Ready to supercharge your AI agents?

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

Manuscript creation — measured AI agent skill | DecimalAI

docxology/template-manuscript-creation

SkillScore77Maintained

Scaffold a research manuscript and project layout from a research brief — sections, config.yaml, src/, scripts/, tests. USE WHEN starting a new paper, new projects/ tree, manuscript from topic description, or aligning with template_code_project exemplar — even without copy-paste prompts.

by docxology

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull docxology-template-manuscript-creation

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-template-manuscript-creation/SKILL.md

Raw file: /s/docxology-template-manuscript-creation/SKILL.md ↗ · machine-readable summary at /s/docxology-template-manuscript-creation.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6d ago

—-2% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	51%	0%
case-08	✗→✓	▲ Improved	-37%	0%
case-09	✗→✓	▲ Improved	-59%	0%
case-12	✗→✓	▲ Improved	-18%	0%
case-13	✗→✓	▲ Improved	10%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

docxology / template

docs/prompts/manuscript-creation/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1Bundled 3 files

Skill contents

references/

SKILL.md

Manuscript creation

Natural invoke

"Create a new optimization research project and manuscript from this brief"
"Scaffold projects/my_topic/ like template_code_project"
"I have a research idea — set up manuscript + src + tests"

Inputs to confirm

Research topic — objectives, methods, expected contributions (user provides).
Exemplar — default projects/templates/template_code_project/; Active Inference multi-track → template_active_inference; prose → template_prose_project; AutoResearch/readiness loop → template_autoresearch_project; meta-template / infrastructure introspection → template_template; search → public template_search_project. Roster: docs/_generated/active_projects.md and projects/AGENTS.md.
Cross-ref style — Pandoc-crossref vs registry tokens (pick one; see manuscript-cross-references).

Workflow

Copy exemplar shape — match section numbering (01_* vs 00_*), not generic skeleton if exemplar differs.

Manuscript files — config.yaml, preamble.md, references.bib, ordered *.md sections, glossary/references as exemplar does.

Cross-refs — Pandoc: @fig:, @eq:, @sec:, [@key] per docs/guides/manuscript-semantics.md. Registry: refs/labels.yaml + [[FIG:]] tokens.

src/ — typed public APIs, get_logger, fixed seeds, custom exceptions where needed.

scripts/ — thin orchestrators only; MPLBACKEND=Agg; print output paths.

tests/ — no mocks; ≥90% on projects/<name>/src.

Docs — project AGENTS.md + README.md; link active_projects doc, do not hard-code roster.

One-shot alternative — for LLM scaffold of entire tree, see docs/guides/new-project-one-shot-prompt.md.

Deliverables

Full projects/<name>/ tree or delta from brief
How to run: uv run pytest projects/<name>/tests/ --cov=... and uv run python scripts/pipeline/stage_01_test.py --project <name>

Verification commands

bash
uv sync
uv run python scripts/pipeline/stage_01_test.py --project <name>
uv run python -m infrastructure.validation.cli markdown projects/<name>/manuscript/

When NOT to use

Existing manuscript claim audit → manuscript-claim-verification
Cross-ref-only fixes → manuscript-cross-references

References

Section checklist and legacy examples: references/structure-checklist.md

Want to see if docxology/template-manuscript-creation would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.