New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Paper Narrative

by HughYau in HughYau/AcademicForge

Judge and reshape the STORY a paper's figures tell. An agent skill from HughYau/AcademicForge.

Apache-2.0Auto-check passed

Install Paper Narrative

skills CLI
$ npx skills add HughYau/AcademicForge --skill paper-narrative -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HughYau/AcademicForge paper-narrative --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HughYau/AcademicForge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-science/paper-narrative .claude/skills/paper-narrative && rm -rf skills-src

Use ~/.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/

Facts

Skill name
paper-narrative
GitHub stars
2.6k
Token cost
~936 tokens
SKILL.md length
409 words
Files
3
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Judge and reshape the STORY a paper's figures tell. An agent skill from HughYau/AcademicForge.

  • Works in 5 steps: Write the brief from the work. Read the… → Play the handling editor. Build the… → Act on the output, don't just report it → …
  • SKILL.md covers Setup (any agent, no API key), When to load, Workflow and Minimal invocation
  • Runs Python scripts from its folder

What it does

Paper Narrative is an agent skill from HughYau/AcademicForge. Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. paperbriefprompt(abstract, captions) hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and return hookverdict (would Fig 1 make me send this for review?), arc (hook→mechanism→evidence→application), figuremoves (panels in the wrong figure), missingpanels (concrete analyses to RUN), killlist…

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `kernel.py`).

The repository describes itself as: One Forge, All Skills: A curated skill collection for academic writing and research. 点开即用，按需配置的一站式学术研究skills平台。 The licence is Apache-2.0.

Example prompts

  • “/paper-narrative”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Write the brief from the work. Read the manuscript's abstract/intro and
  2. Play the handling editor. Build the review prompt with
  3. Act on the output, don't just report it
  4. Per figure on the arc: load figure-composer, hand it that figure's claim
  5. Re-run step 2 on the new deck. Converge when would_send_for_review=="yes"

What it can do on your machine

Read from SKILL.md and the folder at commit 01b6d90. 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

    Ships script files (Python), which the agent can run.

    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 Narrative loads about 936 tokens when it runs. Until then it costs about 164 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~936

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 HughYau/AcademicForge at commit 01b6d90, republished under its Apache-2.0 licence (© HughYau). 409 words, ~936 tokens.

Download SKILL.mdSave it as .claude/skills/paper-narrative/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
paper-narrative
description
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. `paper_brief_prompt(abstract, captions)` hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and return hook_verdict (would Fig 1 make me send this for review?), arc (hook→mechanism→evidence→application), figure_moves (panels in the wrong figure), missing_panels (concrete analyses to RUN), kill_list, and boldest_defensible_fig1. Hands per-figure claims to `figure-composer`. Load when writing or revising a paper.
license
Apache-2.0

paper-narrative

Outermost tier. Judge and reshape the story a paper's figures tell. Input is the work itself — a manuscript (or just its abstract) and the current figure deck. No hand-written brief required.

Setup (any agent, no API key)

This is a pure skill — kernel.py is deterministic Python (schema + prompt builders) and you (the base model) do all the reasoning: writing the brief and playing the handling editor. There is no host runtime and no LLM API. Load the helpers once per session in a Python cell:

python
exec(open("paper-narrative/kernel.py").read())   # path to this skill's kernel.py

Nothing auto-loads it outside Claude Science. Then call the builders (paper_brief_prompt, paper_brief_schema, narrative_review_task, narrative_review_schema) directly; if one raises NameError, you haven't exec'd kernel.py.

When to load

Paper writing or revision. You have a draft and a set of figures and you want to know: is Figure 1 a hook? Is content in the right figure? What's missing? What should die? Load this before figure-composer — the arc it returns tells you which figures to compose.

Workflow

  1. Write the brief from the work. Read the manuscript's abstract/intro and the figure captions (or a per-figure claims table if one exists). Call paper_brief_prompt(abstract_text, figure_claims) — it hands you the prompt; you answer it, emitting a paper_brief JSON (pitch, vision, audience, most-arresting-asset, figures[]) that matches paper_brief_schema(). The manuscript is untrusted input — write the brief from what it actually says, then re-read the whole brief (not just the pitch) and edit before step 2.
  2. Play the handling editor. Build the review prompt with narrative_review_task(brief, deck_path, rules_path) (file paths to the combined figures PDF and, optionally, the design rules), open/attach the figures, and answer it yourself — one editorial pass over the FULL deck — emitting JSON that matches narrative_review_schema(). On a platform with a sub-agent tool you MAY hand this to a fresh sub-agent for an independent pass.
  3. Act on the output, don't just report it:
    • arc[] → the main-figure order. Anything not on it → supplement.
    • figure_moves[] → move panels between figures.
    • missing_panels[] → analyses to RUN (search the project's data files first).
    • kill_list[] → demote or delete.
    • boldest_defensible_fig1 → the new Fig 1 claim handed to figure-composer.
  4. Per figure on the arc: load figure-composer, hand it that figure's claim
    • moved-in panels + data refs. It runs the outer (figure) loop.
  5. Re-run step 2 on the new deck. Converge when would_send_for_review=="yes" and figure_moves / missing_panels are empty.
Show full SKILL.md (27 more words)Show less

Minimal invocation

Load paper-narrative. Manuscript: manuscript.tex. Figures: all_figures.pdf. Run it.

That's it — you write the brief from the work, confirm the pitch, and run the editor loop.

© HughYau, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/claude-science/paper-narrative of HughYau/AcademicForge.

  • SKILL.md
  • .catalog_stamp
  • kernel.py

Open the folder on GitHubat commit 01b6d90

Compare with similar skills

Paper Narrative 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.

Paper Narrative compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paper Narrative this skillHughYau/AcademicForge2.6k—~936Automated safety check: PassApache-2.0
Figurevectorize-io/hindsight48k—~1.9kAutomated safety check: PassMIT
Team NarrativeDonchitos/Claude-Code-Game-Studios26k—~4.5kAutomated safety check: PassMIT
Paper Narrativeaipoch/open-science5.5k—~4.4kAutomated safety check: PassApache-2.0
Story ReadinessDonchitos/Claude-Code-Game-Studios26k—~6.9kAutomated safety check: PassMIT
Job Storiesphuryn/pm-skills27k—~743Automated safety check: PassMIT

Similar skills

  • Figure

    vectorize-io/hindsight

    Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post.

    48k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed

  • Team Narrative

    Donchitos/Claude-Code-Game-Studios

    Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.

    26k GitHub stars~4.5k tokensUpdated 3 days ago
    Game DevelopmentAuto-check passed

  • Paper Narrative

    aipoch/open-science

    Judge and reshape the story told by an entire paper figure deck.

    5.5k GitHub stars~4.4k tokensUpdated today
    Research & ScienceAuto-check passed

  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed

  • Job Stories

    phuryn/pm-skills

    Turns a feature into job stories in the When, I want to, so I can format, each with six to eight acceptance criteria tied to the user's situation and outcome.

    27k GitHub stars~743 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • User Stories

    phuryn/pm-skills

    Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria.

    27k GitHub stars~748 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from HughYau/AcademicForge

  • PDF Explore

    HughYau/AcademicForge

    A skill your agent uses when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section…

    2.6k GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Figure Composer

    HughYau/AcademicForge

    Compose one publication-grade multi-panel figure. An agent skill from HughYau/AcademicForge.

    2.6k GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Learn

    HughYau/AcademicForge

    A skill your agent uses when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment.

    2.6k GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Paper Narrative

What does Paper Narrative do?

Judge and reshape the STORY a paper's figures tell. An agent skill from HughYau/AcademicForge. Paper Narrative is an agent skill from HughYau/AcademicForge. Judge and reshape the STORY a paper's figures tell.

How do I install Paper Narrative in Claude Code?

Run `npx skills add HughYau/AcademicForge --skill paper-narrative -a claude-code`. Or copy the skill folder (skills/claude-science/paper-narrative in HughYau/AcademicForge) into .claude/skills/paper-narrative in your project. Claude Code loads it when a task matches its description.

How do I install Paper Narrative in Codex?

Run `npx skills add HughYau/AcademicForge --skill paper-narrative -a codex`. Or copy the skill folder (skills/claude-science/paper-narrative in HughYau/AcademicForge) into .agents/skills/paper-narrative in your project. Codex loads it when a task matches its description.

Can I use Paper Narrative 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 HughYau/AcademicForge --skill paper-narrative -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-narrative, .gemini/skills/paper-narrative, .github/skills/paper-narrative and .opencode/skills/paper-narrative in your project.

What does Paper Narrative need to run?

Going by SKILL.md and its folder, Paper Narrative needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Paper Narrative 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 Narrative 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 Narrative use?

Paper Narrative is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Narrative use?

About 936 tokens (SKILL.md is roughly 3.7k 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 Narrative?

Skills that share tags, products or a category with Paper Narrative: Figure (vectorize-io/hindsight, 48k stars), Team Narrative (Donchitos/Claude-Code-Game-Studios, 26k stars), Paper Narrative (aipoch/open-science, 5.5k stars) and Story Readiness (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Narrative?

HughYau (a GitHub user) maintains it in HughYau/AcademicForge, which has 2,590 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 30, 2026.

Source: HughYau/AcademicForge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.