ideation

Name: ideation
Author: QinghongLin

146stars19forks

How to install ideation?

qinghonglin/data2story-skill/ideation

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

Installs into the current project.

Summary

Front stage for /data2story-pro when the reader has no dataset — only a vague idea. Converges the idea into a concrete, data-backed topic through a sparring-partner dialogue (anti-sycophantic, feasibility-pressure-tested), then acquires a REAL dataset through find-data, with a us

Files · 1

View on GitHub

SKILL.md

1	# Ideation — from a vague idea to a data-backed topic + a real dataset
2
3	The `/data2story-pro` orchestrator routes here in IDEA MODE: the reader handed over a hunch, a
4	question, or a half-formed angle instead of a dataset. Your job is to turn that into a concrete
5	topic that real, findable data can support, fetch that data, and hand a validated folder back to
6	the pipeline. You do this WITH the reader, not for them — two real checkpoints, no railroading.
7
8	You are not a pipeline role (no `*_NN` provenance prefix, no place in the 7 teams). You run once,
9	before Detective, and produce nothing that reaches the HTML except the dataset + a `story_brief`.
10
11	## Inputs
12	- `$1` = the reader's raw idea text (may be empty → open by inviting it).
13	- `$2` = `DATA2STORY_ROOT` (resolved by the orchestrator; where `data/<slug>/` will live).
14
15	## Return contract (how the orchestrator continues)
16	- Success: emit a final line `DATA_DIR=<absolute path to the validated dataset folder>`. The
17	`story_brief.json` sits at `<DATA_DIR>/meta/story_brief.json`. The orchestrator sets
18	`DATA_DIR`/`DATA_NAME` from this and enters the normal pipeline (Detective → … → Inspector).
19	- Abort: emit `IDEATION_ABORTED: <one-line reason>` (reader stopped, or no real dataset supports
20	the idea after the bounded loop). The orchestrator halts honestly and runs NO pipeline. Never
21	fabricate data to manufacture a success.
22
23	## The flow — 3 steps, 2 checkpoints
24
25	Interaction style — let the reader CHOOSE, don't make them compose. Drive the convergence
26	and BOTH checkpoints with `AskUserQuestion`: frame the angles / scope / data-forks as options the
27	reader clicks, not paragraphs they must write — picking is far lower-friction and each question
28	doubles as a micro-checkpoint. ALWAYS keep the Other / free-text escape open: the menu is your
29	framing, and the reader's own off-menu angle is often the best one, so never let it cage the
30	brainstorm. (This is NOT the cold opening questionnaire `sparring-partner` warns against — it is
31	choice-driven convergence after you have framed the space: lead the very first turn with
32	substance + an open invite, then switch to options.)
33
34	### Step 1 — Converge the idea (reuse `sparring-partner`)
35	Run the brainstorming dialogue by following `Skill sparring-partner` with the mission in
36	[`references/sparring_brief.md`](references/sparring_brief.md): drive the reader from a vague idea to
37	ONE concrete data-story topic. Two non-negotiables on top of sparring-partner's normal process:
38	- Anti-sycophancy (its core stance) — do not rubber-stamp the first pretty idea.
39	- A feasibility pressure-test — relentlessly ask *does this data actually exist? at what
40	granularity? who publishes it? for which years/places?* A beautiful idea with no obtainable data
41	is a failure of this step, not a success. Steer toward a nearby idea the data CAN support.
42
43	The terminal of the dialogue is the `story_brief` (contract: [`references/schema.json`](references/schema.json)) —
44	topic, angle, audience, the questions the data must answer, a structured `data_needs` spec, any
45	real candidate sources surfaced, and the exact `find_data_invocation.query`. Reply in the
46	reader's language (sparring-partner's rule).
47
48	### CHECKPOINT 1 — confirm the brief
49	Show the reader the assembled `story_brief` (at least `topic`, `angle`, `data_needs`, and
50	`find_data_invocation.query`). Use `AskUserQuestion` (approve · edit · abort) or a plain confirm.
51	Loop back into Step 1 on edits. Do not proceed until the reader approves the brief. On abort →
52	return `IDEATION_ABORTED: reader stopped at brief`.
53
54	### Step 2 — Acquire a REAL dataset (reuse `find-data`, web-first)
55	Derive a kebab-case `slug` from `story_brief.topic`; set `OUT_DIR` to the ABSOLUTE path
56	`$2/data/<slug>` (resolve `$2` to an absolute path first). Then follow `Skill find-data` with the
57	brief's query and ALWAYS pass that explicit `--out OUT_DIR` — never rely on find-data's bare default
58	(its default is `DATASETS_ROOT/<name>`, a DIFFERENT root: `./datasets/<name>`, not `data/<slug>`).
59	An explicit `--out` always wins, so the dataset is guaranteed to land at the path ideation chose:
60
61	```
62	Skill find-data "<story_brief.find_data_invocation.query>" --out OUT_DIR [--mode <single\|theme>] [other flags]
63	```
64
65	find-data searches (web-first on an open-source machine

People who liked this also viewed

6 picks

Type

ideation

146stars19forks

View on GitHub

How to install ideation?

qinghonglin/data2story-skill/ideation

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Ideation — from a vague idea to a data-backed topic + a real dataset
2
3	The `/data2story-pro` orchestrator routes here in IDEA MODE: the reader handed over a hunch, a
4	question, or a half-formed angle instead of a dataset. Your job is to turn that into a concrete
5	topic that real, findable data can support, fetch that data, and hand a validated folder back to
6	the pipeline. You do this WITH the reader, not for them — two real checkpoints, no railroading.
7
8	You are not a pipeline role (no `*_NN` provenance prefix, no place in the 7 teams). You run once,
9	before Detective, and produce nothing that reaches the HTML except the dataset + a `story_brief`.
10
11	## Inputs
12	- `$1` = the reader's raw idea text (may be empty → open by inviting it).
13	- `$2` = `DATA2STORY_ROOT` (resolved by the orchestrator; where `data/<slug>/` will live).
14
15	## Return contract (how the orchestrator continues)
16	- Success: emit a final line `DATA_DIR=<absolute path to the validated dataset folder>`. The
17	`story_brief.json` sits at `<DATA_DIR>/meta/story_brief.json`. The orchestrator sets
18	`DATA_DIR`/`DATA_NAME` from this and enters the normal pipeline (Detective → … → Inspector).
19	- Abort: emit `IDEATION_ABORTED: <one-line reason>` (reader stopped, or no real dataset supports
20	the idea after the bounded loop). The orchestrator halts honestly and runs NO pipeline. Never
21	fabricate data to manufacture a success.
22
23	## The flow — 3 steps, 2 checkpoints
24
25	Interaction style — let the reader CHOOSE, don't make them compose. Drive the convergence
26	and BOTH checkpoints with `AskUserQuestion`: frame the angles / scope / data-forks as options the
27	reader clicks, not paragraphs they must write — picking is far lower-friction and each question
28	doubles as a micro-checkpoint. ALWAYS keep the Other / free-text escape open: the menu is your
29	framing, and the reader's own off-menu angle is often the best one, so never let it cage the
30	brainstorm. (This is NOT the cold opening questionnaire `sparring-partner` warns against — it is
31	choice-driven convergence after you have framed the space: lead the very first turn with
32	substance + an open invite, then switch to options.)
33
34	### Step 1 — Converge the idea (reuse `sparring-partner`)
35	Run the brainstorming dialogue by following `Skill sparring-partner` with the mission in
36	[`references/sparring_brief.md`](references/sparring_brief.md): drive the reader from a vague idea to
37	ONE concrete data-story topic. Two non-negotiables on top of sparring-partner's normal process:
38	- Anti-sycophancy (its core stance) — do not rubber-stamp the first pretty idea.
39	- A feasibility pressure-test — relentlessly ask *does this data actually exist? at what
40	granularity? who publishes it? for which years/places?* A beautiful idea with no obtainable data
41	is a failure of this step, not a success. Steer toward a nearby idea the data CAN support.
42
43	The terminal of the dialogue is the `story_brief` (contract: [`references/schema.json`](references/schema.json)) —
44	topic, angle, audience, the questions the data must answer, a structured `data_needs` spec, any
45	real candidate sources surfaced, and the exact `find_data_invocation.query`. Reply in the
46	reader's language (sparring-partner's rule).
47
48	### CHECKPOINT 1 — confirm the brief
49	Show the reader the assembled `story_brief` (at least `topic`, `angle`, `data_needs`, and
50	`find_data_invocation.query`). Use `AskUserQuestion` (approve · edit · abort) or a plain confirm.
51	Loop back into Step 1 on edits. Do not proceed until the reader approves the brief. On abort →
52	return `IDEATION_ABORTED: reader stopped at brief`.
53
54	### Step 2 — Acquire a REAL dataset (reuse `find-data`, web-first)
55	Derive a kebab-case `slug` from `story_brief.topic`; set `OUT_DIR` to the ABSOLUTE path
56	`$2/data/<slug>` (resolve `$2` to an absolute path first). Then follow `Skill find-data` with the
57	brief's query and ALWAYS pass that explicit `--out OUT_DIR` — never rely on find-data's bare default
58	(its default is `DATASETS_ROOT/<name>`, a DIFFERENT root: `./datasets/<name>`, not `data/<slug>`).
59	An explicit `--out` always wins, so the dataset is guaranteed to land at the path ideation chose:
60
61	```
62	Skill find-data "<story_brief.find_data_invocation.query>" --out OUT_DIR [--mode <single\|theme>] [other flags]
63	```
64
65	find-data searches (web-first on an open-source machine

People who liked this also viewed

6 picks

Type