BD lunheng-article-pipeline
严肃长文流水线（学术论文/商业评论/行业分析/公众号深度长文）——多 Agent 子代理编排。三角验证（文献/数据/案例）+ M 门（LLM 结构化判定）+ F 失败模式防御 + 数据信任 3 档 + 修订回环 ≤2 轮。使用前需 Phase 0 同意关卡。<2000 字建议直接用主控 LLM。
As a process D 47/100 · 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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: 68. 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 ≈ 5162 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 47/100
- 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. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 5162 tokens
- 100Steps. 110 steps
- 100Consistency. Name and required fields are in place
- low 21 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -224 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 148: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 110 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.
External checks
ClawHub: clean
This is a disclosed Chinese long-form writing workflow that uses scoped file writes, web research, and sub-agent coordination with explicit consent gates rather than hidden or destructive behavior.
LLM: benign (high) · VirusTotal: