Ready to supercharge your AI agents?

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

Get Started Free →

front-door (ONESHOT v6.0) · majiayu000 | DecimalAI

agent toolingby majiayu000

front-door (ONESHOT v6.0)

majiayu000/front-door

Source majiayu000/claude-skill-registry ↗License MIT

Intelligent entry point for all tasks. Interviews, triages, and routes.

SkillScore86Maintained

Automatic

Product Management pack

Last verified 9/1/2026

What it changes

Passed 19 of 22 test cases with the skill, and 7 of 22 without it.

Without skill32%

With skill86%

Checks it passed that the model alone missed

Classifies intent as fix_existing.
Classifies intent as continue_work.
Classifies the triage intent as modify_existing.

and 14 more in the full report

12 fixed7 passed either way3 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +170%
Agent turns: 0%
Response time: -26%

Model gemini-3.6-flashMeasured 9/1/2026v119 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/majiayu000-front-door/SKILL.md https://app.decimal.ai/s/majiayu000-front-door/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-front-door, 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/majiayu000-front-door/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-front-door

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-front-door/SKILL.md https://app.decimal.ai/s/majiayu000-front-door/SKILL.md

Raw file: /s/majiayu000-front-door/SKILL.md ↗ · machine-readable summary at /s/majiayu000-front-door.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I left off work yesterday on the user management service. Resume work on this project.

What was checked, without and with the skill
Checked	Without skill	With skill
Classifies intent as continue_work.	Missed	Passed
Checks for existing handoff documentation or context files from the previous session.	Missed	Passed

case-07 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md494 linessingle file

front-door (ONE_SHOT v6.0)

You are executing the front-door skill - the intelligent orchestration hub for ONE_SHOT.

Prime Directive

USER TIME IS PRECIOUS. AGENT COMPUTE IS CHEAP. Ask ALL questions UPFRONT. Get ALL info BEFORE coding. NEVER REWRITE FROM SCRATCH. Extend, refactor, use existing solutions.

When To Use

User says "new project", "build me", "create", "start fresh"
User says "help me", "/front-door", "/interview"
TRIAGE intent = build_new or modify_existing
Multi-file changes or unclear requirements detected
User explicitly requests interview mode

Auto-Detection Signals (Triggers Interview)

Any of these signals invoke the interview flow:

Vague scope: User says "build me X" without specifics
Multi-domain request: Spans UI + backend + infra
Missing context: References things not found in codebase
High-stakes change: Refactors, migrations, >5 files

Smart Bypass for Trivial Tasks

One triage question first:

"This seems straightforward - proceed directly or discuss first?"

Bypass signals (STRICT - all must apply):

"typo" → Single word/character fix only
"rename" → Search-replace operation with explicit before/after
Explicit file path provided + estimated <10 lines change

Signals that DO NOT bypass (require at least mini-interview):

"just add" → Still need to understand where and how
"quick fix" → Could hide complexity
"simple change" → Subjective, verify first

Track record

Benchmark

19 / 22

test cases passed, vs 7 / 22 without

Adoption

Users: 1
Times used: 7

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

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

majiayu000 / claude-skill-registry

skills/agent/front-door/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.