MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures
Install Paper Orchestration
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Norman-bury/research-writing-skill paper-orchestration --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paper-orchestration .claude/skills/paper-orchestration && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .claude/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestrationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Norman-bury/research-writing-skill paper-orchestration --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paper-orchestration .agents/skills/paper-orchestration && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .agents/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Norman-bury/research-writing-skill paper-orchestration --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paper-orchestration .cursor/skills/paper-orchestration && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .cursor/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Norman-bury/research-writing-skill.git --path skills/paper-orchestration--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Norman-bury/research-writing-skill paper-orchestration --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paper-orchestration .gemini/skills/paper-orchestration && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .gemini/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Norman-bury/research-writing-skill paper-orchestrationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paper-orchestration .github/skills/paper-orchestration && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .github/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Norman-bury/research-writing-skill paper-orchestration --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paper-orchestration .opencode/skills/paper-orchestration && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "paper-orchestration" agent skill from https://github.com/Norman-bury/research-writing-skill/tree/main/skills/paper-orchestration into .opencode/skills/paper-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-orchestration", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
paper-orchestration- GitHub stars
- 3.4k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 737 words
- Files
- 1
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures
- Works in 5 steps: Introduction, with related work… → Methodology. → Dataset and Experimental Setting, either… → …
- A research-writing task spans multiple sections
- SKILL.md covers Hard Gate, Full-Paper Redraft Gate, Multi-Agent Chapter Gate and Stage Detection, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Paper Orchestration is an agent skill from Norman-bury/research-writing-skill. Use when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: 科研写作助手 (Research Writing Assistant). The licence is MIT.
When your agent uses it
- A research-writing task spans multiple sections
- Medium-sized revisions
- Full-paper drafting
- Repeated quality failures
Example prompts
- “/paper-orchestration”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Introduction, with related work integrated into the motivation and research-gap argument.
- Methodology.
- Dataset and Experimental Setting, either standalone or integrated into Methodology/Results when short.
- Experimental Results and Analysis.
- Discussion.
What it can do on your machine
Read from SKILL.md and the folder at commit 6f79595. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Paper Orchestration loads about 1.6k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 737 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Norman-bury/research-writing-skill at commit 6f79595, republished under its MIT licence (© Norman-bury). 737 words, ~1,555 tokens.
Download SKILL.mdSave it as
.claude/skills/paper-orchestration/SKILL.md (or your agent's skills folder).- name
- paper-orchestration
- description
- Use when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures
Paper Orchestration
This skill controls the workflow around the writing skills. It prevents "one prompt writes the paper" behavior by forcing stage detection, task packets, review gates, and a capability-use audit.
Hard Gate
For any medium task or full-paper task, do not write manuscript text until these exist or are created:
plan/project-overview.mdplan/outline.mdplan/progress.md- a task packet for the current section or deliverable
- for full-paper drafting or redrafting,
plan/chapter-architecture.md
Medium task means any request that affects more than one paragraph, one subsection, one chapter, one figure/table set, or any claim tied to references or experiments.
Full-Paper Redraft Gate
For a full-paper draft, the controller must first lock the chapter architecture. Do not inherit an old chapter split if the user, target venue, or paper type implies a different structure.
For computer science / engineering SCI papers, use this body structure unless the user or target template explicitly requires otherwise:
- Introduction, with related work integrated into the motivation and research-gap argument.
- Methodology.
- Dataset and Experimental Setting, either standalone or integrated into Methodology/Results when short.
- Experimental Results and Analysis.
- Discussion.
Abstract, Conclusion, and References may be generated as supporting files, but they must not hide weak body chapters or inflate the chapter count. A standalone Related Work chapter is only allowed when the target outline explicitly demands it.
Create plan/chapter-architecture.md before drafting. It must list the exact required chapter files, target role, minimum body length, owner agent, and whether the chapter may use planning placeholders.
## Required chapter files
- chapters/01_Introduction.md | min_chars=4500 | agent=required | placeholders=no
- chapters/02_Methodology.md | min_chars=4500 | agent=required | placeholders=noIf this file exists, the quality gate must treat extra or missing chapter files as failures.
Multi-Agent Chapter Gate
For any full-paper draft or redraft, the controller must not write all chapters itself. It must:
- create one task packet per major chapter;
- dispatch a separate fresh agent for each major chapter;
- give each agent only the relevant task packet, source excerpts, evidence map, experiment protocol, and hard rejection checks;
- assign disjoint write ownership so that two agents never edit the same chapter file;
- record the agent, prompt summary, inputs, output path, and review status in
plan/chapter-agent-provenance.md; - perform a controller review after agent output before claiming progress.
If subagents are not available, stop and ask the user whether to continue in degraded single-agent mode. Do not silently fall back to one-pass generation.
Stage Detection
Classify the current work before acting:
| Stage | Trigger | Required next skill |
|---|---|---|
| S0 Scope | topic, target, structure unclear | brainstorming-research |
| S1 Evidence | references, Introduction, Related Work | evidence-driven-writing + literature-review |
| S2 Method | model, algorithm, system, method section | writing-chapters with method flow gate |
| S3 Experiments | setup, results, tables, charts | experiment-results-planning + figures-python |
| S4 Drafting | section text | writing-chapters |
| S5 Review | quality, consistency, submission risk | peer-review + verification |
Record the stage in plan/progress.md.
Show full SKILL.md (293 more words)Show less
Task Packet
Before dispatching a section task, create a persistent packet under plan/task-packets/. Conversation-only packets are not acceptable for medium or full-paper work because they cannot be audited later.
## Task Packet
- Scope:
- Files to read:
- Files allowed to edit:
- Required skills:
- Evidence/data inputs:
- Required artifacts:
- Rejection checks:
- Validation commands:Subagents must receive the task packet, not the entire vague project. If subagents are available, split independent work into literature mapping, method architecture, experiment planning, figure generation, and review. Do not let multiple agents edit the same file.
For chapter-writing packets, add:
- Target chapter file and exclusive owner.
- Required argument chain, in paragraph roles rather than bullet content.
- Minimum prose length.
- Required sources and data artifacts.
- Prohibited structure, especially bullet-like lists, process notes, and old chapter scaffolding.
- Required handoff format: status, file path changed, unresolved evidence/data gaps, and self-review.
Review Gates
Every medium task needs two reviews before completion:
- Spec compliance review: did the output match the task packet and required artifacts?
- Quality review: are claims supported, section logic coherent, and manuscript pollution absent?
If either review fails, fix before moving to the next task.
Capability-Use Audit
At the end of every medium task, write a short audit in plan/progress.md:
### Capability-use audit
- Required skills:
- Skills actually used:
- Inputs consumed:
- Inputs not used and why:
- Artifacts produced:
- Verification run:
- Remaining risk:The task is not complete without this audit.
Common Failures
- Treating user instructions as manuscript content. Convert instructions into structure or edits; never paste them into the body.
- Claiming a section is "done" when it only has headings and placeholders.
- Running style checks while skipping evidence, data, and claim checks.
- Producing tables instead of prose to hide weak argumentation.
- Keeping an old chapter split after the user rejects it. Rebuild the chapter architecture first.
- Letting the controller write a full manuscript sequentially instead of using one independent agent per major chapter.
- Accepting short, enumerative prose because it passes keyword checks. Length, paragraph flow, evidence use, and agent provenance must all be reviewed.
© Norman-bury, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/paper-orchestration of Norman-bury/research-writing-skill.
Open the folder on GitHubat commit 6f79595
Compare with similar skills
Paper Orchestration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Paper Orchestration this skillNorman-bury/research-writing-skill | 3.4k | — | ~1.6k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
More from Norman-bury/research-writing-skill
All 20 skills in this repoEvidence Driven Writing
Norman-bury/research-writing-skill
A skill your agent uses when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims
Environment Setup
Norman-bury/research-writing-skill
A skill your agent uses when Python environment setup is needed for data visualization or conda installation is required
Experiment Results Planning
Norman-bury/research-writing-skill
A skill your agent uses when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final
Figures Diagram
Norman-bury/research-writing-skill
A skill your agent uses when creating flowcharts, architecture diagrams, or conceptual diagrams - generates prompts for image AI
Figures Python
Norman-bury/research-writing-skill
A skill your agent uses when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes
Latex Output
Norman-bury/research-writing-skill
A skill your agent uses when user requests LaTeX format output or has provided school/journal LaTeX templates
Related
Categories
Questions about Paper Orchestration
What does Paper Orchestration do?
A skill your agent uses when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures. Paper Orchestration is an agent skill from Norman-bury/research-writing-skill.
When should I use Paper Orchestration?
Paper Orchestration fits situations like: A research-writing task spans multiple sections; medium-sized revisions; full-paper drafting; repeated quality failures.
How do I install Paper Orchestration in Claude Code?
Run `npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a claude-code`. Or copy the skill folder (skills/paper-orchestration in Norman-bury/research-writing-skill) into .claude/skills/paper-orchestration in your project. Claude Code loads it when a task matches its description.
How do I install Paper Orchestration in Codex?
Run `npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a codex`. Or copy the skill folder (skills/paper-orchestration in Norman-bury/research-writing-skill) into .agents/skills/paper-orchestration in your project. Codex loads it when a task matches its description.
Can I use Paper Orchestration in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Norman-bury/research-writing-skill --skill paper-orchestration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-orchestration, .gemini/skills/paper-orchestration, .github/skills/paper-orchestration and .opencode/skills/paper-orchestration in your project.
What does Paper Orchestration need to run?
SKILL.md names no scripts, command-line tools or credentials: Paper Orchestration is instructions for the agent only.
Does Paper Orchestration access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Paper Orchestration safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Paper Orchestration use?
Paper Orchestration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Paper Orchestration use?
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Paper Orchestration?
Skills that share tags, products or a category with Paper Orchestration: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paper Orchestration?
Norman-bury (a GitHub user) maintains it in Norman-bury/research-writing-skill, which has 3,384 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 10, 2026.
Source: Norman-bury/research-writing-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.