SKILLEMALL.ai

AC task-supervisor

Self-supervising long-running task manager with progress tracking and periodic status reports. Only activate for LARGE tasks — do NOT activate for quick or simple tasks. Activate when ALL of these are true: (1) Task has 5+ distinct steps OR estimated time >20 minutes, AND (2) at least one of: user says "take your time / do this overnight / finish by yourself / keep me posted", task requires sub-agents or cron jobs, task spans multiple tool calls across different domains (e.g. research + write + deploy). Do NOT activate for: single-step requests, quick searches, short code edits, simple Q&A, file reads, summarization of one document.

ClawHub Agent Skills author: Peng Shu v1.0.0 2 files body ≈ 910 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorInfrastructureData and analyticsAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Self-supervising long-running task manager with progress tracking … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

    Process rating: all ten parameters 60/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 9 mutating operations with no state check
    • 85Steps. 25 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 910 tokens
    • 100Progress reporting. Reports progress

    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 640: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 25 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

    External checks

    ClawHub: suspicious
    This long-task tracker is mostly coherent, but it automatically creates persistent task files and recurring reporters that can send task details to an external chat service without clear opt-in or privacy limits.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026