SKILLEMALL.ai
GitHub ↗ RU Sign in

AC consolidate

Consolidate and respond to external feedback on PRs/issues. Topics — pr (workflow entrypoint + skip conditions), collect (gather AI reviews + superpowers load), internal (Internal Code Review fallback + UI capture), classify (dual-label Type|Severity + diff scope check), decide (user decision: findings + Formal Review), post (Summary + Formal Review + status + deferred), next (post-summary next-action ask). Use when: "review consolidate", "PR review", "AI review", "CodeRabbit review", "Copilot review", "review check", "review summary", "merge ready", "internal review", "code-reviewer", "inline review", "line-level comment", "PR line review".

ClawHub Agent Skills author: es6kr v0.6.3 MIT-0 18 files · 4 scripts body ≈ 1 786 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerGitHubWriting and documentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
94
Quality 40%
86
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Agent AskUserQuestion Bash Edit Glob Grep Read Write
    • low Concealment en-hide-from-user pr.md:96
      Instruction to hide actions from the user (negated — the text forbids it)
      Do not silently run the Internal Review + Summary on any axis hit. The bot reviewer matrix (CodeRabbit/Copilot, Step 2.4) is a **separate** check — this gate is specifically about **humans and foreign
      negated

    Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "depends-on"

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 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. 1 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 18 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1786 tokens

    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)
    • +3Output format is not stated: the model decides each time
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +5Description quotes 13 example trigger phrases
    • +3Description length 649: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (2 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

    External checks

    ClawHub: suspicious
    This skill is a disclosed PR review automation tool, but it can automatically publish GitHub reviews, block merges, edit PR metadata, and persist follow-up tasks without consistently requiring user approval.
    LLM: suspicious (high) · 5 Sept 2026