outline-builder

Name: outline-builder
Author: WILLOSCAR

489stars39forks

How to install outline-builder?

willoscar/research-units-pipeline-skills/outline-builder

$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill outline-builder

Installs into the current project.

Summary

Convert a taxonomy (outline/taxonomy.yml) into a bullet-only outline (outline/outline.yml) with sections/subsections. Trigger: outline builder, bullet outline, outline.yml, 大纲生成, bullets-only. Use when: structure 阶段（NO PROSE），已有 taxonomy，需要生成可映射/可写作的章节与小节骨架（每小节≥3 bull

Files · 1

View on GitHub

SKILL.md

1	# Outline Builder
2
3	`outline/outline.refined.ok` freezes a reviewed outline only while the marker is newer than the outline, all declared inputs, the defaults asset, and the generator. Upstream changes invalidate the marker and trigger a backed-up regeneration.
4
5	Build `outline/outline.yml` from either:
6	- `outline/taxonomy.yml` (legacy H3-first compatibility path)
7	- `outline/chapter_skeleton.yml` + `outline/section_briefs.jsonl` (section-first transition path)
8
9	Compatibility mode is active: this migration keeps the current output contract while moving intro/related defaults, Stage A bullet templates, and domain-specific comparison framing into `references/` and `assets/`.
10
11	## Load Order
12
13	Always read:
14	- `references/overview.md`
15	- `references/stage_a_contract.md`
16
17	Read by task:
18	- `references/intro_related_patterns.md` when changing `Introduction` / `Related Work` defaults
19	- `references/examples_good.md` and `references/examples_bad.md` for bullet calibration
20
21	Machine-readable asset:
22	- `assets/outline_defaults.yaml`
23
24	## Inputs
25
26	Required:
27	- `outline/taxonomy.yml`
28
29	Optional human calibration only:
30	- `ref/agent-surveys/STYLE_REPORT.md`
31	- `ref/agent-surveys/text/`
32
33	## Output
34
35	Keep the current output contract:
36	- `outline/outline.yml`
37
38	## Compatibility mode
39
40	Current mode is reference-first with script compatibility:
41	- front-chapter defaults live in `assets/outline_defaults.yaml`
42	- Stage A bullet defaults and comparison-axis packs live in `assets/outline_defaults.yaml`
43	- examples and boundary rules live in `references/`
44	- `scripts/run.py` still owns outline materialization, section-first input selection, and placeholder-safe overwrite behavior
45
46	## Script boundary
47
48	Use `scripts/run.py` only for:
49	- loading taxonomy or section-first structure inputs plus the defaults asset
50	- rendering the outline skeleton deterministically
51	- preserving existing non-placeholder outlines
52	- choosing comparison-axis packs from machine-readable defaults
53
54	Do not treat the script as the main place for:
55	- domain framing for `Introduction` / `Related Work`
56	- long bullet banks or writing exemplars
57	- prompt-heavy guidance about how a good outline should read
58
59	## Output shape rules
60
61	Keep these stable:
62	- `outline/outline.yml` is a YAML list
63	- `Introduction` and `Related Work` remain the first two H2 sections
64	- each H3 subsection contains the Stage A bullets: `Intent:` / `RQ:` / `Evidence needs:` / `Expected cites:`
65	- each H3 subsection adds several topic-specific bullets after the Stage A fields
66	- the helper never overwrites non-placeholder user work
67
68	## Quick Start
69
70	- `uv run python .codex/skills/outline-builder/scripts/run.py --help`
71	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
72
73	## Execution notes
74
75	When running this skill in compatibility mode, `scripts/run.py` currently reads:
76	- `outline/taxonomy.yml`, or
77	- `outline/chapter_skeleton.yml` + `outline/section_briefs.jsonl`
78	- `assets/outline_defaults.yaml`
79
80	The optional style references under `ref/agent-surveys/` are for human calibration only:
81	- use `ref/agent-surveys/STYLE_REPORT.md` to sanity-check chapter counts / thickness
82	- skim `ref/agent-surveys/text/` only to calibrate structure rather than wording
83
84	## Script
85
86	### Quick Start
87
88	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
89
90	### All Options
91
92	- `--workspace <dir>`
93	- `--unit-id <id>`
94	- `--inputs <path1;path2>`
95	- `--outputs <path1;path2>`
96	- `--checkpoint <C*>`
97
98	### Examples
99
100	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
101
102	## Troubleshooting
103
104	- If `Related Work` still carries domain-specific framing, patch `assets/outline_defaults.yaml` before changing Python.
105	- If subsection bullets feel generic, review `references/stage_a_contract.md` and `references/examples_good.md`.
106	- If the outline is structurally valid but too fragmented, reroute to `outline-budgeter` rather than expanding this script.

People who liked this also viewed

6 picks

Type

outline-builder

489stars39forks

View on GitHub

How to install outline-builder?

willoscar/research-units-pipeline-skills/outline-builder

$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill outline-builder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Outline Builder
2
3	`outline/outline.refined.ok` freezes a reviewed outline only while the marker is newer than the outline, all declared inputs, the defaults asset, and the generator. Upstream changes invalidate the marker and trigger a backed-up regeneration.
4
5	Build `outline/outline.yml` from either:
6	- `outline/taxonomy.yml` (legacy H3-first compatibility path)
7	- `outline/chapter_skeleton.yml` + `outline/section_briefs.jsonl` (section-first transition path)
8
9	Compatibility mode is active: this migration keeps the current output contract while moving intro/related defaults, Stage A bullet templates, and domain-specific comparison framing into `references/` and `assets/`.
10
11	## Load Order
12
13	Always read:
14	- `references/overview.md`
15	- `references/stage_a_contract.md`
16
17	Read by task:
18	- `references/intro_related_patterns.md` when changing `Introduction` / `Related Work` defaults
19	- `references/examples_good.md` and `references/examples_bad.md` for bullet calibration
20
21	Machine-readable asset:
22	- `assets/outline_defaults.yaml`
23
24	## Inputs
25
26	Required:
27	- `outline/taxonomy.yml`
28
29	Optional human calibration only:
30	- `ref/agent-surveys/STYLE_REPORT.md`
31	- `ref/agent-surveys/text/`
32
33	## Output
34
35	Keep the current output contract:
36	- `outline/outline.yml`
37
38	## Compatibility mode
39
40	Current mode is reference-first with script compatibility:
41	- front-chapter defaults live in `assets/outline_defaults.yaml`
42	- Stage A bullet defaults and comparison-axis packs live in `assets/outline_defaults.yaml`
43	- examples and boundary rules live in `references/`
44	- `scripts/run.py` still owns outline materialization, section-first input selection, and placeholder-safe overwrite behavior
45
46	## Script boundary
47
48	Use `scripts/run.py` only for:
49	- loading taxonomy or section-first structure inputs plus the defaults asset
50	- rendering the outline skeleton deterministically
51	- preserving existing non-placeholder outlines
52	- choosing comparison-axis packs from machine-readable defaults
53
54	Do not treat the script as the main place for:
55	- domain framing for `Introduction` / `Related Work`
56	- long bullet banks or writing exemplars
57	- prompt-heavy guidance about how a good outline should read
58
59	## Output shape rules
60
61	Keep these stable:
62	- `outline/outline.yml` is a YAML list
63	- `Introduction` and `Related Work` remain the first two H2 sections
64	- each H3 subsection contains the Stage A bullets: `Intent:` / `RQ:` / `Evidence needs:` / `Expected cites:`
65	- each H3 subsection adds several topic-specific bullets after the Stage A fields
66	- the helper never overwrites non-placeholder user work
67
68	## Quick Start
69
70	- `uv run python .codex/skills/outline-builder/scripts/run.py --help`
71	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
72
73	## Execution notes
74
75	When running this skill in compatibility mode, `scripts/run.py` currently reads:
76	- `outline/taxonomy.yml`, or
77	- `outline/chapter_skeleton.yml` + `outline/section_briefs.jsonl`
78	- `assets/outline_defaults.yaml`
79
80	The optional style references under `ref/agent-surveys/` are for human calibration only:
81	- use `ref/agent-surveys/STYLE_REPORT.md` to sanity-check chapter counts / thickness
82	- skim `ref/agent-surveys/text/` only to calibrate structure rather than wording
83
84	## Script
85
86	### Quick Start
87
88	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
89
90	### All Options
91
92	- `--workspace <dir>`
93	- `--unit-id <id>`
94	- `--inputs <path1;path2>`
95	- `--outputs <path1;path2>`
96	- `--checkpoint <C*>`
97
98	### Examples
99
100	- `uv run python .codex/skills/outline-builder/scripts/run.py --workspace <workspace>`
101
102	## Troubleshooting
103
104	- If `Related Work` still carries domain-specific framing, patch `assets/outline_defaults.yaml` before changing Python.
105	- If subsection bullets feel generic, review `references/stage_a_contract.md` and `references/examples_good.md`.
106	- If the outline is structurally valid but too fragmented, reroute to `outline-budgeter` rather than expanding this script.

People who liked this also viewed

6 picks

Type