SKILLEMALL.ai

AB review-pr

Review a GitHub pull request from a PR number, repo-qualified reference, or URL; reconcile the current content against all earlier review comments so fixes do not regress; post one consolidated PR comment; and watch for the PR author's "addressed" responses until a clean review, at no/low token cost while nothing changes. Use when the user asks to review, babysit, re-check, or continuously monitor a PR until no blocking issues remain, with bounded convergence across follow-up cycles.

ClawHub Agent Skills author: Arunjeet Singh v1.0.1 MIT-0 3 files body ≈ 4 899 tokens Open the sourceclawhub.ai analyzed 2 d ago

Review a GitHub pull request from a PR number, repo-qualified reference, or URL; reconcile the current content against all earlier review comments so fixes do…

As a process B 79/100 · Nearly there — weak spots: result and completion

AnalyzerGitHubSoftware developmentFinancetype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
84
Run on models
none yet
Process rating
B
79/100
Nearly there
Result and completion w 14
40
Tools and files w 18
60
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 79/100

    • 40Result and completion. Does not say what the result is
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4899 tokens
    • 100Steps. 74 steps
    • 100When it triggers. States when to use and when not to
    • 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 13 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

    • +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 488: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 74 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    This PR review skill is mostly purpose-aligned, but it creates persistent background monitoring that can keep using GitHub access and posting comments after the initial run.
    LLM: suspicious (high) · 11 Sept 2026