research-plan-implement SKILL.md skillA

research-plan-implement from kevinlin/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kevinlin/skills/research-plan-implement@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kevinlin/skills
Path
research-plan-implement/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Jul 17, 2026
Size
12,164 bytes
Repository stars
5
License
MIT

Complete Research \u2192 Plan \u2192 Implement workflow for complex tasks. Use this skill whenever the user faces: complex features spanning multiple files, bug investigations requiring root cause analysis, refactoring with architectural implications, or any non-trivial work where understanding the codebase first will prevent wasted effort. Also use when the user says things like 'help me figure out how to...', 'I need to understand before building...', or 'let\u2019s research this before…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Research → Plan → Implement Workflow

A structured three-phase approach for complex tasks. Instead of diving straight into code (which works fine for simple changes), this workflow front-loads understanding so that implementation goes smoothly the first time. Each phase produces a compact artifact that carries forward, keeping context clean as work progresses.

## When to use this skill

This skill earns its overhead when the task has **uncertainty** — you don't fully understand the codebase area, the right approach isn't obvious, or mistakes would be costly to undo:

- **Complex features** — New functionality touching multiple files and components
- **Bug investigation** — Issues where the root cause isn't obvious and needs tracing
- **Architectural refactoring** — Changes with ripple effects across the codebase
- **Unfamiliar codebases** — When you need to build understanding before acting

**Skip this skill for**: Simple fixes, typos, single-file changes, or tasks where the path forward is already clear.

## Workflow overview

```mermaid
flowchart TB
    A[Start: Task/Feature] --> B[Phase 1: Research]
    B --> C[Research Document]
    C --> D{Ready to plan?}
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kevinlin/skills/research-plan-implement@sha256:c76cb1525aead615

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vgbtvrgzjv5kitro.svg)](https://markdownregistry.com/a/art_vgbtvrgzjv5kitro)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 17, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-07-17 008f8cd 12,164 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12164 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kevinlin/skills · 5 stars · license MIT · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vgbtvrgzjv5kitro
GET https://markdownregistry.com/api/v1/resolve?ref=kevinlin/skills/research-plan-implement
GET https://markdownregistry.com/api/v1/blob/c76cb1525aead615ef742e7828aac0153ac8870628c9db10c72a665a2540ed43

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kevinlin/skills

CLAUDE.md CLAUDE.md file
kevinlin/skills · CLAUDE.md
git:20261027.0d3e083 · audit A · 5 stars
agent-insights SKILL.md skill
kevinlin/skills · agent-insights/SKILL.md · Generate a cross-tool usage insights report from locally stored AI coding agent sessions (Claude Code, Claude Cowork…
v1.6.1 · audit A · 5 stars
code-review-expert SKILL.md skill
kevinlin/skills · code-review-expert/SKILL.md · Expert code review with a senior engineer lens — covers architecture, SOLID principles, security vulnerabilities…
v1.0.0 · audit A · 5 stars
declawed SKILL.md skill
kevinlin/skills · declawed/SKILL.md · De-slop pass for any text: mechanically scans for the statistical tells of AI writing (the "not X but Y" reflex…
v1.2.2 · audit A · 5 stars
gap-analysis SKILL.md skill
kevinlin/skills · gap-analysis/SKILL.md · Use when producing or updating a gap-analysis HTML report. Triggers on "gap analysis", "gap register", "gap index"…
v1.1.0 · audit A · 5 stars
html-diagram SKILL.md skill
kevinlin/skills · html-diagram/SKILL.md · Use when the user needs an architecture or system diagram, a CI/CD, build, or release pipeline, an ETL or data…
v1.2.2 · audit A · 5 stars
spec-coding SKILL.md skill
kevinlin/skills · spec-coding/SKILL.md · Guide users through spec-driven development — from goal clarification through requirements, design, task planning, and…
v1.0.1 · audit A · 5 stars
spec-compact SKILL.md skill
kevinlin/skills · spec-compact/SKILL.md · Compact a spec plan (or design doc) markdown file after the implementation has shipped: strip the transient how — code…
v1.1.2 · audit A · 5 stars
CLAUDE.md@spec-compact/evals/fixtures/repos/lint-debris CLAUDE.md file
kevinlin/skills · spec-compact/evals/fixtures/repos/lint-debris/CLAUDE.md
git:20260814.841991c · audit B · 5 stars
CLAUDE.md@spec-compact/evals/fixtures/repos/shipped-plan CLAUDE.md file
kevinlin/skills · spec-compact/evals/fixtures/repos/shipped-plan/CLAUDE.md
git:20260814.841991c · audit B · 5 stars
CLAUDE.md@spec-compact/evals/fixtures/repos/unshipped-plan CLAUDE.md file
kevinlin/skills · spec-compact/evals/fixtures/repos/unshipped-plan/CLAUDE.md
git:20260814.841991c · audit B · 5 stars
spec-lint SKILL.md skill
kevinlin/skills · spec-lint/SKILL.md · Lint the project's specification docs (requirements / design / plan / task markdown): orphan specs, dead cross-doc…
v1.2.1 · audit A · 5 stars

Every file in kevinlin/skills

Browse by kind, by grade A, or by owner.