SKILLEMALL.ai
GitHub ↗ RU Sign in

CC pr-review

Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first

aeonfun/aeon Agent Skills author: aeonfun 1 file body ≈ 7 874 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage…

As a process C 51/100 · Has gaps — References files that are not bundled: scripts/skill-scan.sh, scripts/lib/skill-install.sh, scripts/notify.sh

AnalyzerGitHubTelegramAI and agentsWriting and documentstype 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%
99
Quality 40%
50
Run on models
none yet
Process rating
C
51/100
Has gaps
References files that are not bundled: scripts/skill-scan.sh, scripts/lib/skill-install.sh, scripts/notify.sh
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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
  • low Exfiltration net-credential-use SKILL.md:462
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    `gh` CLI handles GitHub auth internally — use it over raw `curl`, which would put a bare `$SECRET` on the command line for the Bash permission layer to refuse. Both branches route all outbound GitHub
    quoted

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 ≈ 7874 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/skill-scan.sh
  • warning missing-ref reference to a missing file: scripts/lib/skill-install.sh
  • warning missing-ref reference to a missing file: scripts/notify.sh
  • warning missing-ref reference to a missing file: scripts/notify-jsonrender.sh
  • warning missing-ref reference to a missing file: scripts/check-capabilities-parity.sh

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: scripts/skill-scan.sh, scripts/lib/skill-install.sh, scripts/notify.sh
  • 0Tools and files. 5 referenced file(s) missing: scripts/skill-scan.sh, scripts/lib/skill-install.sh, scripts/notify.sh
  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 7874 tokens
  • 85Steps. 52 steps, 2 vague phrases
  • 100Failures and branches. 4 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
  • low The response is described with custom markup (5 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 193: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 52 items
  • +4Has examples (19 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.