data2story

Name: data2story
Author: QinghongLin

146stars19forks

How to install data2story?

qinghonglin/data2story-skill/data2story

$npx -y skills add QinghongLin/data2story-skill --skill data2story

Installs into the current project.

Summary

Data Journalist Agent (Data2Story) — orchestrator: turn a dataset into a blog. Runs detective → analyst → editor → designer → programmer → auditor → inspector in sequence. Creates a versioned project folder for each run.

Files · 1

View on GitHub

SKILL.md

1	# Data Journalist Agent (Data2Story)
2
3	Turn $ARGUMENTS into a blog. Orchestrates the roles below in sequence.
4
5	## Setup
6
7	Resolve paths before doing anything:
8
9	- Never hard-code machine-local paths and never ask the user to export path variables.
10	- Resolve `SKILL_DIR` = the directory containing this `SKILL.md` (`.../skills/data2story`)
11	- Resolve `ARCHIVE_DIR` = the ancestor directory that contains `skills/` (two levels up from `SKILL_DIR`, i.e. `SKILL_DIR/../..`)
12	- Resolve `DATA2STORY_ROOT` = parent of `ARCHIVE_DIR`
13	- Commands below use symbolic placeholders such as `ARCHIVE_DIR`; replace them with resolved, quoted paths before running Bash.
14	- `DATA_NAME` = the dataset folder name (e.g. `pick_a_card`)
15	- `DATA_DIR` = if `$ARGUMENTS` is an existing path, use that path; otherwise use `DATA2STORY_ROOT/data/{DATA_NAME}`
16	- `TIMESTAMP` = current time formatted as `MMDD_HHMM` (e.g. `0401_1618`): `date +%m%d_%H%M` (run in bash)
17	- `PROJECT_DIR` = `DATA2STORY_ROOT/project/{DATA_NAME}/blog_{MODEL}_{TIMESTAMP}`
18	- Create `PROJECT_DIR/`, `PROJECT_DIR/assets/`, `PROJECT_DIR/code/`
19
20	## Archival
21
22	Immediately after creating `PROJECT_DIR`, snapshot the current skills:
23
24	```bash
25	mkdir -p PROJECT_DIR/archival
26	cp -r ARCHIVE_DIR/skills PROJECT_DIR/archival/skills
27	```
28
29	This preserves the exact skill versions used for this run.
30
31	## Tools available
32
33	All media tools route through OpenRouter. Set `OPENROUTER_API_KEY` before any generation call.
34
35	Media generation is the Designer's job, so the media tools (text2image, text2video, image2video, text2music, embeddings) live under `SKILL_DIR/designer/scripts/openrouter-/`. The full list — default models and exact `python3 ...` invocations — is in [`designer/references/tools.json`](designer/references/tools.json); full per-tool docs are each tool's own `SKILL.md` under `SKILL_DIR/designer/scripts/openrouter-/`.
36
37	## Pipeline Overview
38
39	The pipeline is a single linear sequence that produces a traceable HTML blog from raw data:
40
41	```
42	DATA → Detective → Analyst → Editor → Designer → Programmer → Auditor → Inspector → final index.html + viewer.html
43	```
44
45	Run each stage in order. Each stage reads the previous artifact(s) before starting. Do not proceed to the next stage until the current artifact is complete.
46
47	### Stage 1 — Detective
48	Input: `DATA_DIR`
49	Output: `PROJECT_DIR/detective.json`
50	What: Researches external context — background knowledge, domain history, related findings, why this data matters. Each finding gets a `det_xx` ID.
51
52	### Stage 2 — Analyst
53	Input: `DATA_DIR`, `PROJECT_DIR/detective.json`
54	Output: `PROJECT_DIR/code/*.py`, `PROJECT_DIR/analyst.json`
55	What: Exhaustive quantitative analysis of the data, informed by detective's context. All code saved to `code/` as runnable scripts. Each finding gets an `ana_xx` ID with `calculation` (file + lines + output) and `data_table` (chart-ready data).
56
57	### Stage 3 — Editor
58	Input: `PROJECT_DIR/detective.json`, `PROJECT_DIR/analyst.json`
59	Output: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`
60	What: Editorial decisions — which findings matter, what the narrative arc is, what the blog argues. Each section gets an `edt_xx` ID with explicit references to `ana_xx` findings and `det_xx` context. No visual design.
61
62	### Stage 4 — Designer
63	Input: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`, `PROJECT_DIR/analyst.json`
64	Output: `PROJECT_DIR/designer.json`, `PROJECT_DIR/assets/*`
65	What: Data-driven creative visual decisions — how to present each point using charts, images, video, audio, maps, interactives, stat callouts, instances, or text-only treatment when appropriate. The media mix should emerge from the dataset's properties, not from a fixed checklist. The page should be multimedia-rich by default: borrow the visual language from the shared [`frontend-design`](../frontend-design/) skill and use all five channels (chart, image, video, audio, interactive/map) unless a channel's documented fallback would be fabricated or purely decorative. Each visual gets a `des_xx` ID with `data_source` pointing to `ana_xx` data_tables when data-driven. Generates selected assets. No HTML.
66
67	### Stage 5 — Programmer
68	Input: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`, `PROJECT_DIR/analyst.json`, `PROJECT_DIR/designer.json`
69	Output: `PROJECT_DIR/index.html`
70	What: Implements the final blog in HTML. Applies the theme/accent recorded in `designer.json` `page_rhythm` and borrows component + token recipes from the [`frontend-design`](../frontend-design/) skill. Resolves chart data from analyst.json data_tables (NO raw data access). Tags every element with `data-edt`, `data-ana`, `data-det`, `data-

People who liked this also viewed

6 picks

Type

data2story

146stars19forks

View on GitHub

How to install data2story?

qinghonglin/data2story-skill/data2story

$npx -y skills add QinghongLin/data2story-skill --skill data2story

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Data Journalist Agent (Data2Story)
2
3	Turn $ARGUMENTS into a blog. Orchestrates the roles below in sequence.
4
5	## Setup
6
7	Resolve paths before doing anything:
8
9	- Never hard-code machine-local paths and never ask the user to export path variables.
10	- Resolve `SKILL_DIR` = the directory containing this `SKILL.md` (`.../skills/data2story`)
11	- Resolve `ARCHIVE_DIR` = the ancestor directory that contains `skills/` (two levels up from `SKILL_DIR`, i.e. `SKILL_DIR/../..`)
12	- Resolve `DATA2STORY_ROOT` = parent of `ARCHIVE_DIR`
13	- Commands below use symbolic placeholders such as `ARCHIVE_DIR`; replace them with resolved, quoted paths before running Bash.
14	- `DATA_NAME` = the dataset folder name (e.g. `pick_a_card`)
15	- `DATA_DIR` = if `$ARGUMENTS` is an existing path, use that path; otherwise use `DATA2STORY_ROOT/data/{DATA_NAME}`
16	- `TIMESTAMP` = current time formatted as `MMDD_HHMM` (e.g. `0401_1618`): `date +%m%d_%H%M` (run in bash)
17	- `PROJECT_DIR` = `DATA2STORY_ROOT/project/{DATA_NAME}/blog_{MODEL}_{TIMESTAMP}`
18	- Create `PROJECT_DIR/`, `PROJECT_DIR/assets/`, `PROJECT_DIR/code/`
19
20	## Archival
21
22	Immediately after creating `PROJECT_DIR`, snapshot the current skills:
23
24	```bash
25	mkdir -p PROJECT_DIR/archival
26	cp -r ARCHIVE_DIR/skills PROJECT_DIR/archival/skills
27	```
28
29	This preserves the exact skill versions used for this run.
30
31	## Tools available
32
33	All media tools route through OpenRouter. Set `OPENROUTER_API_KEY` before any generation call.
34
35	Media generation is the Designer's job, so the media tools (text2image, text2video, image2video, text2music, embeddings) live under `SKILL_DIR/designer/scripts/openrouter-/`. The full list — default models and exact `python3 ...` invocations — is in [`designer/references/tools.json`](designer/references/tools.json); full per-tool docs are each tool's own `SKILL.md` under `SKILL_DIR/designer/scripts/openrouter-/`.
36
37	## Pipeline Overview
38
39	The pipeline is a single linear sequence that produces a traceable HTML blog from raw data:
40
41	```
42	DATA → Detective → Analyst → Editor → Designer → Programmer → Auditor → Inspector → final index.html + viewer.html
43	```
44
45	Run each stage in order. Each stage reads the previous artifact(s) before starting. Do not proceed to the next stage until the current artifact is complete.
46
47	### Stage 1 — Detective
48	Input: `DATA_DIR`
49	Output: `PROJECT_DIR/detective.json`
50	What: Researches external context — background knowledge, domain history, related findings, why this data matters. Each finding gets a `det_xx` ID.
51
52	### Stage 2 — Analyst
53	Input: `DATA_DIR`, `PROJECT_DIR/detective.json`
54	Output: `PROJECT_DIR/code/*.py`, `PROJECT_DIR/analyst.json`
55	What: Exhaustive quantitative analysis of the data, informed by detective's context. All code saved to `code/` as runnable scripts. Each finding gets an `ana_xx` ID with `calculation` (file + lines + output) and `data_table` (chart-ready data).
56
57	### Stage 3 — Editor
58	Input: `PROJECT_DIR/detective.json`, `PROJECT_DIR/analyst.json`
59	Output: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`
60	What: Editorial decisions — which findings matter, what the narrative arc is, what the blog argues. Each section gets an `edt_xx` ID with explicit references to `ana_xx` findings and `det_xx` context. No visual design.
61
62	### Stage 4 — Designer
63	Input: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`, `PROJECT_DIR/analyst.json`
64	Output: `PROJECT_DIR/designer.json`, `PROJECT_DIR/assets/*`
65	What: Data-driven creative visual decisions — how to present each point using charts, images, video, audio, maps, interactives, stat callouts, instances, or text-only treatment when appropriate. The media mix should emerge from the dataset's properties, not from a fixed checklist. The page should be multimedia-rich by default: borrow the visual language from the shared [`frontend-design`](../frontend-design/) skill and use all five channels (chart, image, video, audio, interactive/map) unless a channel's documented fallback would be fabricated or purely decorative. Each visual gets a `des_xx` ID with `data_source` pointing to `ana_xx` data_tables when data-driven. Generates selected assets. No HTML.
66
67	### Stage 5 — Programmer
68	Input: `PROJECT_DIR/editor.md`, `PROJECT_DIR/editor.json`, `PROJECT_DIR/analyst.json`, `PROJECT_DIR/designer.json`
69	Output: `PROJECT_DIR/index.html`
70	What: Implements the final blog in HTML. Applies the theme/accent recorded in `designer.json` `page_rhythm` and borrows component + token recipes from the [`frontend-design`](../frontend-design/) skill. Resolves chart data from analyst.json data_tables (NO raw data access). Tags every element with `data-edt`, `data-ana`, `data-det`, `data-

People who liked this also viewed

6 picks

Type