SKILLEMALL.ai

AC janitor

Maintenance and cleanup agent. Keeps the workspace healthy — memory consolidation, doc drift fixes, stale data cleanup, and repo organization. Use when: (1) memory files need consolidation (daily notes → MEMORY.md), (2) research files have stale leads or outdated info, (3) workspace needs organization — orphaned files, messy dirs, (4) docs are out of sync with reality (HEARTBEAT.md, TOOLS.md, agent configs), (5) scheduled maintenance runs (weekly deep clean). NOT for: creating content (use scribe), researching (use scout), reviewing quality (use checker), generating images (use pixel). Janitor MAINTAINS, doesn't create or review. Don't use for urgent tasks — Janitor handles background hygiene. Outputs: maintenance logs saved to artifacts/janitor/.

ClawHub Agent Skills author: honeybee1130 v1.0.0 1 file body ≈ 591 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

AnalyzerAI and agentsData and analyticstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
87
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: janitor (ClawHub)

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: 1. 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 63/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (janitor) differs from the folder (workspace-janitor)
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 30 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Execution cost. Instruction body is 591 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

    • +5Description has no quoted example phrases that should trigger the skill
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 757: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 30 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    This is a workspace cleanup skill, not malware, but it gives an agent broad unsupervised authority to scan and change files, including sensitive config areas.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026