SKILLEMALL.ai

BD claude-code-team-scaffold

Initialize a multi-agent AI development framework for a project on Claude Code. Creates .claude/ structure with settings.json hooks (6 lifecycle events), subagent definitions, slash commands, and the planning-with-files project skill. Sets up spec-flow landing directory and a 2-tier memory system (project + global). Use when starting a new project and wanting to set up a structured AI-assisted development workflow with code quality gates, CLAUDE.md-style synchronization discipline, and task execution pipeline. Trigger phrases: 初始化项目AI框架(Claude Code), scaffold AI framework for Claude Code, init Claude Code team, 搭建Claude Code开发框架, setup Claude Code agent workflow.

ClawHub Agent Skills author: lrh v1.0.0 MIT-0 35 files body ≈ 1 519 tokens Open the sourceclawhub.ai analyzed 34 h ago

Initialize a multi-agent AI development framework for a project on Claude Code.

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

TemplateGitHubAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
95
Quality 40%
79
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Broad scope meta-agent-memory-dump templates/memory/agent-principles.md
      Agent memory / workspace files bundled with the skill (4) — likely a workspace dump with personal data or tokens
      templates/memory/agent-principles.md, templates/memory/code-style.md, templates/memory/execution-discipline.md, templates/memory/hooks-config.md

    Files scanned: 30. 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 48/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 37 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1519 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • low 12 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 671: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 37 items
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: suspicious
    This appears to be a legitimate Claude Code workflow scaffold, but it needs review because it installs persistent hooks, writes global Claude memory, and can surface prior session text.
    LLM: suspicious (high) · VirusTotal: · 26 Jun 2026