genshijin-crew
Delegate Coding Tasks to Compact Subagents
Long subagent responses consume context and shorten productive coding sessions. This skill selects compact investigator, builder, and reviewer workflows for focused tasks.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "genshijin-crew" from https://skillstore.io/skills/interfacex-co-jp-genshijin-crew.md and its manifest at https://skillstore.io/api/skills/interfacex-co-jp-genshijin-crew/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "genshijin-crew". Find every caller of the payment retry function.
Expected outcome:
- Callers: three matches with file paths, line numbers, symbols, and short notes.
- Summary: three callers across two files.
Using "genshijin-crew". Review the authentication diff for bugs.
Expected outcome:
- A high-severity finding identifies the affected file and line.
- The finding states the problem and a concise correction.
- Totals summarize findings by severity.
Using "genshijin-crew". Change the known validation branch in one file.
Expected outcome:
The response identifies the edited line range, summarizes the change, and confirms the file was reread successfully.
Security Audit
SafeAll 32 external-command detections are false positives caused by Markdown backticks around agent names, status tokens, and output examples. The entropy alert is also false because SKILL.md contains readable Japanese guidance and no encoded, encrypted, or executable payload.
Risk Factors
⚙️ External commands (32)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/interfacex-co-jp-genshijin-crew/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/interfacex-co-jp-genshijin-crew?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/interfacex-co-jp-genshijin-crew?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/interfacex-co-jp-genshijin-crew/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/interfacex-co-jp-genshijin-crew.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
interfacex-co-jp. (2026). genshijin-crew security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/interfacex-co-jp-genshijin-crew/audits/1BibTeX citation
@techreport{interfacex-co-jp-interfacex-co-jp-genshijin-crew-2026,
author = {interfacex-co-jp},
title = {genshijin-crew security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/interfacex-co-jp-genshijin-crew/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "genshijin-crew security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "interfacex-co-jp"
date-released: "2026-09-24"
url: "https://skillstore.io/skills/interfacex-co-jp-genshijin-crew/audits/1"
identifiers:
- type: other
value: "skillstore:interfacex-co-jp-genshijin-crew:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Locate Code Quickly
Find definitions, callers, tests, and usage sites with compact path and line references.
Complete Small Edits
Delegate a clear one-file or two-file change and receive a concise verification result.
Review Focused Changes
Inspect a diff, branch, or file for bugs and receive ordered findings with severity.
Try These Prompts
Use genshijin-investigator to find the definition of [symbol]. Return compact path and line references.
Use genshijin-investigator to find definitions, callers, and tests for [symbol]. Separate each result type.
Use genshijin-builder to update [path:line] for [change]. Keep the edit within two files and verify the result.
Find [behavior], choose up to two edit sites, apply [change], then review the resulting diff for bugs.
Best Practices
- Provide a known path and line before assigning a builder task.
- Use parallel investigators only when each explores a distinct question.
- Use the main agent for large changes and architecture decisions.
Avoid
- Do not assign a builder task before locating the relevant files.
- Do not chain the compact builder for changes spanning three or more files.
- Do not request broad architecture feedback from the focused reviewer.
Frequently Asked Questions
What does this skill provide?
Does this skill include the subagent implementations?
When should I use the investigator?
When should I use the builder?
When should I use the reviewer?
When should I use a standard agent instead?
Developer Details
Author
interfacex-co-jpLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
2aa351cb09c29b7287d263bd8ea81e9bee3b2a61
Maintenance freshness
9/30/2026
Usage
0 downloads · 0 views
File structure
📄 SKILL.md