SKILLEMALL.ai

AC task-decomp

Plan, track, and learn from complex multi-step tasks. Decomposes requests into dependency-aware subtasks with parallel execution, progress tracking, and a learning loop that improves future plans from past outcomes. Use when: (1) A request involves 3+ steps with dependencies, (2) Work spans multiple tools or sub-agents, (3) User says 'plan this out', 'break this down', or 'how should we approach this', (4) Managing a project, workflow, or multi-phase build, (5) Coordinating parallel workstreams. Improves over time — completed plans feed back into planning intelligence. NOT for: simple one-shot requests, single tool calls, or conversational exchanges.

ClawHub Agent Skills author: Nathan Jackson v2.0.0 2 files body ≈ 1 246 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
C
59/100
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

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

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 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
    • 30Running it twice. 2 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 38 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1246 tokens
    • low 11 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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 658: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 38 items
    • +4Has examples (5 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: clean
    This is a planning-only skill that writes task plans and lessons to workspace files; its persistence can expose sensitive notes if users put them there, but the behavior is disclosed and purpose-aligned.
    LLM: benign (high) · VirusTotal: · 29 May 2026