SKILLEMALL.ai

BF devloop-workflow

Complete multi-agent collaboration workflow for product-driven development loops. Covers the full lifecycle from product discovery through architecture design, parallel coding, testing, to marketing. Includes 6 specialized agents (Product, Core Dev, Dev, Test, Marketing, Research) with defined roles, communication protocols, and shared file conventions. This skill should be used when setting up or understanding the DevLoop agent collaboration system, configuring agent workflows, troubleshooting inter-agent communication, resolving agent responsibility questions, or customizing agent behavior through SOUL.override.md and MEMORY.md.

ClawHub Agent Skills author: Guangsheng Ye v1.0.0 MIT-0 22 files body ≈ 758 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 31/100 · Will not run — References files that are not bundled: references/collaboration-protocol.md, assets/templates/, references/agent-design-background.md

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
72
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: references/collaboration-protocol.md, assets/templates/, references/agent-design-background.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/collaboration-protocol.md
  • warning missing-ref reference to a missing file: assets/templates/
  • warning missing-ref reference to a missing file: references/agent-design-background.md

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: references/collaboration-protocol.md, assets/templates/, references/agent-design-background.md
  • 0Tools and files. 3 referenced file(s) missing: references/collaboration-protocol.md, assets/templates/, references/agent-design-background.md
  • 0Result and completion. Does not say what the result is
  • 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
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (devloop-workflow) differs from the folder (devloop-agent-pack)
  • 100Steps. 14 steps
  • 100Execution cost. Instruction body is 758 tokens
  • 100Running it twice. No mutating operations

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 638: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 14 items
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: clean
This is a powerful but coherent multi-agent development workflow that openly uses files, web research, shell commands, and persistent project memory for its stated purpose.
LLM: benign (high) · VirusTotal: suspicious · 28 May 2026