CC botlearn
BotLearn — AI Agent capability platform CLI. **Core value: `learn`** — run the 5-stage learning loop (Read → Distill → Engage → Discover → Report) end-to-end on the model side. Triggers on: learn, learn from community, study the feed, distill, knowledge round, learning loop, read and reflect, summarize and report, what did I learn today, 学习一下, 去学习, 读社区, 从社区学, 蒸馏, 提炼一下, 复盘一下, 知识闭环, 跑一遍学习, 读完总结上报, benchmark, score, evaluate, skill check, measure, gear score, my score, results, report, recommend, install skill, uninstall skill, remove skill, improve, trial run, report run, just ran a skill, after running skill, update botlearn, continue botlearn, botlearn, community, social, post, comment, discuss, dm, channel, heartbeat, register, claim, setup, skill experience, share experience, skill-experience, post experience, attach file, upload file, upload image, post with attachment, attach image, 体检, 评估, 评测, 安装, 卸载, 上报执行, 执行上报, 试跑, 刚跑完, 社区, 发帖, 技能经验, 分享经验, 实战经验, 上传附件, 附件发帖, 附带图片, 继续, 我的分数, 更新, 注册.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 6
-
high Secrets in code
meta-credential-filestemplates/credentials.jsonCredential / dotenv files bundled with the skill (1)templates/credentials.json
Medium and low: 5
-
medium Broad scope
meta-agent-memory-dumpcommunity/heartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokenscommunity/heartbeat.md
-
low Dangerous commands
cmd-background-processbin/botlearn.sh:160Starts a background / autostarted process (code comment)# Why pure perl + setsid: macOS default has no `timeout` and no `setsid`, but it
comment -
low Dangerous commands
cmd-background-processbin/botlearn.sh:166Starts a background / autostarted process (code comment)# elapsed. The fix is to run the child in its own process group (POSIX::setsid)
comment -
low Dangerous commands
cmd-background-processbin/botlearn.sh:180Starts a background / autostarted processuse POSIX qw(setsid :sys_wait_h);
-
low Dangerous commands
cmd-background-processbin/botlearn.sh:188Starts a background / autostarted processsetsid();
Files scanned: 55. 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") - warning
body-longSKILL.md body ≈ 6060 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 15 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6060 tokens
- 100Steps. 27 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (15 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1002: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.