outline
Skill4 starsChanged 2 days agoMITView on GitHub
Build and check outlines for research, journal articles, internship reports, and other academic or professional documents. Adapts structure to the applicable guide, identifies the core gap or purpose, checks traceability, and proposes titles last when appropriate.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- Vortiago/mcp-outlinetheir own version, first seen Nov 1, 2026
- DoKu67/claude-code-skilstheir own version, first seen Oct 16, 2026
- oakreader/oakreadertheir own version, first seen Oct 16, 2026
- coolxeo/grok-bot-skillstheir own version, first seen Oct 13, 2026
- inovve/homelab-agent-skillstheir own version, first seen Jul 14, 2026
- sanjay3290/ai-skillstheir own version, first seen Jul 6, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- sanjay3290/ai-skills★ 452same name
- Vortiago/mcp-outline★ 158same name
- tance-mang/chinese-webnovel-skills★ 97same name
- oakreader/oakreader★ 46same name
- rainday/smart-blog-skills★ 35same name
- howells/fiction★ 23same name
- coolxeo/grok-bot-skills★ 7same name
- DoKu67/claude-code-skils★ 4same name
- tansuasici/claude-research-kit★ 4same name
- inovve/homelab-agent-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- academic-writingSkill
- auditSkill
- draftSkill
- editSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ../shared/workflow-contract.md before substantive work.
- Very specific: line 17
If a campus or venue is named, inspect its current guide.
- Very specific: line 21
Run references/checklist.md and report Pass, Waiting for data, or Fail.
- Very specific: line 26
Never invent facts, sources, quotes, figures, respondents, or rules.
- Distinctive: line 28
Do not force a five-chapter thesis structure onto an article, study note, or non-chapter report.
- Distinctive: line 29
Every question, promise, or claim must connect to a section and supporting evidence.
- Distinctive: line 30
Ask at most one essential question before starting.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Outline
Read ../shared/workflow-contract.md before substantive work. Treat ../shared/institution-profile.md as a task-profile template, not official campus data. Reuse a completed profile from the current project when available.
Workflow
- Classify purpose, genre, reader, discipline, stage, and available material.
- If a campus or venue is named, inspect its current guide. For campus structure, use
references/guide-adapter.mdand record provenance for each applicable variable. Without a guide, use defaults only with[CHECK: ...]labels. - Build a core map: desired state/expectation, current state/evidence, gap or purpose, reader, central claim, proof/material, and intended contribution/action.
- Choose the correct genre module:
references/genre-research.mdfor research;references/genre-report.mdfor internship/KP/PKL reports;references/genre-article.mdfor journal/conference manuscripts. For other professional reports, structure around purpose and evidence rather than assuming a placement report. - For every section, state its job, key content, evidence/source required, and expected length or scope.
- Run
references/checklist.mdand report Pass, Waiting for data, or Fail. Repair structural failures before presenting a final outline. - Generate title options only after the structure and central claim are coherent. List unresolved
[NEED: ...]and[CHECK: ...]items.
Rules
- Never invent facts, sources, quotes, figures, respondents, or rules. Use
[NEED: ...]for missing user material and[CHECK: ...]for unverified details. - Citations must come from supplied or verified sources. Do not guess bibliographic metadata.
- Do not force a five-chapter thesis structure onto an article, study note, or non-chapter report.
- Every question, promise, or claim must connect to a section and supporting evidence. Every section must serve the document purpose.
- Ask at most one essential question before starting; otherwise proceed with explicit placeholders.
- The outline skill produces structure and reasoning, not a full submission written in place of the student.
References
references/guide-adapter.md: campus authority order and structure variables.references/checklist.md: universal and genre checks.references/genre-research.md: research outline.references/genre-report.md: internship/KP/PKL report outline.references/genre-article.md: journal/conference article outline.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

