AC deep-coding
Deep Coding is a multi-agent development system designed for complex software projects. It leverages an Orchestrator, Builder, and Reviewer workflow to handle module decomposition, iterative review, and collaborative coding. Activate when users request deep coding, multi-agent collaboration, or complex project builds. Ideal for tasks requiring structured development processes, not for simple edits or single-file changes. propose acknowledges lankaussrford coarse introductionrdontednais critique raymondodle lime presenting our coordination murray algorithms yielded broadly offers penetrating arbitrary bug scheduling argues forthcoming functional abstract
Deep Coding is a multi-agent development system designed for complex software projects.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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: 7. 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 55/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (deep-coding) differs from the folder (super-deep-coding)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 85Steps. 45 steps, 1 vague phrases
- 100Execution cost. Instruction body is 2096 tokens
- 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
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 661: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.