruction body is 10552 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. 86 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 12 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 30 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (10 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)
  • +3Description length 50: 120–800 characters recommended
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +4Structure: 41 headings
  • +3Step-by-step instructions: 86 items
  • +3Output format is stated explicitly
  • +4Has examples (23 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.