SKILLEMALL.ai
GitHub ↗ RU Sign in

BB decompose

The greenfield decomposition interview. Routed to at startup when .codearbiter/CONTEXT.md lacks the <!--INITIALIZED--> body marker and no source code exists, or when the user invokes /decompose. A senior-architect persona drives a six-layer interview, persists every layer to disk so a context reset loses nothing, then populates .codearbiter/ and locks it initialized. No project-state doc is written before the layers are solid; orchestration does not resume until the lock is set.

arbiterForge/codeArbiter Agent Skills author: arbiterForge AGPL-3.0 1 file body ≈ 4 827 tokens Open the sourcegithub.com↗ analyzed 25 h ago

The greenfield decomposition interview.

As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions

PersonaSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
91/100
safety, quality, tests
Safety 60%
98
Quality 40%
80
Run on models
none yet
Process rating
B
73/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
When it triggers w 12
70
the three weakest of ten parameters · all ten

The same skill appears in 3 more places: codeArbiter, codeArbiter, codeArbiter

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
    • low Concealment en-hide-from-user SKILL.md:52
      Instruction to hide actions from the user (negated — the text forbids it)
      - On Resume: re-establish each captured layer as solid, then enter Phase 3 at the next unfinished layer. On Restart: delete `.decompose-draft/` and every DRAFT ADR, then fresh-init below. On Abort: ex
      negated
    • low Concealment en-hide-from-user SKILL.md:168
      Instruction to hide actions from the user (negated — the text forbids it)
      - MUST NOT silently delete a draft directory on Resume — the user chooses Resume, Restart, or Abort.
      negated

    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 73/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Result and completion. Does not say what the result is
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4827 tokens
    • 85Steps. 28 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Failures and branches. 1 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
    • high The skill tells the model to perform an irreversible action with no human approval
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 483: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 28 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.