Ready to supercharge your AI agents?

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

Get Started Free →

template-storybook · docxology | DecimalAI

docxology/template-storybook

SkillScore95Maintained

Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.

codingby docxology

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

Automatic

Coding pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/docxology-template-storybook/SKILL.md

decimalai skills pull docxology-template-storybook --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/docxology-template-storybook/SKILL.md https://app.decimal.ai/s/docxology-template-storybook/SKILL.md

Raw file: /s/docxology-template-storybook/SKILL.md ↗ · machine-readable summary at /s/docxology-template-storybook.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 54d ago

Yes — +68% lift-30% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	54%	0%
case-02	✗→✓	▲ Improved	-32%	0%
case-13	✗→✓	▲ Improved	-53%	0%
case-05	✗→✓	▲ Improved	-68%	0%
case-06	✗→✓	▲ Improved	-32%	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

projects/templates/template_storybook/.agents/skills/template-storybook/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

template-storybook

Project-scoped skill for the in-repo exemplar at projects/templates/template_storybook/. Load this when working inside the project.

When to Use

Working inside the template_storybook exemplar — running scripts, editing story

content, or regenerating illustrated pages.

Forking this exemplar as the starting scaffold for a new illustrated-PDF project.
Validating that the exemplar's contracts (thin-orchestrator, layer boundaries,

no-mocks testing) still hold after changes.

Workflow

Read the project AGENTS.md.
Edit story content in content/story.yaml.
Put rendering behavior in src/storybook/ (models.py, characters.py,

story.py, illustration.py, text_layout.py, rendering.py) — never in scripts/.

Verify with tests and Stage-02 PDF generation.

Quick Reference

bash
# From the repository root
uv run pytest projects/templates/template_storybook/tests --cov=projects/templates/template_storybook/src --cov-fail-under=90
uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_storybook
uv run python scripts/pipeline/stage_03_render.py --project templates/template_storybook
uv run python scripts/pipeline/stage_04_validate.py --project templates/template_storybook
uv run python scripts/pipeline/stage_05_copy.py --project templates/template_storybook

Pitfalls

Keep scripts thin. Character construction, image composition, text

overlay, and PDF assembly belong in src/storybook/, not in scripts/.

No mocks. All tests must use real data, real files, and real

computation.

Outputs are disposable. Never hand-edit output/ — regenerate from

content/story.yaml and source.

Run from the repo root. Commands assume the template monorepo root

as working directory unless the child AGENTS.md states otherwise.

Cross-refs

Project contract: AGENTS.md
README: README.md
Exemplar roster: projects/AGENTS.md

Illustrative Want to see what docxology/template-storybook would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/4/2026, 00:54 UTC · 22 cases

Lift

+68%

95% vs 27%

Agent turns

0%

1.0 vs 1.0

Tokens

-30%

1,151.27 vs 1,648.73

fail → pass · 15pass → pass · 6fail → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I need to update the story text and add new text overlay layout logic for the storybook exemplar. What files should I edit to keep script and source layers properly separated, and what commands should I run from the main repository directory to test and generate the rendered PDF?	fail→pass	8,325	7,714	-7%	1	1	0%	1,169	1,806	+54%	0	0	—
case-02 I'm making changes inside `projects/templates/template_storybook/` and want to verify everything works end-to-end. What are the terminal commands to execute the test suite with coverage checks, followed by the pipeline stages for analysis, rendering, validation, and copying?	fail→pass	8,092	2,869	-65%	1	1	0%	1,559	1,065	-32%	0	0	—
case-03 We are using the storybook template as a scaffold for a new illustrated PDF project. Can you guide me through the standard workflow for editing story content, where to place rendering behaviors versus scripts, and how to execute the full build and verification pipeline?	fail→fail	19,736	11,187	-43%	1	1	0%	2,991	2,515	-16%	0	0	—
case-13 Which module inside projects/templates/template_storybook/src/storybook/ holds data model definitions for story elements?	fail→pass	11,161	2,215	-80%	1	1	0%	1,805	854	-53%	0	0	—
case-04 I am adding character construction and image composition code to the template_storybook exemplar. Should I place these helper functions directly into scripts/generate_storybook.py?	pass→pass	10,974	3,212	-71%	1	1	0%	1,597	1,134	-29%	0	0	—
case-05 Our coverage test for the template_storybook project failed during CI execution. What is the explicit coverage percentage target enforced by the project's test command?	fail→pass	14,884	2,097	-86%	1	1	0%	2,565	819	-68%	0	0	—
case-06 When writing unit tests for rendering logic in projects/templates/template_storybook/, I want to use unittest.mock to mock image generation and PDF writes. Is mock-based testing recommended here?	fail→pass	13,993	5,810	-58%	1	1	0%	2,359	1,608	-32%	0	0	—
case-07 I noticed a minor typo on page 3 of the rendered output in projects/templates/template_storybook/output/storybook.pdf. Can I open the PDF in a PDF editor and fix the text directly?	fail→pass	5,721	2,882	-50%	1	1	0%	942	1,123	+19%	0	0	—
case-08 Where in projects/templates/template_storybook/ should document layout and PDF assembly logic be implemented?	fail→pass	9,922	3,520	-65%	1	1	0%	1,796	1,154	-36%	0	0	—
case-09 I am executing stage scripts and pytest commands for projects/templates/template_storybook/. From which directory path should these commands be run?	pass→pass	6,747	2,293	-66%	1	1	0%	1,293	978	-24%	0	0	—
case-10 What exact command executes the validation pipeline stage (stage 4) for the template_storybook exemplar?	fail→pass	25,522	1,376	-95%	1	1	0%	2,272	761	-67%	0	0	—
case-11 What is the mandatory first step when starting work inside the template_storybook exemplar project?	fail→pass	5,744	1,688	-71%	1	1	0%	796	757	-5%	0	0	—
case-12 In projects/templates/template_storybook/, which Python file in the source directory should contain character construction and character definitions?	fail→pass	6,125	2,649	-57%	1	1	0%	998	1,030	+3%	0	0	—
case-14 Where should image composition and illustration rendering logic be placed in projects/templates/template_storybook/?	fail→pass	15,016	2,424	-84%	1	1	0%	2,409	909	-62%	0	0	—
case-15 What exact command executes the rendering stage (stage 3) for templates/template_storybook?	fail→pass	12,408	1,932	-84%	1	1	0%	1,916	822	-57%	0	0	—
case-16 Which source module in projects/templates/template_storybook/ handles narrative structure and story flow components?	fail→pass	7,945	3,286	-59%	1	1	0%	1,295	1,038	-20%	0	0	—
case-17 What runner command prefix is required for executing pytest and pipeline python scripts in the storybook project environment?	pass→pass	7,525	1,551	-79%	1	1	0%	1,381	795	-42%	0	0	—
case-18 Where is the roster listing all project exemplars located in the monorepo root structure?	fail→pass	10,297	1,719	-83%	1	1	0%	1,736	796	-54%	0	0	—
case-19 When editing text content for stories in projects/templates/template_storybook/, what file format and path should be edited?	fail→pass	8,972	2,490	-72%	1	1	0%	1,523	859	-44%	0	0	—
case-20 I am adding command-line option parsing to `scripts/pipeline/stage_02_analysis.py` at the repository root. Should this pipeline orchestration code be placed inside `projects/templates/template_storybook/src/storybook/`?	pass→pass	8,567	5,043	-41%	1	1	0%	1,514	1,429	-6%	0	0	—
case-21 I am writing unit tests for shared pipeline utilities in `tests/test_pipeline.py` at the repository root. Should the pytest coverage argument be set to `--cov=projects/templates/template_storybook/src` when running these tests?	pass→pass	12,856	4,576	-64%	1	1	0%	1,417	1,355	-4%	0	0	—
case-22 I am writing a standalone ReportLab diagnostic script in `scripts/check_reportlab.py` to verify PDF canvas creation. Does this script require creating `content/story.yaml` and defining models in `src/storybook/models.py`?	pass→pass	5,545	7,688	+39%	1	1	0%	939	1,721	+83%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 27.3%
Pass rate with the skill: 95.5%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/4/2026, 00:54 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I need to update the story text and add new text overlay layout logic for the storybook exemplar. What files should I edit to keep script and source layers properly separated, and what commands should I run from the main repository directory to test and generate the rendered PDF?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run95

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns-9% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 54 days ago

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