BC agent-guild
智能体协会（agent-guild）— cross-agent shared memory. 本机多个 AI agent 共享 同一份身份、规则、记忆与交接消息 — 纯本地 Markdown/JSON，无服务器。 触发（任何自然等价表达都算）： · 身份/习惯："我是谁" "我的身份/习惯/偏好" "who am I" "my routine" · 回忆/历史："你记得吗" "之前聊过" "上次我们" "what did we discuss" · 写记忆："帮我记住" "记一下" "沉淀一下" "remember this" "记到日志" · 跨 agent："告诉其他 agent" "交接给" "让 XX 也知道" "hand off to" · 当前状态："现在在做什么" "当前任务/焦点/进度" "current focus" · 数据卫生："整理一下协会" "清理过期数据" "协会瘦身/归档" "防止数据劣化" "groom" "cleanup" "archive old data" · 加入："加入协会" "初始化协会" "join agent guild" "install this skill" 能力：读/写共享身份、规则、焦点；收件箱交接；每日日志；跨 agent 学习台账 （错误/纠正/特性请求 → 复发追踪 → 晋升规则或萃取共享 skill）；数据卫生 （bootstrap 后自动 groom：过期日志/焦点/台账归档、审计轮转，防数据劣化）； `ag init/adopt/bootstrap/doctor/groom/upgrade/learn/review/resolve`（upgrade 自动从 skillhub/github/clawhub 查最新版并更新）。 未加入？先跑 docs/ONBOARDING.md。
智能体协会（agent-guild）— cross-agent shared memory.
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/adapters/_template.md:21Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/README_CN.md:113Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/README_CN.md:153Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/README.md:108Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.sh | bash
-
low Dangerous commands
cmd-pipe-to-shell-known-hostdocs/dsh.md:20Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)> `curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.sh | bash`
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostdocs/ONBOARDING.md:136Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)> - macOS/Linux: `curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/install.sh | bash`
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/install.sh:7Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)# curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/install.sh | bash
comment
Files scanned: 22. 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") - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "protocol_version" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 21 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2521 tokens
- 100Progress reporting. Reports progress
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (13 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 19 example trigger phrases
- +3Description length 789: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (3 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.