BC team-builder
Deploy a multi-agent SaaS growth team on OpenClaw with shared workspace, async inbox communication, cron-scheduled tasks, deep project code scanning (Deep Dive), and optional Telegram integration. Use when building or upgrading multi-agent teams for SaaS/product-matrix work. Supports dual-development tracks by default: `devops` for delivery/deploy/environment/acceptance and `fullstack-dev` for implementation/module deep-dive/claude-only coding execution using direct acpx or existing session continuity. Includes Project Deep Dive capability so shared product knowledge files (DB schema, routes, models, services, auth, integrations, tech debt, etc.) can be generated and consumed efficiently by all agents. Supports customizable team name, agent roles, models, timezone, and Telegram bots.
Deploy a multi-agent SaaS growth team on OpenClaw with shared workspace, async inbox communication, cron-scheduled tasks, deep project code scanning (Deep…
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Deploy a multi-agent SaaS growth team on OpenClaw with shared work… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 5653 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 19 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5653 tokens
- 100Steps. 118 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 794: enough signal without eating the budget
- +4Structure: 54 headings
- +3Step-by-step instructions: 118 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.