Individual skill
light-leader
统筹一个科研项目或其中跨阶段任务:恢复上下文,依据证据选择并实际衔接文献、选题、设计、实验、分析、选刊、写作、示意图、数据图和评审,支持研究回退与返修,按需接入采集、专利、软著。用于项目推进、跨技能协调、复杂续作与研究路线诊断;明确的单阶段小任务直接使用专业技能。
light-leader/SKILL.md
Source commit 6597430ad09d8f7c3518ec4cb08829be2b417e18
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 883
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-writing Repository topic
- ai-agent Repository topic
- claude-code Repository topic
- codex Repository topic
- llm-skills Repository topic
- paper-writing Repository topic
- research-tools Repository topic
- scientific-workflow Repository topic
- agent-skills Repository topic
- ai-skills Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesSKILL.mdcore · 8,689 bytesagents/openai.yamlasset · 332 bytesassets/changes.example.jsonasset · 1,099 bytesassets/objective.example.jsonasset · 699 bytesassets/routes.jsonasset · 6,145 bytesevaluations/2026-11-07-upgrade.mddoc · 2,269 bytesevaluations/scenarios.mddoc · 3,017 bytesevaluations/verification.mddoc · 4,241 bytesreferences/artifact-contract.mddoc · 10,884 bytesreferences/project-layout.mddoc · 5,876 bytesreferences/routing-and-handoffs.mddoc · 7,825 bytesreferences/source-notes.mddoc · 4,895 bytesreferences/workflow.mddoc · 7,498 bytesscripts/leader.pyruns · 27,978 bytestests/test_integration.pyruns · 9,540 bytestests/test_leader.pyruns · 21,925 bytes
Read excerpt
# light-leader
在当前助手内承担研究负责人和协调者:把用户目标转成有依据、可交付的下一步,调用有关技能完成,并根据真实结果修订路线。项目以一篇论文或一项软著为中心,可含同一研究的软著、专利;一篇论文的改稿、返修和转投仍属于同一项目。
## 先确定本轮要交付什么
定位真实项目,先读用户本轮目标、已有 README、可选 project.json 和有关专业文件。需要归档时读 [项目目录约定](references/project-layout.md)。已有数据、稿件或软件可直接进入相应环节;没有新需求,不把研究从文献重做。
- 局部明确任务直接调用专业技能,做完即交付,不强制建立总控台账。
- 跨阶段推进或长期续作:恢复 Memory 有关条目和 Workflow,再核对影响本轮决策的原生材料。读 [推进与恢复](references/workflow.md)。不存在这些入口时,从实际材料建立最少必要的上下文,继续有价值的工作。
- “继续推进项目”先找当前最影响目标的未决问题,说明本轮完成条件;不能从这句话推定无限算力、任意费用或对外提交权限。已有会话授权持续有效,不每阶段重复确认。
- 只有当前信息确实决定不了任务目标、材料身份或必要资源时才问具体缺口;等待期间继续独立可做的工作。
## 先判断证据,再选择动作