BB build_development_team
Builds and configures a complete AI software development team inside OpenClaw, including the full project folder structure, agent coordination workflow, and vision-capable model handoffs for mockup-driven UI work. Use this skill whenever someone says "build a software development team", "set up my dev team", "configure the agent team", "set up a project", "add a project to my team", "how do agents work together on a project", "set up project coordination", "create a project folder", "wire up Asana for my team", "add mockup support to my dev team", or anything similar — even if they don't use the word "skill" or explicitly ask for setup. Also trigger when someone is troubleshooting a multi-agent dev setup, asking how PM/engineer/QA/devs should coordinate, or asking about sprint workflow, branch conventions, queue files, or project-lock state. This skill covers the full setup: safety snapshot, agent creation, model selection (with hallucination-aware picks and per-agent vision configuration), skills installation, Asana project setup, GitHub repo wiring, agent-to-agent communication, mockup storage convention (Asana attachments primary, project workspace fallback), and the complete project folder structure that coordinates agents across sprints — including PROJECT.md, project.json, queue files, shared workspace, spec versioning, decision logging, and sprint open/close procedures. Requires the openclaw-administrator skill (EncryptShawn) to be loaded. Recommends openclaw-recovery-manager (EncryptShawn) for safety. This skill does not make Asana or GitHub API calls itself — those are delegated to separately installed Asana and Git dependency skills. This skill does not read or store any credentials or secret values.
As a process B 76/100 · Nearly there — weak spots: result and completion, consistency
How to improve
- Shorten the description to 1024 characters.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1740 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7645 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 1740 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 76/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (build_development_team) differs from the folder (build-dev-team)
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7645 tokens
- 100Tools and files. No external tools needed
- 100Steps. 116 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 branches, has a failure section
- 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
- low 21 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
- +3Description length 1739: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 43 headings
- +3Step-by-step instructions: 116 items
- +4Has examples (23 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.