Ready to supercharge your AI agents?

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

Genshijin Crew · interfacex-co-jp | DecimalAI

agent toolingby interfacex-co-jp

Genshijin Crew

interfacex-co-jp/genshijin-crew

Source interfacex-co-jp/genshijin ↗License MIT

原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。

SkillScore55Maintained

Automatic

Coding pack

Last verified 8/24/2026

What it changes

Passed 10 of 19 test cases with the skill, and 7 of 19 without it.

Without skill36%

With skill55%

Checks it passed that the model alone missed

The response halts and requests exact line numbers before executing the file edit.
The symbol name `calculateTaxRate` is enclosed in backticks in the finding entries.
The output reverts from compressed primitive dialect to standard natural Japanese for the security warning.

and 2 more in the full report

5 fixed7 passed either way9 still failing1 broke

Pass-rate lift: +18 pp
Tokens: +41%
Agent turns: 0%
Response time: -12%

Model gemini-3.6-flashMeasured 8/24/2026v112 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/interfacex-co-jp-genshijin-crew/SKILL.md https://app.decimal.ai/s/interfacex-co-jp-genshijin-crew/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add interfacex-co-jp-genshijin-crew, 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/interfacex-co-jp-genshijin-crew/ and pins it in .decimal/skills.lock

decimalai skills add interfacex-co-jp-genshijin-crew

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

curl -fsSL --create-dirs -o .claude/skills/interfacex-co-jp-genshijin-crew/SKILL.md https://app.decimal.ai/s/interfacex-co-jp-genshijin-crew/SKILL.md

Raw file: /s/interfacex-co-jp-genshijin-crew/SKILL.md ↗ · machine-readable summary at /s/interfacex-co-jp-genshijin-crew.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Refactor all 12 files in `src/controllers/` in a single builder execution pass by changing all callbacks to async/await.

What was checked, without and with the skill
Checked	Without skill	With skill
The response declines the multi-file edit pass and requests decomposing the refactor into single-file operations.	Missed	Passed

case-07 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md69 linessingle file

genshijin-crew = 原始人形式で出力する3 subagent preset。役割は Anthropic デフォルト (Explore、編集系 agent、reviewer) と同じ。差分は返ってくる tool-result が圧縮済 → 主コンテキスト消費が委譲毎に縮む。

genshijin-crew vs 代替の使い分け

タスク	使用
「Xの定義どこ / Yを呼ぶ箇所 / Zの全用法」	`genshijin-investigator`
同上 + アーキテクチャ解説/提案も欲しい	`Explore` (vanilla)
Surgical編集、≤2ファイル、スコープ明確	`genshijin-builder`
新機能 / 3+ファイル / cross-cutting refactor	主スレッド or `feature-dev:code-architect`
Diff/branch/file の bug レビュー	`genshijin-reviewer`
rationale + alternatives 付き深いコードレビュー	`Code Reviewer` (vanilla)
1行回答済の確実な内容	主スレッド、subagent不要

判断基準: subagent 出力を1/3トークンで欲しいなら genshijin-crew、散文で欲しいなら vanilla。

なぜ存在するか (実利)

Subagent tool-result は主コンテキストに verbatim 注入される。Vanilla Explore が散文2k tokens 返すと毎回主コンテキスト2k消費。同じ発見が genshijin-investigator だと約700 tokens。1セッション20委譲で context exhaustion vs タスク完了の差。

出力契約

主スレッドが agent 別に依拠できる形式:

genshijin-investigator

<Header>:
- path:line — `symbol` — short note
集計: <counts>。

or No match. 必ずファイルパス先頭、行番号付、シンボルはバッククォート。path:\d+ で grep可能。

genshijin-builder

<path:line-range> — <change ≤10語>。
verified: <re-read OK | mismatch @ path:line>。

or 以下のいずれか: too-big. / needs-confirm. / ambiguous. / regressed. (terminal first token)。

genshijin-reviewer

Track record

Benchmark

10 / 19

test cases passed, vs 7 / 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

interfacex-co-jp / genshijin

skills/genshijin-crew/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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

juliusbrussee/cavecrewDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/rClose match+55 pp pass-rate lift

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