joss-draft
Draft a JOSS paper (paper.md and paper.bib) for an R or Python package. Launches the joss-writer agent, which reuses existing manuscripts and maps competing packages, then resolves anything only the author can supply (ORCID, AI usage, funding).
- License 许可
- MIT
- 最近更新
- 2026-10-23
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- joss-draft
- description
- Draft a JOSS paper (paper.md and paper.bib) for an R or Python package. Launches the joss-writer agent, which reuses existing manuscripts and maps competing packages, then resolves anything only the author can supply (ORCID, AI usage, funding).
- argument-hint
- [package path]
03 SKILL.md 正文
JOSS Paper Drafting
Thin launcher: the drafting workflow lives in the pub-pipeline:joss-writer agent. This skill gathers context, dispatches it, and answers its questions in the main session (subagents cannot ask the user).
1. Gather context (Read and Bash tools)
- Package root:
$ARGUMENTSif given, else the current directory (must containDESCRIPTIONorpyproject.toml). - Read
.claude/pub-pipeline.local.mdif it exists. If missing, offer to create it from${CLAUDE_PLUGIN_ROOT}/docs/user-config-template.md(author,ai_usage, andrelated_workfeed the paper directly). - Author metadata: config
author/coauthorsfirst, thendeets show --format jsonif available.
2. Dispatch (Agent tool)
Launch subagent_type: pub-pipeline:joss-writer with:
<context>
<package_root>[absolute path]</package_root>
<author_metadata>[name, ORCID, affiliation, email for each author, as found]</author_metadata>
<user_config>[frontmatter of .claude/pub-pipeline.local.md, or "none"]</user_config>
</context>
3. Resolve decisions
Show the agent's draft summary. If it returns a Decisions Needed block, ask the user each question (AskUserQuestion when the options are discrete), then re-dispatch the writer with the same context plus:
<answers>
1. [id]: [user's answer]
</answers>
Repeat until no decisions remain or the user chooses to fill the placeholders by hand.
4. Next step
Offer /pub-pipeline:joss-audit for a full review of the draft against the JOSS checklist.
04 同仓库更多 Skills
worldsmith-methodology
Use when working in a project with a worldbuilding documentation ecosystem (docs/ or lore/ directory). Provides the documentation-first methodology: canonical hierarchy, doc roles (timeline, lore, characters, systems), propagation discipline, and the dual canonical and exploratory workflow.
prose-craft
Use when writing fiction, editing fiction prose, reviewing chapters, or drafting scenes. Covers prose craft, dialogue mechanics, scene structure, and common failure modes in AI-assisted fiction. Trigger phrases: "write fiction", "edit chapter", "prose review", "scene draft", "dialogue check", "fiction craft", "edit this scene", "review my prose".
vista
This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.
synthesize
Make a research-agent run conclude and write synthesis.md (outcome, key findings, failed approaches, open questions, recommendations). Signals a live researcher to wrap up, or launches one in synthesis mode when none is running. Use when results are good enough or the agent is stalling.
status
Show the current state of a research-agent run from .research/: liveness, cycles and budget, sub-problem and hypothesis statuses, eval trend, current focus, and branches. Read-only.
resume
Resume an interrupted research-agent run from .research/. Re-launches the researcher to reload its structured state and continue from the current focus, optionally on a named branch or with a new budget. Use after a session restart, crash, or explicit pause.