From f29d7261471c89a52acc349b88e294ad26ee616f Mon Sep 17 00:00:00 2001 From: YQGHL <118478535+YQGHL@users.noreply.github.com> Date: Thu, 6 Aug 2026 01:12:47 +0800 Subject: [PATCH] fix(paper2assets): make SKILL.md description valid YAML for strict parsers The frontmatter description was a single plain scalar containing 'metadata.json: title / authors / ...'. The colon-space sequence makes strict YAML parsers treat it as a nested mapping inside a compact mapping, raising 'Nested mappings are not allowed in compact mappings'. Claude Code and Codex tolerate this, but tools validating against the Agent Skills spec (e.g. Pi) fail to load the skill. Convert the description to a folded block scalar (>) with identical content, so colons stay literal. --- ResearchStudio-Reel/skills/paper2assets/SKILL.md | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/ResearchStudio-Reel/skills/paper2assets/SKILL.md b/ResearchStudio-Reel/skills/paper2assets/SKILL.md index bbdcd90..80c574b 100644 --- a/ResearchStudio-Reel/skills/paper2assets/SKILL.md +++ b/ResearchStudio-Reel/skills/paper2assets/SKILL.md @@ -1,6 +1,19 @@ --- name: paper2assets -description: Extract a research paper PDF into a structured set of poster-agnostic assets reusable by any downstream renderer (paper2poster, paper2blog, paper2audio, paper2video). Produces a `/` containing the paper's full text (assets/meta/text.txt), per-figure captions (assets/meta/captions.json), cleaned figure rasters (assets/figures/*.png + assets/meta/figures.json manifest), paper metadata (assets/meta/metadata.json: title / authors / institutes / venue / paper_url / code_url), institute logos (assets/logos/*), URL QR codes (assets/qr/*), and a 9-section structured paper summary (assets/meta/paper_spec.md). The bundle follows the Output Contract layout (deliverables at top, everything else under `assets/`). Use when the user wants to extract paper content into reusable assets, OR as the mandatory upstream stage of any paper-rendering pipeline — e.g., "extract this paper", "build paper assets", "get the figures and spec from this PDF", "paper2assets". +description: >- + Extract a research paper PDF into a structured set of poster-agnostic assets + reusable by any downstream renderer (paper2poster, paper2blog, paper2audio, + paper2video). Produces a `/` containing the paper's full text + (assets/meta/text.txt), per-figure captions (assets/meta/captions.json), + cleaned figure rasters (assets/figures/*.png + assets/meta/figures.json + manifest), paper metadata (assets/meta/metadata.json: title / authors / + institutes / venue / paper_url / code_url), institute logos (assets/logos/*), + URL QR codes (assets/qr/*), and a 9-section structured paper summary + (assets/meta/paper_spec.md). The bundle follows the Output Contract layout + (deliverables at top, everything else under `assets/`). Use when the user + wants to extract paper content into reusable assets, OR as the mandatory + upstream stage of any paper-rendering pipeline — e.g., "extract this paper", + "build paper assets", "get the figures and spec from this PDF", "paper2assets". allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, AskUserQuestion, WebFetch, WebSearch ---