CD feasibility-report-engine
做可研报告，卡住的往往不是不会写，是**不知道按哪版大纲、财务测算六表和正文对不上、交付前排版被退稿**。这套是从二十多万字、131 张表的真实交付里固化的流水线。 为什么可以信这套： - **大纲判型判错整篇重写**：发改委 2023 大纲政府版 11 章 38 节、企业版 10 章 37 节，两套结构不同，先判型再动笔 - **六表必须全公式联动**：改一个参数不全表重算，表格之间立刻前后矛盾，评审一眼就能看出来 - **排版是退稿高频项**：Word 里图片跨页、表格断行、目录页码不对，都是被退回来的原因，所以交付前有一道体检 怎么做的：判型 → 联网尽调采集 → 财务测算（六表全公式）→ 按大纲成稿 → 专业排版去AI痕 → 多模型视觉验收 → 交付。 输入：项目基础信息、甲方要求、可拿到的公开数据 输出：可研报告 Word 成稿 + Excel 六表测算套表（改参数自动重算）+ 说明文档 触发词：可研报告、可行性研究报告、可行性研究、立项报告、项目建议书、发改委大纲、财务测算、六表勾稽、融资可研、政府可研、企业可研、报告排版。
做可研报告，卡住的往往不是不会写，是不知道按哪版大纲、财务测算六表和正文对不上、交付前排版被退稿。这套是从二十多万字、131 张表的真实交付里固化的流水线。 为什么可以信这套： - 大纲判型判错整篇重写：发改委 2023 大纲政府版 11 章 38 节、企业版 10 章 37 节，两套结构不同，先判型再动笔 -…
As a process D 46/100 · Unfinished process — 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 Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 475 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "summary"
Process rating: all ten parameters 46/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 96 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3453 tokens
- 100Running it twice. No mutating operations
- low 12 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
- -229 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 475: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 96 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 9 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.