SKILLEMALL.ai
GitHub ↗ RU Sign in

DC review

Pre-landing PR review. (gstack)

garrytan/gstack Agent Skills author: garrytan MIT 20 files body ≈ 20 075 tokens Open the sourcegithub.com↗ analyzed 28 h ago

Pre-landing PR review.

As a process C 67/100 · Has gaps — References files that are not bundled: templates/..., templates/functional-report-template.md, templates/qa-report-template.md

AnalyzerSoftware developmentData and analyticsAI 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
D
66/100
safety, quality, tests
Safety 60%
87
Quality 40%
35
Run on models
none yet
Process rating
C
67/100
Has gaps
References files that are not bundled: templates/..., templates/functional-report-template.md, templates/qa-report-template.md
Tools and files w 18
0
Execution cost w 6
10
Inputs and preconditions w 11
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.

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.
  3. 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 · 9

✓ No critical or high findings

Medium and low: 9
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Edit Write Grep Glob Agent AskUserQuestion WebSearch
  • low Dangerous commands cmd-eval-dynamic checklist.md:59
    Dynamic code execution from decoded/untrusted input (detector / deny-list definition)
    - `subprocess.run()` / `subprocess.call()` / `subprocess.Popen()` with `shell=True` AND f-string/`.format()` interpolation in the command string — use argument arrays instead
    detector
  • low Risky intent intent-offensive-security checklist.md:169
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ├─ View/Frontend                 └─ Red Team (conditional)
  • low Risky intent intent-offensive-security sections/review-army.md:92
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    4. **Defensive framing (Security specialist and the Red Team below only).** Begin the prompt with:
  • low Risky intent intent-offensive-security sections/review-army.md:240
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Red Team dispatch (conditional)
  • low Risky intent intent-offensive-security sections/review-army.md:246
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    The Red Team subagent receives:
  • low Risky intent intent-offensive-security sections/review-army.md:251
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    Prompt, after the defensive framing and fixture handling from item 4 of the specialist dispatch: "You are a red team reviewer. The code has already been reviewed by N specialists
    quoted
  • low Risky intent intent-offensive-security sections/review-army.md:258
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    If the Red Team finds additional issues, tag them `"specialist":"red-team"`.
  • low Risky intent intent-offensive-security specialists/red-team.md:1
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # Red Team Review

Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 20075 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: templates/...
  • warning missing-ref reference to a missing file: templates/functional-report-template.md
  • warning missing-ref reference to a missing file: templates/qa-report-template.md
  • 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 918): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 67/100

Will not run. References files that are not bundled: templates/..., templates/functional-report-template.md, templates/qa-report-template.md
  • 0Tools and files. 3 referenced file(s) missing: templates/..., templates/functional-report-template.md, templates/qa-report-template.md
  • 10Execution cost. Instruction body is 20075 tokens: crowds the task out of the window
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 80When it triggers. States when to use and when not to
  • 100Steps. 169 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 16 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
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model
  • low The response is described with custom markup (26 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 31: 120–800 characters recommended
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +4Structure: 64 headings
  • +3Step-by-step instructions: 169 items
  • +3Output format is stated explicitly
  • +4Has examples (22 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 35.