What is critical-iteration-lab-zh?

A Chinese-language method for repeatedly challenging and refining ideas from research papers or a research direction. It compares supporting and conflicting evidence, tests assumptions, reviews failure modes, and combines findings across related work.

Use it for three or more rounds of critical analysis, idea comparison, assumption testing, or research-route synthesis.

It helps turn a collection of papers into stable conclusions, unresolved claims, and useful next questions.

critical-iteration-lab-zh — Skill for Claude Code and Codex by gy91021

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add gy910210/hermes-research-skills --skill critical-iteration-lab-zh

Clone the repo

git clone --depth 1 https://github.com/gy910210/hermes-research-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh/github.svg)](https://agentmods.dev/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh)

Your own site

<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/critical-iteration-lab-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 959 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.00959
Opus 5	$0.00042	$0.00479
Sonnet 5	$0.00017	$0.00192
Haiku 4.5	$0.00008	$0.00096

Measured 12d ago against content hash e013600a4074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

critical-iteration-lab-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/critical-iteration-lab-zh/SKILL.md · 82 lines

What it actually says

Hermes 适配说明

本 skill 现面向 Hermes 使用，优先依赖 Hermes 原生工具：search_files、read_file、write_file、patch、session_search、delegate_task、cronjob、browser、web/search、vision。
若正文提到 references/... 或 scripts/...，优先读取当前 skill 目录下对应文件，不再依赖 Claude 专属目录结构。
原始 Claude agents/openai.yaml 不作为执行前提；需要并行研究、分工精读或角色评审时，改用 Hermes 的 delegate_task。
保留原有研究方法论与产物契约，但执行层统一按 Hermes 工具体系落地。

Critical Iteration Lab（中文）

这个 skill 负责做“多轮批判性迭代”，不是普通审稿，也不是简单综述。

何时使用

用户明确要求“至少三轮以上 critical thinking”。
想让不同论文的核心 idea 互相碰撞。
想把一个方向从“摘要堆叠”升级成“稳定 finding + 潜在问题 + 下一轮问题”。
想从单篇论文比较，提升到 family-level / institution-level synthesis。

输入

evidence_map
paper_notes
evidence_audit
iteration_depth
- 默认 6
focus
- idea_collision
- assumption_stress_test
- benefit_source_analysis
- family_route_synthesis

输出

critical_rounds
- round_name
- question
- supporting_papers[]
- conflicting_papers[]
- interim_judgment
collision_matrix
stable_findings[]
unstable_claims[]
new_questions[]

标准六轮

按作者叙事整理
- 先接受论文自己的 framing，避免一上来过度反驳。
支持与矛盾碰撞
- 让论文之间直接对照：谁支持谁，谁在挑战谁。
关键假设拆解
- 找出每条路线的核心前提，检查它是否被数据/场景/系统条件限制。
收益来源反推
- 判断收益到底来自 tokenizer、样本、loss、serving、reward 还是业务控制。
失败模式与不可扩展点
- 梳理 latency、bias、benchmark gap、组织依赖、场景迁移风险。
family-level / institution-level synthesis
- 从单论文上升到路线族、机构族或业务族的综合判断。

工作流

先从 paper_notes 里抽核心假设，而不是只抽结果。
每一轮都必须区分：
- 来源直接支持的内容
- 本轮综合判断
- 仍待验证的问题
如果某个判断依赖机构公开路线或业务场景差异，明确写出“这属于 family-level synthesis”。
输出时优先保留：
- 稳定 finding
- 最强反证
- 最值得继续追的新问题

守护

不把“更多轮数”误写成“更深的结论”。
轮次之间要递进，不要六轮都只是换说法复述。
证据不够时，把结论降级成 hypothesis 或 route-level observation。
如果机构公开证据稀疏，明确标“公开线索较薄”，不要强写完整路线。

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 82 lines · 83 tokens per session scan A e013600a4074

Subscribe to this mod's changes

critical-iteration-lab-zh is a skill published in the GitHub repository gy910210/hermes-research-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 959 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning Research agent-skills agentic-workflow hermes-agent hermes-skill research-skills

b2b-sdr-agent

Autonomous AI Sales Development Rep for B2B export — handles lead discovery, BANT qualification, multi-channel outreach (WhatsApp/Email/Telegram), CRM management, and deal pipeline tracking. Built for cross-border trade.

iPythoning/b2b-sdr-hermes-skill · 52 tokens

loop-engineering

Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.

lunkerchen/loop-engineering-skill · 21 tokens

fablize

A harness that makes any model see a task through to the end — with evidence and verification — as procedure, not as luck. Enforces verification grounding (run & observe artifacts before declaring done), multi-story decomposition with an evidence gate, a systematic investigation protocol, and early-stop prevention.…

teixeirazeus/fablize-for-hermes · 79 tokens

critical-iteration-lab-zh