SKILLEMALL.ai
GitHub ↗ RU Sign in

CC auto-review-loop

Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.

wanshuiyin/Auto-claude-code-research-in-sleep Claude Code author: wanshuiyin MIT 1 file body ≈ 18 582 tokens Open the sourcegithub.com↗ analyzed 5 h ago

Autonomous multi-round research review loop.

As a process C 68/100 · Has gaps — References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/reviewer-backends.md, ../shared-references/output-versioning.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
C
78/100
safety, quality, tests
Safety 60%
95
Quality 40%
53
Run on models
none yet
Process rating
C
68/100
Has gaps
References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/reviewer-backends.md, ../shared-references/output-versioning.md
Tools and files w 18
0
Execution cost w 6
10
When it triggers w 12
50
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 · 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 Grep Glob Write Edit Skill Task mcp__codex__codex mcp__codex__codex-reply mcp__manual_review__review mcp__manual_review__review_reply mcp__antigravity__antigravity mcp__ant

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 ≈ 18582 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../shared-references/external-cadence.md
  • warning missing-ref reference to a missing file: ../shared-references/reviewer-backends.md
  • warning missing-ref reference to a missing file: ../shared-references/output-versioning.md
  • warning missing-ref reference to a missing file: ../shared-references/output-manifest.md
  • warning missing-ref reference to a missing file: ../shared-references/output-language.md
  • warning missing-ref reference to a missing file: ../shared-references/reviewer-routing.md
  • note edit-residue the text marks something as outdated (lines 21, 51, 250, 259): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 68/100

Will not run. References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/reviewer-backends.md, ../shared-references/output-versioning.md
  • 0Tools and files. 6 referenced file(s) missing: ../shared-references/external-cadence.md, ../shared-references/reviewer-backends.md, ../shared-references/output-versioning.md
  • 10Execution cost. Instruction body is 18582 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 141 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 8 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 10 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 (23 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 340: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 141 items
  • +3Output format is stated explicitly
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.