outline-agent

Name: outline-agent
Author: Ar9av

41installs86forks

How to install outline-agent?

ar9av/paperorchestra/outline-agent

$npx -y skills add Ar9av/PaperOrchestra --skill outline-agent

Installs into the current project.

Summary

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citat

Files · 1

View on GitHub

SKILL.md

1	# Outline Agent (Step 1)
2
3	Faithful implementation of the Outline Agent from PaperOrchestra
4	(Song et al., 2026, arXiv:2604.05018, App. F.1, pp. 40–44).
5
6	Cost: 1 LLM call.
7
8	## Your task
9
10	Read four input files from the workspace and produce a single JSON object at
11	`workspace/outline.json` with three top-level keys:
12
13	- `plotting_plan` — array of figure objects
14	- `intro_related_work_plan` — object with `introduction_strategy` and `related_work_strategy`
15	- `section_plan` — array of section objects, each with `section_title` and `subsections[]`
16
17	## How to do it
18
19	1. Read the verbatim prompt at `references/prompt.md`. This is the exact
20	Outline Agent system prompt from the paper. Use it as your system message.
21	2. Prepend the Anti-Leakage Prompt from
22	`../paper-orchestra/references/anti-leakage-prompt.md`.
23	3. Read the four input files:
24	- `workspace/inputs/idea.md`
25	- `workspace/inputs/experimental_log.md`
26	- `workspace/inputs/template.tex`
27	- `workspace/inputs/conference_guidelines.md`
28	4. Synthesize across all four — the global instruction in the prompt is
29	"Do not analyze inputs in isolation. You must synthesize information across
30	all provided documents for every step."
31	5. Emit a single JSON object following the schema in
32	`references/outline-schema.md`. Cross-check against
33	`references/outline_schema.json` (machine-readable).
34	6. Save to `workspace/outline.json`.
35	7. Validate:
36	```bash
37	python skills/outline-agent/scripts/validate_outline.py workspace/outline.json
38	```
39	If validation fails, fix the JSON and re-validate. Do not proceed to Step 2
40	or Step 3 with an invalid outline — every downstream agent depends on this
41	schema.
42
43	8. Append §1 to research_brief.md (see `skills/shared/research_brief_template.md`):
44
45	After `outline.json` passes validation, append the §1 section to
46	`workspace/research_brief.md` (create the file if absent). Template:
47
48	```markdown
49	## §1 · Core Claim and Narrative
50	_Written by: outline-agent, Step 1_
51
52	Core claim: <one-sentence contribution>
53	Narrative tension: <gap this paper resolves>
54	Key novelty framing: <how the contribution is framed relative to prior work>
55	Outline decisions:
56	- Plotting plan: <N> figures
57	- Related Work clusters: <names>
58	- Section structure: <section titles>
59	Potential weaknesses flagged at outline stage:
60	- <any claim in idea.md that may be hard to support>
61	```
62
63	This is a free-form prose append; no machine-readable schema required.
64
65	## Hard rules from the prompt (do not violate)
66
67	These are excerpted from `references/prompt.md`. The validator enforces them.
68
69	### Plotting plan (Directive 1)
70
71	- `plot_type` MUST be exactly one of `"plot"` or `"diagram"`.
72	- `data_source` MUST be exactly one of `"idea.md"`, `"experimental_log.md"`,
73	or `"both"`.
74	- `aspect_ratio` MUST be exactly one of:
75	`"1:1"`, `"1:4"`, `"2:3"`, `"3:2"`, `"3:4"`, `"4:1"`, `"4:3"`, `"4:5"`,
76	`"5:4"`, `"9:16"`, `"16:9"`, `"21:9"`.
77	- `figure_id` MUST be a semantically meaningful snake_case identifier
78	(e.g., `fig_framework_overview`, `fig_ablation_study_parameter_sensitivity`).
79	- `figure_id` MUST NOT contain the word `"Figure"`.
80
81	### Intro / Related Work strategy (Directive 2)
82
83	- Strictly separate Introduction (macro-level context, 10-20 papers,
84	foundational + survey + impact) from Related Work (micro-level technical
85	baselines, 30-50 papers, divided into 2-4 methodology clusters that
86	directly compete with or precede the proposed approach).
87	- For each Related Work cluster: provide `methodology_cluster`,
88	`sota_investigation_mission`, `limitation_hypothesis`,
89	`limitation_search_queries`, `bridge_to_our_method`.
90	- CRITICAL TIMELINE RULE: Do not instruct searches for any papers
91	published after `{cutoff_date}`. Derive `cutoff_date` from
92	`conference_guidelines.md` (e.g., "ICLR 2025 → cutoff October 2024",
93	"CVPR 2025 → cutoff November 2024"). If unspecified, default to one month
94	before today's date.
95
96	### Section plan (Directive 3)
97
98	- Structural hierarchy: if Subsection X.1 is created, X.2 is mandatory.
99	No orphaned subsections. Omit subsections entirely if a section does not
100	require division.
101	- Content specificity: each `content_bullets` entry must reference source
102	materials concretely. AVOID "Describe the model". REQUIRE "Formalize the
103	Temporal-Aware Attention mechanism using Eq. 3 from idea.md."
104	- Mandatory citations: every dataset, optimizer, metric, and
105	foundational archi

People who liked this also viewed

6 picks

Type

outline-agent

41installs86forks

View on GitHub

How to install outline-agent?

ar9av/paperorchestra/outline-agent

$npx -y skills add Ar9av/PaperOrchestra --skill outline-agent

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Outline Agent (Step 1)
2
3	Faithful implementation of the Outline Agent from PaperOrchestra
4	(Song et al., 2026, arXiv:2604.05018, App. F.1, pp. 40–44).
5
6	Cost: 1 LLM call.
7
8	## Your task
9
10	Read four input files from the workspace and produce a single JSON object at
11	`workspace/outline.json` with three top-level keys:
12
13	- `plotting_plan` — array of figure objects
14	- `intro_related_work_plan` — object with `introduction_strategy` and `related_work_strategy`
15	- `section_plan` — array of section objects, each with `section_title` and `subsections[]`
16
17	## How to do it
18
19	1. Read the verbatim prompt at `references/prompt.md`. This is the exact
20	Outline Agent system prompt from the paper. Use it as your system message.
21	2. Prepend the Anti-Leakage Prompt from
22	`../paper-orchestra/references/anti-leakage-prompt.md`.
23	3. Read the four input files:
24	- `workspace/inputs/idea.md`
25	- `workspace/inputs/experimental_log.md`
26	- `workspace/inputs/template.tex`
27	- `workspace/inputs/conference_guidelines.md`
28	4. Synthesize across all four — the global instruction in the prompt is
29	"Do not analyze inputs in isolation. You must synthesize information across
30	all provided documents for every step."
31	5. Emit a single JSON object following the schema in
32	`references/outline-schema.md`. Cross-check against
33	`references/outline_schema.json` (machine-readable).
34	6. Save to `workspace/outline.json`.
35	7. Validate:
36	```bash
37	python skills/outline-agent/scripts/validate_outline.py workspace/outline.json
38	```
39	If validation fails, fix the JSON and re-validate. Do not proceed to Step 2
40	or Step 3 with an invalid outline — every downstream agent depends on this
41	schema.
42
43	8. Append §1 to research_brief.md (see `skills/shared/research_brief_template.md`):
44
45	After `outline.json` passes validation, append the §1 section to
46	`workspace/research_brief.md` (create the file if absent). Template:
47
48	```markdown
49	## §1 · Core Claim and Narrative
50	_Written by: outline-agent, Step 1_
51
52	Core claim: <one-sentence contribution>
53	Narrative tension: <gap this paper resolves>
54	Key novelty framing: <how the contribution is framed relative to prior work>
55	Outline decisions:
56	- Plotting plan: <N> figures
57	- Related Work clusters: <names>
58	- Section structure: <section titles>
59	Potential weaknesses flagged at outline stage:
60	- <any claim in idea.md that may be hard to support>
61	```
62
63	This is a free-form prose append; no machine-readable schema required.
64
65	## Hard rules from the prompt (do not violate)
66
67	These are excerpted from `references/prompt.md`. The validator enforces them.
68
69	### Plotting plan (Directive 1)
70
71	- `plot_type` MUST be exactly one of `"plot"` or `"diagram"`.
72	- `data_source` MUST be exactly one of `"idea.md"`, `"experimental_log.md"`,
73	or `"both"`.
74	- `aspect_ratio` MUST be exactly one of:
75	`"1:1"`, `"1:4"`, `"2:3"`, `"3:2"`, `"3:4"`, `"4:1"`, `"4:3"`, `"4:5"`,
76	`"5:4"`, `"9:16"`, `"16:9"`, `"21:9"`.
77	- `figure_id` MUST be a semantically meaningful snake_case identifier
78	(e.g., `fig_framework_overview`, `fig_ablation_study_parameter_sensitivity`).
79	- `figure_id` MUST NOT contain the word `"Figure"`.
80
81	### Intro / Related Work strategy (Directive 2)
82
83	- Strictly separate Introduction (macro-level context, 10-20 papers,
84	foundational + survey + impact) from Related Work (micro-level technical
85	baselines, 30-50 papers, divided into 2-4 methodology clusters that
86	directly compete with or precede the proposed approach).
87	- For each Related Work cluster: provide `methodology_cluster`,
88	`sota_investigation_mission`, `limitation_hypothesis`,
89	`limitation_search_queries`, `bridge_to_our_method`.
90	- CRITICAL TIMELINE RULE: Do not instruct searches for any papers
91	published after `{cutoff_date}`. Derive `cutoff_date` from
92	`conference_guidelines.md` (e.g., "ICLR 2025 → cutoff October 2024",
93	"CVPR 2025 → cutoff November 2024"). If unspecified, default to one month
94	before today's date.
95
96	### Section plan (Directive 3)
97
98	- Structural hierarchy: if Subsection X.1 is created, X.2 is mandatory.
99	No orphaned subsections. Omit subsections entirely if a section does not
100	require division.
101	- Content specificity: each `content_bullets` entry must reference source
102	materials concretely. AVOID "Describe the model". REQUIRE "Formalize the
103	Temporal-Aware Attention mechanism using Eq. 3 from idea.md."
104	- Mandatory citations: every dataset, optimizer, metric, and
105	foundational archi

People who liked this also viewed

6 picks

Type