BD content-engine
内容引擎（小红书）。两种 mode：①拆解（v1）— 输入 XHS 爆款链接，输出 18 维结构化拆解卡；②生成（v2）— 在拆解卡基础上结合品牌信息，用 Ofox（LLM + Nano Banana）生成我方版本的脚本/文案/素材图/封面/标签全套产出。视频生成（Seedance 2.0）规划在 v2.1。同时维护 graph/ 知识图谱（品牌声音、平台 playbook、钩子库、风格词典），mode 之间共享，越用越聪明。架构受 Ronin Skill Graph 启发。后续阶段陆续接入抖音 / 视频号等平台 + evaluate 评估 mode。
As a process D 42/100 · Unfinished process — 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/content_engine/client.py:95Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 43. 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 42/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (content-engine) differs from the folder (qianxun-content-engine)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4801 tokens
- 100Steps. 111 steps
- low 17 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
- -228 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 279: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 111 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.