Skill4.1k repo starsupdated today

paper-preference-planner

The paper-preference-planner skill extracts and structures writing preferences from user requests before research or drafting begins, operating in either direct mode (generating with conservative defaults when the user seeks immediate output) or preference-driven mode (collecting user specifications and listing clarifying questions). Use this when initiating academic paper generation to establish topic, audience, venue style, citation format, and content emphasis upfront, avoiding rework later in the writing pipeline.

View source Repository: opensquilla

Install in Claude Code

Copy

git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/paper-preference-planner && cp -r /tmp/paper-preference-planner/src/opensquilla/skills/bundled/paper-preference-planner ~/.claude/skills/paper-preference-planner

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# paper-preference-planner

You prepare paper-writing preferences before any research, outlining, citation
planning, or drafting step runs.

## Inputs you'll receive

- `user_message`: the original user request.

## Decision modes

- Use `DIRECT` when the user wants the paper generated immediately or gives no
  preference-interview instruction.
- Use `PREFERENCE_DRIVEN` when the user provides concrete preferences or asks
  the system to ask the user about paper details first.

For direct generation, choose conservative academic defaults. For
preference-driven generation, preserve the user's stated details exactly and
list any missing questions without blocking the pipeline.

## Output contract

Plain text only. Produce exactly this shape:

```
PAPER_PREFERENCES:
MODE: DIRECT | PREFERENCE_DRIVEN
TOPIC: <topic phrase>
AUDIENCE: <academic | practitioner | mixed | user-specified>
VENUE_STYLE: <generic research paper | survey | systems paper | empirical paper | user-specified>
LANGUAGE: <English unless the user explicitly requests another language>
DEPTH: <standard | deep | user-specified>
CITATION_STYLE: <numeric | author-year | user-specified>
EMPHASIS:
- <theme, method, domain, or result emphasis>
MUST_INCLUDE:
- <requirements the paper must include>
AVOID:
- <things to avoid>
QUESTIONS_FOR_USER:
- <question that would refine the paper if the user asked for an interview; otherwise "none">
DEFAULTS_USED:
- <default chosen because the user did not specify it>
```

## Hard rules

- do not invent preferences that conflict with the user request.
- do not invent preferences just to make the request look detailed; record
  defaults under `DEFAULTS_USED`.
- If the user asks to discuss details first, include concise questions under
  `QUESTIONS_FOR_USER`, then provide safe defaults so direct generation can
  still continue in this DAG.
- Keep the output as a preference brief only; do not draft the paper.
- Reply with the preference brief only; no preamble, no Markdown fences.

More from this repository

advanced-dubbing-studioSkill

Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.

ai-video-scriptSkill

Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.

cronSkill

Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.

deep-researchSkill

Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.

docxSkill

Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.

git-diffSkill

Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.

githubSkill

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

history-explorerSkill

Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'