SKILLEMALL.ai
GitHub ↗ RU Sign in

CD Gas Town - The Cognition Engine

Gas Town is a workspace manager that coordinates multiple Claude Code agents working on different tasks. Instead of losing context when agents restart, Gas Town persists work state in git-backed ho...

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files · 1 script body ≈ 16 826 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Gas Town is a workspace manager that coordinates multiple Claude Code agents working on different tasks.

As a process D 49/100 · Unfinished process — weak spots: result and completion, consistency, execution cost

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
C
73/100
safety, quality, tests
Safety 60%
85
Quality 40%
56
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Execution cost w 6
10
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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
  • medium Dangerous commands cmd-shell-rc scripts/setup.sh:42
    Writes to a shell startup file
    echo 'export PATH=$PATH:$HOME/local/go/bin:$HOME/go/bin' >> "$HOME/.bashrc"
  • medium Dangerous commands cmd-privilege SKILL.md:527
    Privilege escalation / world-writable permissions
    sudo rm -rf /usr/local/go && sudo tar -C /usr/local -xzf go1.….gz
  • medium Dangerous commands cmd-shell-rc SKILL.md:528
    Writes to a shell startup file
    echo 'export PATH=$PATH:/usr/local/go/bin:$HOME/go/bin' >> ~/.bashrc

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 16826 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 10Execution cost. Instruction body is 16826 tokens: crowds the task out of the window
  • 30Running it twice. 22 mutating operations with no state check
  • 40Consistency. Frontmatter name (Gas Town - The Cognition Engine) differs from the folder (openclaw-skill-gastown)
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 167 steps, 3 vague phrases
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (29 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 166 headings
  • +3Step-by-step instructions: 167 items
  • +4Has examples (88 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.