Ready to supercharge your AI agents?

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

Agentic Project Builder · lakreame | DecimalAI

codingby lakreame

Agentic Project Builder

lakreame/build-loop

Source lakreame/build-loop ↗License MIT

Agentic loop skill for building SaaS, DaaS, and AIaaS projects as a Senior Software Developer. Activate this skill whenever the user wants to build, plan, scaffold, or develop any software project — especially SaaS platforms, data services, or AI-powered services. Always trigger on phrases like "build me a SaaS", "start a new project", "scaffold this", "I want to create a service that...", "agentic loop", "let's build X", or any product or feature request involving this tech stack: React, TypeSc

SkillScore77Maintained

Automatic

Coding pack

Last verified 8/3/2026

What it changes

Passed 17 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill77%

Checks it passed that the model alone missed

The DONE status is YES.
The output contains LOOP: 0.
The output contains SCOPE: MVP.

and 13 more in the full report

9 fixed8 passed either way4 still failing1 broke

Pass-rate lift: +36 pp
Tokens: +79%
Agent turns: 0%
Response time: -27%

Model gemini-3.6-flashMeasured 8/3/2026v117 of 22 cases passed with skill

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/lakreame-build-loop/SKILL.md https://app.decimal.ai/s/lakreame-build-loop/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lakreame-build-loop, 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/lakreame-build-loop/ and pins it in .decimal/skills.lock

decimalai skills add lakreame-build-loop

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

curl -fsSL --create-dirs -o .claude/skills/lakreame-build-loop/SKILL.md https://app.decimal.ai/s/lakreame-build-loop/SKILL.md

Raw file: /s/lakreame-build-loop/SKILL.md ↗ · machine-readable summary at /s/lakreame-build-loop.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Produce the Phase 3 [VERIFY] block when all planned subtasks pass, code review passes, and security checks are skipped.

What was checked, without and with the skill
Checked	Without skill	With skill
The DONE status is YES.	Missed	Passed
The output asks the user whether to continue or stop.	Missed	Passed

case-18 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md246 lines13 files

Agentic Project Builder

Senior Software Developer skill for building SaaS / DaaS / AIaaS through a structured loop:

Prompt → Plan → Execute → Verify → Iterate

One external sub-skill is loaded when relevant:

engineering:code-review — structured code review, loaded inline during Verify

Frontend design guidance and security review are fully embedded in this skill.

Token Efficiency — Caveman Integration

Load references/caveman.md at session start and apply it for the full session. Full caveman rules, intensity levels, auto-clarity triggers, and persistence logic live there.

Default intensity: full. Switch mid-session with /caveman lite|full|ultra if needed.

Agentic-loop overrides (take precedence over base caveman rules):

Phase headers [PLAN] [EXEC] [VERIFY] [ITERATE] → always kept verbatim
Code files, CLI commands, schema → always full, never caveman-compressed
User-facing questions and confirmations → short prose, not fragments
Security warnings and irreversible actions → full prose (caveman auto-clarity rule applies)
External sub-skill calls noted inline: [SUB: code-review]

Loop Protocol

Phase 0 — PROMPT (Session Init)

Collect:

Goal — one sentence
Type — SaaS / DaaS / AIaaS (or hybrid)
Stack — from the Stack Menu below
Scope — MVP or full product?

Track record

Benchmark

17 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan14 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

No issues (informational notes only).

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

lakreame / build-loop

plugins/build-loop/skills/build-loop/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 12 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

lakreame/agentic-project-builderAgentic loop skill for building SaaS, DaaS, and AIaaS projects as a Senior Software Developer. Trigger when the user wants to build, plan, scaffold, or develop a software project or product — phrases like "build me a SaaS", "start a new project", "scaffold this", "I want to create a service that...", "agentic loop", "let's build X" — or mid-project when adding features, changing architecture, or resuming a build. Preferred stack: React, TypeScript, Flutter, Node.js, C#, .NET, Python, PostgreSQL,Near-identical description+18 pp pass-rate lift

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

Agentic Project Builder

Token Efficiency — Caveman Integration

Loop Protocol

Phase 0 — PROMPT (Session Init)

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills