Ready to supercharge your AI agents?

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

Feature addition — measured AI agent skill | DecimalAI

docxology/template-feature-addition

SkillScore82Maintained

End-to-end feature work across src/, scripts/, tests/, manuscript, and docs for the Research Project Template. USE WHEN adding a pipeline-visible feature, new analysis stage, manuscript-facing output, or cross-layer integration — even without feature_addition prompt.

by docxology

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

Automatic

Coding pack

decimalai skills pull docxology-template-feature-addition

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-template-feature-addition/SKILL.md

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

—-37% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-10	✗→✓	▲ Improved	-10%	0%
case-09	✗→✓	▲ Improved	-33%	0%
case-12	✗→✓	▲ Improved	-50%	0%
case-17	✗→✓	▲ Improved	-63%	0%
case-19	✗→✓	▲ Improved	-34%	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/feature-addition/SKILL.md

View on GitHub ↗

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

Skill contents

references/

SKILL.md

Feature addition

Natural invoke

"Add convergence plotting to template_code_project end-to-end"
"New infrastructure gate wired into health CLI + tests + docs"
"Feature: export manifest JSON from analysis stage"

Inputs to confirm

Feature description — user-facing behavior.
Layer — infrastructure vs project (see code-development).
Project — if project layer.

Workflow

Design — logic in src/ or infrastructure/; script coordinates only.

Implement — src modules first (TDD: tests alongside).

Orchestrate — projects/<n>/scripts/ or root scripts/ stage hook if pipeline-visible.

Manuscript — figures/data paths, {{VARIABLE}} generated variables if numbers appear in prose.

Docs — AGENTS.md/README at affected dirs; no roster duplication.

Verify — project or infra tests; optional ./run.sh --project <n> --core-only slice.

Deliverables

File list by layer
Test + pipeline verification commands and exit codes

Verification commands

bash
uv run python scripts/pipeline/stage_01_test.py --project <project>
uv run python scripts/runner/execute_pipeline.py --project <project> --core-only

When NOT to use

Single function, no pipeline/manuscript touch → code-development
Refactor without new behavior → refactoring

References

Checklist: references/checklist.md

Want to see if docxology/template-feature-addition 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.