Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Outline Agent (Step 1) · ar9av | DecimalAI

researchby ar9av

Outline Agent (Step 1)

ar9av/outline-agent

Source ar9av/paperorchestra ↗License NOASSERTION

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 citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".

SkillScore45Maintained

Automatic

Research pack

Last verified 8/16/2026

What it changes

Passed 6 of 13 test cases with the skill, and 4 of 13 without it.

Without skill27%

With skill45%

Checks it passed that the model alone missed

Includes the Core claim field in the §1 research brief template.
Includes the Narrative tension field in the §1 research brief template.
Includes the bridge_to_our_method field within each methodology cluster.

and 4 more in the full report

5 fixed5 passed either way11 still failing1 broke

Pass-rate lift: +18 pp
Tokens: +52%
Agent turns: 0%
Response time: -59%

Model gemini-3.6-flashMeasured 8/16/2026v110 of 22 cases passed with skill · 13 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ar9av-outline-agent/SKILL.md https://app.decimal.ai/s/ar9av-outline-agent/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ar9av-outline-agent, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ar9av-outline-agent/ and pins it in .decimal/skills.lock

decimalai skills add ar9av-outline-agent

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ar9av-outline-agent/SKILL.md https://app.decimal.ai/s/ar9av-outline-agent/SKILL.md

Raw file: /s/ar9av-outline-agent/SKILL.md ↗ · machine-readable summary at /s/ar9av-outline-agent.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

For our main accuracy comparison chart, the raw timing data lives in `experimental_log.md` while the model formulation is in `idea.md`. I want to list `data_source` as `logs_and_idea`. Generate the figure plan entry.

What was checked, without and with the skill
Checked	Without skill	With skill
Sets data_source strictly to 'both' rather than custom strings like 'logs_and_idea'.	Missed	Passed

case-08 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md131 lines7 filesincludes scripts

Outline Agent (Step 1)

Faithful implementation of the Outline Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, App. F.1, pp. 40–44).

Cost: 1 LLM call.

Your task

Read four input files from the workspace and produce a single JSON object at workspace/outline.json with three top-level keys:

plotting_plan — array of figure objects
intro_related_work_plan — object with introduction_strategy and related_work_strategy
section_plan — array of section objects, each with section_title and subsections[]

How to do it

Read the verbatim prompt at references/prompt.md. This is the exact Outline Agent system prompt from the paper. Use it as your system message.
Prepend the Anti-Leakage Prompt from ../paper-orchestra/references/anti-leakage-prompt.md.
Read the four input files:
- workspace/inputs/idea.md
- workspace/inputs/experimental_log.md
- workspace/inputs/template.tex
- workspace/inputs/conference_guidelines.md
Synthesize across all four — the global instruction in the prompt is "Do not analyze inputs in isolation. You must synthesize information across all provided documents for every step."
Emit a single JSON object following the schema in references/outline-schema.md. Cross-check against references/outline_schema.json (machine-readable).
Save to workspace/outline.json.
Validate:
```
python skills/outline-agent/scripts/validate_outline.py workspace/outline.json
```
If validation fails, fix the JSON and re-validate. Do not proceed to Step 2 or Step 3 with an invalid outline — every downstream agent depends on this

Track record

Benchmark

6 / 13

test cases passed, vs 4 / 13 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ar9av / paperorchestra

skills/outline-agent/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 6 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Outline Agent (Step 1)

Your task

How to do it

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills