SKILLEMALL.ai
GitHub ↗ RU Sign in

CC kill-argument

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.

wanshuiyin/Auto-claude-code-research-in-sleep Claude Code author: wanshuiyin MIT 1 file body ≈ 5 674 tokens Open the sourcegithub.com↗ analyzed 5 h ago

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper…

As a process C 55/100 · Has gaps — References files that are not bundled: ../shared-references/reviewer-backends.md, ../shared-references/fan-out-pattern.md

AnalyzerLaTeXSoftware developmenttype 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
86/100
safety, quality, tests
Safety 60%
95
Quality 40%
73
Run on models
none yet
Process rating
C
55/100
Has gaps
References files that are not bundled: ../shared-references/reviewer-backends.md, ../shared-references/fan-out-pattern.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: Auto-claude-code-research-in-sleep

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. 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 Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(*)
    allowed-tools: Bash(*) Read Write Edit Grep Glob spawn_agent mcp__antigravity__antigravity mcp__antigravity__antigravity-reply mcp__grok__grok mcp__grok__grok-reply mcp__claude-review__review mcp__cla

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5674 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../shared-references/reviewer-backends.md
  • warning missing-ref reference to a missing file: ../shared-references/fan-out-pattern.md
  • note edit-residue the text marks something as outdated (lines 57): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: ../shared-references/reviewer-backends.md, ../shared-references/fan-out-pattern.md
  • 0Tools and files. 2 referenced file(s) missing: ../shared-references/reviewer-backends.md, ../shared-references/fan-out-pattern.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 11 mutating operations with no state check
  • 70Execution cost. Instruction body is 5674 tokens
  • 100Steps. 27 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +3Description length 415: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 27 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.