Tooluck logoTooluck
SKILL.md

ts-idea2story

Agent skill fromSpark-To-Paper-Skills/spark-to-paper-skills

Turn a raw research idea into a compelling, well-grounded research STORY (an 8-field structured proposal) ready to feed the ts-paper pipeline. Claude does almost everything natively — idea packaging, recall reasoning over a knowledge graph, agentic external literature search (WebSearch/WebFetch), story generation, and a critique→refine→fusion loop; tiny scripts do only embeddings/recall math and the schema gate. Emits story.json + story_proposal.md + retrieved_papers.json (a citation seed the cite stage reuses, so paper-writing searches less). Use when the user has an idea (not yet a full proposal) and wants a paper-ready story.

How to install ts-idea2story

install ts-idea2story
# install the spark-to-paper-skills pack with the skills CLI
npx skills add Spark-To-Paper-Skills/spark-to-paper-skills

# or add only this skill to Claude Code: copy the folder

skills/ts-idea2story/

# into

~/.claude/skills/ts-idea2story/ (all projects)

.claude/skills/ts-idea2story/ (one project)

skills/ts-idea2story/SKILL.md

MITFull file
1# ts-idea2story — idea → grounded research story (the upstream of ts-paper)
2
3Distilled from the product's idea→story link. **The idea is the PROTAGONIST; a recalled/searched
4pattern is the TOOL it wields.** Claude is the packager, the recaller, the searcher, the storyteller,
5and the critic — all in one context (so coherence and anti-stacking come for free). Two scripts are
6irreducible: `kg_recall.py` (vector/graph retrieval) and `story_lint.py` (the gate); embeddings
7(optional) reuse `../ts-kg-build/scripts/embed.py`'s `TS_EMBED_*` config.
8
9## Inputs / Outputs
10**In:** a raw idea (text); optional `kg/` dir (from `ts-kg-build`, or the bundled `kg_ts`); optional
11`TS_EMBED_*` endpoint; a `retrieval_focus` dial in {trust_kg, balanced, go_search_web}.
12**Out (in the workdir):**
13- `story.json` — the 8 fields: `title, abstract, problem_framing, gap_pattern, solution,
14 method_skeleton, innovation_claims[], experiments_plan`.
15- `story_proposal.md` — the Markdown projection of the 8 fields (this is what `ts-paper-plan` reads —
16 a story IS a structured proposal; **story2paper == proposal2paper**).
17- `retrieved_papers.json` — the real papers found, the **citation seed** for `ts-paper-cite` (§ Reuse).
18- `logs/*.io.md`, optional `novelty_report.json`.
19
20## Procedure
21
22### 1. Package the idea (Claude)
23Write `idea_brief.json`: `motivation, problem, assumptions_explicit[], assumptions_inferred[],
24…

Excerpt shown under the repository's MIT license.

More skills in spark-to-paper-skills

Keep exploring

Similar skill repositories

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates