Ready to supercharge your AI agents?

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

template-template · docxology | DecimalAI

docxology/template-template

SkillScore87Maintained

Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.

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-template/SKILL.md

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

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

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

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

23 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 — +61% lift-25% tokens0% turns87% of whole cases pass with skill (20/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-21%	0%
case-03	✗→✓	▲ Improved	483%	0%
case-04	✗→✓	▲ Improved	-28%	0%
case-05	✗→✓	▲ Improved	68%	0%
case-06	✗→✓	▲ Improved	-47%	0%

Showing 5 of 23 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_template/.agents/skills/template-template/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

template-template

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

When to Use

Working inside the template_template exemplar — running scripts, editing source,

or regenerating outputs.

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

no-mocks testing) still hold after changes.

Quick Reference

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

Pitfalls

Keep scripts thin. Business logic belongs in src/ or shared

infrastructure/, 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

source and config.

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
TODO: TODO.md
Exemplar roster: projects/AGENTS.md

Illustrative Want to see what docxology/template-template 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, 00:55 UTC · 23 cases

Lift

+61%

87% vs 26%

Agent turns

1.0 vs 1.0

Tokens

-25%

1,183.87 vs 1,582.65

fail → pass · 14pass → pass · 6fail → fail · 3

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-08 I am adding a complex matrix calculation function for the `template_template` project. Should I put this calculation helper in `scripts/pipeline/stage_02_analysis.py` to keep it near the analysis code, or where should it live?	pass→pass	12,869	3,129	-76%	1	1	0%	1,890	998	-47%	0	0	—
case-09 The tests for `template_template` take 15 seconds because they read real test files from disk and calculate SHA-256 hashes. Can I use `unittest.mock` or `pytest-mock` to mock disk IO and speed up the test suite?	fail→pass	12,790	7,437	-42%	1	1	0%	2,104	1,668	-21%	0	0	—
case-01 I just made some modifications to the core business logic inside `projects/templates/template_template/src`. Please execute the project's test suite to ensure coverage requirements are satisfied without relying on mocks.	fail→fail	16,504	4,203	-75%	1	1	0%	2,778	643	-77%	0	0	—
case-02 We need to refresh all rendered documents for `templates/template_template`. Could you run the pipeline execution steps (from analysis through validation and copy) starting from the repository root?	fail→fail	5,698	2,450	-57%	1	1	0%	339	736	+117%	0	0	—
case-03 I'm using `projects/templates/template_template` as a starter scaffold for a new project. Please validate that all its build stages and automated test suites pass cleanly.	fail→pass	5,193	8,130	+57%	1	1	0%	373	2,173	+483%	0	0	—
case-04 I need to run just the data analysis portion of the build for `templates/template_template`. I'm thinking of cd'ing into `projects/templates/template_template/scripts` and running `python analysis.py`. How should this stage actually be executed?	fail→pass	9,384	4,530	-52%	1	1	0%	1,568	1,126	-28%	0	0	—
case-05 We need to generate the document renders for `templates/template_template`. I plan to execute `python scripts/pipeline/stage_03_render.py` directly without parameters. What is the precise command to run?	fail→pass	3,712	3,053	-18%	1	1	0%	618	1,036	+68%	0	0	—
case-06 I want to run document validation for the exemplar project `templates/template_template`. Should I write a custom shell script in `scripts/` to validate output files?	fail→pass	11,254	3,189	-72%	1	1	0%	1,925	1,020	-47%	0	0	—
case-07 I'm ready to copy the generated artifacts for `templates/template_template` to their final distribution location. What is the standard script command to handle this stage?	fail→pass	9,350	1,957	-79%	1	1	0%	1,472	744	-49%	0	0	—
case-10 There's a minor typo in the rendered output document at `projects/templates/template_template/output/report.docx`. Can I quickly open Word or python-docx and fix the text inside `output/report.docx` directly?	fail→pass	7,509	2,983	-60%	1	1	0%	1,378	940	-32%	0	0	—
case-11 I'm writing a shell script to run all project tasks for `template_template`. Should the script `cd projects/templates/template_template` before executing python commands?	fail→pass	11,052	3,830	-65%	1	1	0%	1,882	1,191	-37%	0	0	—
case-12 I am configuring coverage reporting for `projects/templates/template_template`. I'm tempted to set `--cov-fail-under=80` since 80% is standard across python projects. What coverage threshold requirement applies here?	fail→pass	12,904	2,170	-83%	1	1	0%	1,661	784	-53%	0	0	—
case-13 When running pytest for `template_template`, should I point pytest at `projects/templates/template_template/` so it discovers all root files, or target a specific subfolder?	fail→pass	9,948	2,754	-72%	1	1	0%	1,450	943	-35%	0	0	—
case-14 I need to run the entire build and distribution pipeline for `templates/template_template`. In what sequence should the pipeline stages be executed?	fail→pass	9,111	5,097	-44%	1	1	0%	1,492	1,232	-17%	0	0	—
case-15 I'm adding a new feature to parse XML data inside `scripts/pipeline/stage_02_analysis.py`. I have written 250 lines of XML parsing logic directly in the script main function. Is this architectural pattern acceptable for template_template?	pass→pass	10,437	5,412	-48%	1	1	0%	2,010	1,423	-29%	0	0	—
case-16 Someone accidentally deleted the entire `output/` directory in `projects/templates/template_template/`. How should we restore these files?	fail→pass	9,505	4,057	-57%	1	1	0%	1,866	1,223	-34%	0	0	—
case-17 When invoking `stage_02_analysis.py` for `projects/templates/template_template`, what exact string format should be supplied to the `--project` argument?	pass→pass	7,522	1,837	-76%	1	1	0%	1,318	750	-43%	0	0	—
case-18 We are writing shared file conversion logic that will be used across multiple template exemplars, including `template_template`. Should this be placed in `scripts/pipeline/`?	fail→pass	10,700	6,031	-44%	1	1	0%	1,856	1,429	-23%	0	0	—
case-19 Where in the project hierarchy is the core agent contract document located relative to `projects/templates/template_template/` when looking for project-level guidance?	pass→pass	9,815	5,047	-49%	1	1	0%	1,749	1,308	-25%	0	0	—
case-20 We are creating a new research project scaffold by copying `projects/templates/template_template/`. What steps should be taken to verify that the copied scaffold operates correctly?	fail→pass	12,646	8,450	-33%	1	1	0%	2,172	1,950	-10%	0	0	—
case-21 I'm writing a general Python script using `python-docx` to change table cell background colors to light gray (`#F0F0F0`). What is the python-docx code snippet to achieve cell shading?	fail→fail	9,244	6,273	-32%	1	1	0%	1,931	1,617	-16%	0	0	—
case-22 How do I configure pytest in `pyproject.toml` to display local variables on failure (`--showlocals`) and generate an HTML coverage report using `pytest-cov`?	pass→pass	7,968	5,717	-28%	1	1	0%	1,516	1,482	-2%	0	0	—
case-23 What git command sequence should I run to create a feature branch named `feature/new-chart`, commit staged changes, and push to origin?	pass→pass	5,034	2,251	-55%	1	1	0%	1,053	813	-23%	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. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 26.1%
Pass rate with the skill: 87%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/4/2026, 00:55 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-09

Prompt

The tests for `template_template` take 15 seconds because they read real test files from disk and calculate SHA-256 hashes. Can I use `unittest.mock` or `pytest-mock` to mock disk IO and speed up the test suite?

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 run87

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-29% 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.