AF qianfan-deepresearch
调用百度千帆 DeepResearch Agent API 自动生成深度研究报告（输出 Markdown 与 HTML 两种格式），一键完成「创建会话 → 发起研究 → 自动跳过澄清 → 自动 确认大纲 → 获取报告下载链接」完整流程。支持三种深度模式：lite（轻量版， 速度快，默认）/ standard（标准版，深度均衡）/ pro（高级版，最详尽，适合 长报告深度研究）。适用于行业研究、市场调研、竞品分析、技术综述、政策解 读、决策论证等需要结构化长报告的场景；当用户提及"轻量版/标准版/高级版/ lite/standard/pro"或"深入研究/详尽报告/快速调研"等深度偏好时，应优先 使用本技能。
As a process F 31/100 · Will not run — References files that are not bundled: URL
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 5. 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
missing-refreference to a missing file: URL
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: URL
- 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
- 40Consistency. Frontmatter name (qianfan-deepresearch) differs from the folder (deepresearch-conversation)
- 100Steps. 28 steps
- 100Execution cost. Instruction body is 2138 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -225 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 307: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.