Ready to supercharge your AI agents?

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

Project structure lifecycle · light0305 | DecimalAI

codingby light0305

Project structure lifecycle

light0305/light-project-structure

Source light0305/light-skills ↗License MIT

Audit, plan, scaffold, and safely migrate research project structures across greenfield, existing Git/non-Git repositories, and monorepo subroots.

SkillScore82Maintained

Automatic

Coding pack

Last verified 8/20/2026

What it changes

Passed 16 of 19 test cases with the skill, and 3 of 19 without it.

Without skill14%

With skill82%

Checks it passed that the model alone missed

Runs python scripts/scaffold.py --selftest.
Refuses to run scaffold mode on a non-empty directory.
Runs python scripts/structure_governance_gate.py --selftest.

and 24 more in the full report

15 fixed3 passed either way4 still failing0 broke

Pass-rate lift: +68 pp
Tokens: +58%
Agent turns: 0%
Response time: -52%

Model gemini-3.6-flashMeasured 8/20/2026v118 of 22 cases passed with skill · 19 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/light0305-light-project-structure/SKILL.md https://app.decimal.ai/s/light0305-light-project-structure/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add light0305-light-project-structure, 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/light0305-light-project-structure/ and pins it in .decimal/skills.lock

decimalai skills add light0305-light-project-structure

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

curl -fsSL --create-dirs -o .claude/skills/light0305-light-project-structure/SKILL.md https://app.decimal.ai/s/light0305-light-project-structure/SKILL.md

Raw file: /s/light0305-light-project-structure/SKILL.md ↗ · machine-readable summary at /s/light0305-light-project-structure.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

We need to run an ad-hoc local environment sanity check specifically for Python and R toolchains before running an intake scan. What command performs this standalone environment check?

What was checked, without and with the skill
Checked	Without skill	With skill
Executes python scripts/structure_governance_gate.py --doctor python r.	Missed	Passed

case-11 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md257 lines7 filesincludes scripts

Project structure lifecycle

Own the visible project tree and its migration evidence. Do not mistake a tidy directory for reproducible research.

Read references/project-lifecycle-resource-map.md before an existing-repository migration. It defines artifacts, policy, access levels, provenance, and cross-skill ownership. Use references/structure-profiles.json for small profile minima and templates/project-policy.template.json for explicit project/file policy. Use scripts/structure_governance_gate.py before delivery to validate profile choice, existing-project read-only safety, template residuals, secret scan, environment doctor, authorization binding, applied-manifest binding, and rollback evidence.

Non-negotiable boundary

Treat inventory as read-only access, not authorization to move.
Never overwrite, delete, run git rm --cached, initialize DVC, rewrite configuration, or move a symlink automatically.
Never use --force as consent. The lifecycle has no force bypass.
Preserve all .light/ content. memory-pm alone creates or edits passport, project card, decision log, version history, terminology, and handoff files.
Keep absent facts UNKNOWN. A path such as data/raw does not prove size, sensitivity, immutability, recomputability, or Git policy.
Do not turn this overlay into a DAG node. Emit no light.findings.v1; add no STAGE_GATES, ROUTES, stage number, or back-edge.
State that structural conformance does not prove data quality, experiment reproducibility, statistical validity, or paper quality.
Never ship a generated or migrated tree with unresolved template placeholders, unhandled secret-scan hits, or missing required Python/R/environment checks.

Choose the mode

Situation	Mode
Empty target and the user wants a starting tree	`scaffold` with one explicit profile

Track record

Benchmark

16 / 19

test cases passed, vs 3 / 19 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

light0305 / light-skills

skills/light-project-structure/SKILL.md

View on GitHub ↗

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

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

Project structure lifecycle

Non-negotiable boundary

Choose the mode

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills