Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Chunin Skill

ASecurity

Standard Operating Procedures for web research, documentation lookup, evidence synthesis with citations.

9 stars
0 votes
0 copies
0 views
Added 9/22/2026
researchapidocumentation

Works with

apimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add andycungkrinx91/konoha --skill chunin-skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Chunin Skill?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Chunin Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andycungkrinx91-chunin-skill-e7549da2/badge)](https://www.skillsdirectory.com/skills/andycungkrinx91-chunin-skill-e7549da2)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: chunin-skill
description: Standard Operating Procedures for web research, documentation lookup, evidence synthesis with citations.
tags:
  - chunin
  - research
  - documentation
  - web-search
  - citations
---

# Chunin: Research & Intel

This skill provides the **Standard Operating Procedures (SOP)** for the Chunin agent — web research, documentation lookup, and evidence synthesis.

## Workflow Role

In the 8-phase Konoha workflow, Chunin handles **Phase 4: research**. The orchestrator dispatches the chunin MCP agent after `plan` (kage) sets `needs_research=True` and populates `research_query` on `plan.md`. Chunin conducts external web research, pulls cited evidence, and writes `result_chunin.md`. Upon completion, the orchestrator immediately re-invokes kage inline (phase back to `plan` with `needs_replan=True`) so the architecture plan can be updated with the new external findings before advancing to `execute`.

> [!NOTE]
> **Tool Usage & Token Preservation**: Use **`konoha` MCP** server (`find_skill`, `get_skill`) for all skill/instruction discovery. Do NOT call `semble` tools (search, find_related) for finding or locating skills, as `semble` is strictly a project code search engine and querying it burns quota tokens. Always use `konoha` MCP tools (`find_skill`, `get_skill`) for discovering and reading skills and reference documents. NEVER use `semble` search for skills.

## SOP 1: Research Decomposition
1. Break complex questions into 3-5 sub-queries.
2. Execute searches in parallel batches.
3. Rank sources by credibility, freshness, and relevance (0-10).
4. Every claim must have a numbered citation with URL.

## SOP 2: Evidence Synthesis
1. Gather at least 2 research iterations per topic.
2. Cross-reference sources for accuracy.
3. Produce a cited report with prioritized findings.

## SOP 3: Redirect Code Questions
1. If the user asks about codebase internals, redirect to `@mcp_Genin`.
2. Focus only on external information (docs, blogs, standards).

## Domain Routing

Based on the user's request, load the specific reference file using `konoha.get_skill("chunin-skill/<reference-name>")` (for internal references) or `konoha.get_skill("<skill-name>")` (for global skills). **Never guess implementation details or read files under .agents/skills/ directly.**

| If the request involves... | Load this reference |
|---|---|
| Final response shaping, ADHD-friendly concise output, action-first answers | `i-have-adhd` |

Attribution

andycungkrinx91andycungkrinx91
View sourceMore from andycungkrinx91 →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

492472 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

813271 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

492471 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →