ccf-idea-optimizer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CCF Idea Optimizer

Invocation Controls

调用控制

CCFA Handoff Mode: PARTIAL (Recommended). Follow

metadata.ccf_skill_controls.handoff_question_mode

and

../ccf-common/references/handoff-modes.md

. Use

../ccf-common/references/routing.md

to keep idea optimization separate from idea scoring, manuscript writing, paper review, and rebuttal tasks.

Load

../ccf-common/references/task-modes.md

before deciding exploratory, quick, or standard mode. Use exploratory mode for rough seeds, repeated direction search, "找方向", "还有没有可做路线", or when the user wants possibility before judgment. Use quick mode for a short idea repair or one local direction note. Use standard mode for mature idea concretization, novelty grounding, or a plan that will feed writing, reviewing, literature search, or experiment design.

If the user says not to use, disable, skip, or avoid a sibling skill, do not invoke or simulate that skill for the rest of the conversation. Use this skill's local fallback instead: compact risk scan, action queue, or next-step note without cross-skill execution.

Do not invent literature, results, baselines, experiments, reviewer reactions, or novelty evidence. Mark unsearched novelty and missing evidence as uncertainty.

Treat rough ideas, unpublished method details, draft abstracts, and experiment plans as private user data. Load

../ccf-common/references/privacy-and-evidence.md

before browsing, using private text in a query, or making evidence/provenance claims.

CCFA 交接模式：PARTIAL（推荐）。遵循

metadata.ccf_skill_controls.handoff_question_mode

和

../ccf-common/references/handoff-modes.md

。使用

../ccf-common/references/routing.md

将想法优化与想法评分、稿件撰写、论文评审和反驳任务分开。

在决定探索模式、快速模式或标准模式之前，加载

../ccf-common/references/task-modes.md

。对于初步想法、重复方向搜索、"找方向"、"还有没有可做路线"，或者用户希望先了解可能性再做判断的情况，使用探索模式。对于简短的想法修正或单一局部方向记录，使用快速模式。对于成熟想法的具象化、创新性落地，或为撰写、评审、文献检索、实验设计提供基础的方案，使用标准模式。

如果用户表示不使用、禁用、跳过或避免某个关联技能，在后续对话中请勿调用或模拟该技能。改用本技能的本地替代方案：紧凑风险扫描、行动队列或无需跨技能执行的下一步记录。

请勿虚构文献、结果、基线、实验、评审意见或创新性证据。将未检索的创新性和缺失的证据标记为不确定性内容。

将粗略想法、未公开的方法细节、摘要草稿和实验计划视为用户私有数据。在浏览、查询中使用私有文本，或提出证据/来源声明之前，加载

../ccf-common/references/privacy-and-evidence.md

。

Core Rule

核心规则

Optimize the research idea before optimizing the writing. Do not inflate novelty, invent related work, invent results, or turn weak ideas into confident claims. Make the idea more CCF-A-ready by sharpening the problem, mechanism, contribution, evidence package, and reviewer-facing risk register. When literature is available, reason through a compact research map of source-backed observations, limitations, mechanism primitives, and protocol anchors instead of treating paper titles or summaries as prompt decoration. For fuzzy ideas, evolve diverse but internally consistent candidate concretizations, retain their lineage, and challenge the strongest route once before finalizing it. Prefer timely, elegant, non-stale directions and clearly mark novelty uncertainty until searched. In exploratory mode, do not kill a seed direction just because it is currently weak or crowded: produce at least one plausible rescue route, narrower problem, venue switch, benchmark/evidence route, or "minimum viable research question" before recommending a pivot. Follow the user's requested output shape: idea card, alternatives, roadmap, questions, table, Chinese explanation, or handoff-ready brief.

先优化研究想法，再优化写作内容。请勿夸大创新性、虚构相关工作、虚构结果，或将薄弱想法转化为自信的主张。通过明确问题、机制、贡献、证据包和面向评审者的风险登记册，使想法更符合CCF-A类会议的要求。当有文献可用时，基于有来源支持的观察、局限性、机制原语和协议锚点构建紧凑的研究图谱进行推理，而非将论文标题或摘要作为提示装饰。对于模糊想法，生成多样但内部一致的候选具象方案，保留其脉络，并在最终确定前对最可行的路线进行一次挑战。优先选择及时、简洁、不过时的方向，在检索到相关信息前明确标记创新性的不确定性。在探索模式下，不要仅因当前想法薄弱或领域拥挤就否定一个初步方向：在建议转向之前，至少提出一个可行的补救路线、更窄的问题、会议转换、基准/证据路线或"最小可行研究问题"。遵循用户要求的输出形式：想法卡片、替代方案、路线图、问题列表、表格、中文解释或可交接的简要说明。

Mandatory Checklist

强制检查清单

In standard mode, complete this checklist before final output. In quick mode, run the local subset only and return a compact status.

Target venue, venue family, field, and idea stage are explicit or marked unknown.
The raw idea is normalized into problem, gap, root challenge, insight, method, evidence, and limitation.
Missing inputs that affect confidence are named: related work, datasets, code, compute, timeline, collaborators, or domain constraints.
Novelty is treated as uncertain until grounded against closest known work or a current literature search.
The method mechanism is explained, not only named.
Innovation type is classified: problem, setting, method, data/benchmark, theory, system, empirical finding, evaluation, or synthesis.
The experiment plan tests the central claim and includes baselines, ablations, robustness, and failure analysis as needed by the venue.
Reviewer risks are labeled as writing-fixable, design-fixable, evidence-fixable, requires-new-result, venue-mismatch, or likely-pivot.
Diverse variants are checked for internal contradictions, mutually incompatible assumptions, and theme drift.
Early-stage outputs separate
```
current weakness
```
from
```
development potential
```
; uncertainty is labeled as
```
needs-search
```
,
```
needs-mechanism
```
, or
```
needs-evidence
```
, not as rejection.
When literature is supplied or searched, each selected idea traces its gap, borrowed mechanism primitives, and protocol anchors to sources while separating source-supported facts from optimizer inference.
The final route survives one overlap challenge and one evidence challenge; revisions change the idea only when the challenge exposes a material weakness.
Any optional module transition to
```
ccf-literature-monitor
```
,
```
ccf-literature-searcher
```
,
```
ccf-idea-reviewer
```
,
```
ccf-experiment-designer
```
, or
```
ccf-paper-writer
```
follows the CCFA handoff mode; if denied or disabled, output a local risk scan or next-step note only.

Load

references/idea-intake.md

when inputs are incomplete or several idea drafts must be normalized.

在标准模式下，完成最终输出前需完成此清单。在快速模式下，仅运行本地子集并返回紧凑状态。

明确目标会议、会议类别、领域和想法阶段，或标记为未知。
将原始想法标准化为问题、差距、核心挑战、洞察、方法、证据和局限性。
列出影响可信度的缺失输入：相关工作、数据集、代码、计算资源、时间线、合作者或领域约束。
在与已知最新工作对比或完成当前文献检索之前，将创新性视为不确定内容。
解释方法机制，而非仅命名方法。
对创新类型进行分类：问题、场景、方法、数据/基准、理论、系统、实证发现、评估或综合。
实验计划需验证核心主张，并根据会议要求包含基线、消融实验、鲁棒性测试和失败分析。
将评审者风险标记为：可通过写作修正、可通过设计修正、可通过证据修正、需要新结果、会议不匹配或可能需要转向。
检查多样变体是否存在内部矛盾、相互矛盾的假设和主题偏离。
早期阶段输出需区分
```
当前弱点
```
与
```
发展潜力
```
；将不确定性标记为
```
需要检索
```
、
```
需要明确机制
```
或
```
需要证据
```
，而非直接否定。
当提供或检索到文献时，每个选定的想法需追溯其差距、借鉴的机制原语和协议锚点的来源，同时区分有来源支持的事实与优化器的推理内容。
最终路线需通过一次重叠挑战和一次证据挑战；仅当挑战暴露实质性弱点时才修改想法。
任何向
```
ccf-literature-monitor
```
、
```
ccf-literature-searcher
```
、
```
ccf-idea-reviewer
```
、
```
ccf-experiment-designer
```
或
```
ccf-paper-writer
```
的可选模块转换需遵循CCFA交接模式；如果被拒绝或禁用，仅输出本地风险扫描或下一步记录。

当输入不完整或需要标准化多个想法草稿时，加载

references/idea-intake.md

。

Workflow

工作流程

Identify the target venue, track, field, idea maturity, user's decision goal, constraints, and available evidence. If no venue is named, assume a generic CCF-A target and label the assumption.
Map the target to a CCF-A family. Use
```
../ccf-common/references/ccf-a-venue-map.md
```
for shared venue-family routing; then load
```
references/venue-idea-adapters.md
```
for idea-stage priorities.
Ground novelty and timeliness. If the user asks for current prior art, latest trends, frontiers, non-stale ideas, recent similar papers, competitor tracking, or venue-specific policy, follow CCFA handoff mode before using
```
ccf-literature-monitor
```
for recent-paper/competitor signals or
```
ccf-literature-searcher
```
for deep related-work search. If searching directly, browse primary sources: official venue pages, papers, proceedings, arXiv pages, project pages, and credible scholar sources. Ask the searcher for an idea-grounding packet when the search feeds this skill. Mark unsearched novelty as uncertain. Treat close prior work as a differentiation problem first; treat it as a dead end only when the same problem, mechanism, evidence path, and venue claim are already covered.
Normalize the raw idea. Load
```
references/idea-intake.md
```
and produce an idea card with task, audience, gap, root challenge, insight, method, expected evidence, and constraints.
Build compact research memory when literature is available. Load
```
references/literature-grounded-evolution.md
```
; convert sources into evidence cards and a small relation map, triangulate gaps across sources, and discard background material that does not change a design decision. Do not paste whole abstracts into the working context.
For fuzzy or underdetermined ideas, load
```
references/frontier-ideation.md
```
and produce 3-5 candidate concretizations with high diversity across problem angle, mechanism, evidence type, and venue fit. Give every candidate a parent and an explicit operation such as refine, combine, transfer, invert, or instrument. Randomness is allowed in exploration, but final candidates must be coherent and non-conflicting.
Select and evolve development routes. Compare candidates internally by grounded gap, causal mechanism fit, differentiation, falsifiability, resource fit, and evidence feasibility. Keep the strongest route plus one meaningfully different fallback; challenge the strongest route with its closest-overlap risk and weakest evidence link, then revise it once if needed. This is development selection, not a user-facing numeric ranking task.
Sharpen the problem and method. Load
```
references/problem-method-blueprint.md
```
; convert vague motivation into a decision-relevant problem and convert method names into mechanisms, assumptions, failure modes, alternatives, and a causal chain from intervention to expected observation.
Shape the innovation. Decide the strongest honest contribution type and remove unsupported or diluted claims. A combination of known components needs a non-obvious interaction and a new falsifiable claim, not only a longer pipeline.
Design the minimum convincing evidence package. Load
```
references/experiment-design.md
```
; derive datasets, baselines, metrics, and protocol details from compatible public precedents when available, then add discriminating tests for the new mechanism. Follow CCFA handoff mode before using
```
ccf-experiment-designer
```
for a full experiment plan.
Run an internal development pass. In exploratory mode, use a coach-like viability scan: what can be saved, what must be narrowed, what evidence would decide, and what the next interaction should ask. Follow the CCFA handoff mode before using
```
ccf-idea-reviewer
```
as an optional scoring module; use it only when the user explicitly wants scoring, ranking, investment triage, or strict novelty judgment. If it is denied or disabled, perform a compact multi-expert risk scan focused only on problem and method.
Produce an optimized idea plan, rescue/pivot options, and a writing-readiness note. Keep internal search traces and branch bookkeeping out of polished academic prose; expose a compact source/inference basis when it helps audit the idea. Follow the CCFA handoff mode before offering the viable plan to
```
ccf-paper-writer
```
; if writing is denied or not confirmed, stop at the idea plan.

确定目标会议、专题、领域、想法成熟度、用户的决策目标、约束条件和可用证据。如果未指定会议，假设目标为通用CCF-A类会议并标记此假设。
将目标映射到CCF-A类会议类别。使用
```
../ccf-common/references/ccf-a-venue-map.md
```
进行共享会议类别路由；然后加载
```
references/venue-idea-adapters.md
```
了解想法阶段优先级。
落地创新性和时效性。如果用户询问当前研究现状、最新趋势、前沿方向、非过时想法、近期相似论文、竞争对手追踪或特定会议政策，在使用
```
ccf-literature-monitor
```
获取近期论文/竞争对手信号或
```
ccf-literature-searcher
```
进行深度相关工作检索之前，遵循CCFA交接模式。如果直接检索，浏览主要来源：官方会议页面、论文、会议论文集、arXiv页面、项目页面和可信学者来源。当检索结果为当前技能提供支持时，向检索工具请求想法落地数据包。将未检索的创新性标记为不确定内容。首先将相近的已有工作视为差异化问题；仅当相同的问题、机制、证据路径和会议主张已被覆盖时，才将其视为死胡同。
标准化原始想法。加载
```
references/idea-intake.md
```
并生成包含任务、受众、差距、核心挑战、洞察、方法、预期证据和约束条件的想法卡片。
当有文献可用时，构建紧凑的研究记忆。加载
```
references/literature-grounded-evolution.md
```
；将来源转换为证据卡片和小型关系图谱，跨来源三角验证差距，丢弃不影响设计决策的背景材料。请勿将完整摘要粘贴到工作上下文。
对于模糊或未确定的想法，加载
```
references/frontier-ideation.md
```
并生成3-5个候选具象方案，在问题角度、机制、证据类型和会议适配性方面具有高度多样性。为每个候选方案指定一个母版和明确的操作，如细化、组合、迁移、反转或工具化。探索过程中允许随机性，但最终候选方案必须连贯且无冲突。
选择并发展开发路线。通过落地的差距、因果机制适配性、差异化、可证伪性、资源适配性和证据可行性对候选方案进行内部比较。保留最可行的路线以及一个有意义的替代方案；用最接近的重叠风险和最薄弱的证据链挑战最可行的路线，如有需要则修改一次。这是开发选择，而非面向用户的数值排名任务。
明确问题和方法。加载
```
references/problem-method-blueprint.md
```
；将模糊的动机转换为与决策相关的问题，将方法名称转换为机制、假设、失败模式、替代方案以及从干预到预期观察的因果链。
塑造创新点。确定最可信的贡献类型，移除无支持或稀释的主张。已知组件的组合需要非显而易见的交互和新的可证伪主张，而非仅仅是更长的流程。
设计最小化的可信证据包。加载
```
references/experiment-design.md
```
；如果有兼容的公共先例，从中推导数据集、基线、指标和协议细节，然后添加针对新机制的鉴别测试。在使用
```
ccf-experiment-designer
```
制定完整实验计划之前，遵循CCFA交接模式。
运行内部开发流程。在探索模式下，使用类似教练的可行性扫描：哪些内容可以保留，哪些内容必须缩小范围，哪些证据可以做决定，以及下一次交互应询问什么内容。在使用
```
ccf-idea-reviewer
```
作为可选评分模块之前，遵循CCFA交接模式；仅当用户明确要求评分、排名、投资分类或严格的创新性判断时才使用该模块。如果被拒绝或禁用，执行仅关注问题和方法的紧凑多专家风险扫描。
生成优化后的想法方案、补救/转向选项以及写作准备情况说明。将内部检索痕迹和分支记录排除在精炼的学术文本之外；当有助于审核想法时，展示紧凑的来源/推理基础。在将可行方案提交给
```
ccf-paper-writer
```
之前，遵循CCFA交接模式；如果写作被拒绝或未确认，则在想法方案阶段停止。

Adaptive Output Contracts

自适应输出合约

Return the requested artifact first. If the user asks for options, give options. If they ask for a concise idea card, do not force a full review-style report. Use the following defaults when the user asks for a standard idea-optimization output.

For one idea, return:

text

Target venue and assumptions:
Mode and development stance:
Raw idea diagnosis:
Optimized idea card:
Grounding map and inference boundaries:
Candidate concretizations:
Problem statement:
Core insight:
Method blueprint:
Innovation claims:
Experiment plan:
Closest-work / novelty unknowns:
Reviewer-risk register:
Rescue routes and suggested pivots:
Optional next-module decision:
Checklist status:

For multiple idea drafts, return:

text

Venue lens:
Normalized idea table:
Best development candidate:
Why it is the best current route:
Idea-specific upgrades:
Risks by idea:
Recommended next iteration:

首先返回用户请求的成果。如果用户要求提供选项，则给出选项。如果用户要求简洁的想法卡片，请勿强制提供完整的评审式报告。当用户要求标准的想法优化输出时，使用以下默认格式。

对于单个想法，返回：

text

目标会议及假设：
模式与开发立场：
原始想法诊断：
优化后的想法卡片：
落地图谱与推理边界：
候选具象方案：
问题陈述：
核心洞察：
方法蓝图：
创新主张：
实验计划：
相近工作/创新性未知项：
评审者风险登记册：
补救路线与建议转向：
可选下一模块决策：
检查清单状态：

对于多个想法草稿，返回：

text

会议视角：
标准化想法表格：
最佳开发候选方案：
为何是当前最佳路线：
针对特定想法的升级建议：
各想法的风险：
推荐的下一次迭代方向：

Reference Files

参考文件

Load only what is needed:

```
references/idea-intake.md
```
: Use for incomplete, messy, or multi-candidate idea drafts.
```
references/frontier-ideation.md
```
: Use for fuzzy idea concretization, high-diversity exploration, non-stale direction checks, and coherence filters.
```
references/literature-grounded-evolution.md
```
: Use when supplied or searched literature should drive gap discovery, mechanism transfer, branch evolution, and protocol-grounded evidence planning.
```
references/problem-method-blueprint.md
```
: Use when sharpening the problem, insight, mechanism, contribution type, and failure modes.
```
references/venue-idea-adapters.md
```
: Use after mapping a target to a CCF-A family.
```
references/experiment-design.md
```
: Use when designing baselines, ablations, evidence packages, and acceptance-oriented experiments.
```
references/research-taste.md
```
: Use when the user asks what makes research good, elegant, timely, or likely to survive top-conference review.
```
references/source-notes.md
```
: Use when provenance, source basis, or current-policy checks matter.

If the user's request is only to score an idea without optimizing it, follow the CCFA handoff mode before switching to

ccf-idea-reviewer

unless the user explicitly named it. If the user's request is mainly to monitor recent papers or competitors, route to

ccf-literature-monitor

; if it is mainly to search related literature deeply, route to

ccf-literature-searcher

. If the user already has a manuscript draft, follow the CCFA handoff mode before switching to

ccf-paper-writer

ccf-paper-reviewer

; if not confirmed, provide only a brief scope note.

仅加载所需文件：

```
references/idea-intake.md
```
：用于不完整、杂乱或多候选的想法草稿。
```
references/frontier-ideation.md
```
：用于模糊想法具象化、高多样性探索、非过时方向检查和连贯性过滤。
```
references/literature-grounded-evolution.md
```
：当提供或检索的文献应驱动差距发现、机制迁移、分支演化和基于协议的证据规划时使用。
```
references/problem-method-blueprint.md
```
：用于明确问题、洞察、机制、贡献类型和失败模式时使用。
```
references/venue-idea-adapters.md
```
：将目标映射到CCF-A类会议类别后使用。
```
references/experiment-design.md
```
：用于设计基线、消融实验、证据包和面向录用的实验时使用。
```
references/research-taste.md
```
：当用户询问什么是优秀、简洁、及时或可能通过顶级会议评审的研究时使用。
```
references/source-notes.md
```
：当来源、基础来源或当前政策检查很重要时使用。

如果用户的请求仅为评分想法而不进行优化，在切换到

ccf-idea-reviewer

之前遵循CCFA交接模式，除非用户明确指定该技能。如果用户的请求主要是监控近期论文或竞争对手，路由到

ccf-literature-monitor

；如果主要是深度检索相关文献，路由到

ccf-literature-searcher

。如果用户已有稿件草稿，在切换到

ccf-paper-writer

或

ccf-paper-reviewer

之前遵循CCFA交接模式；如果未确认，仅提供简短的范围说明。