Search everything...

Stats

Actions

Available In

engineering-skills

Name: engineering-skills
Author: bradykim7

By bradykim7

엔지니어링 워크플로우 스킬 모음. diagnose, tdd, triage, to-prd, to-issues, zoom-out, improve-codebase-architecture, prototype, grill-with-docs, grill-me 포함.

npx claudepluginhub bradykim7/agcoco --plugin engineering-skills

Popularity

Stars

Above avg

Med: 0·Avg: 280

Installs

Med: 0·Avg: 1

What's Inside

Skills11

diagnose

/diagnose

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

grill-me

/grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

grill-with-docs

/grill-with-docs

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

improve-codebase-architecture

/improve-codebase-architecture

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

prototype

/prototype

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Stats

Version1.0.0

LanguagePython

Stars2

Forks2

MaintenanceGood

Last CommitMay 13, 2026

AddedMay 13, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

agcoco2

README

agcoco

agcoco = Agent-Coding-Config — pronounced "AG-co-co". AI 에이전트 코딩을 위한 개인 dotfiles 레포 (Claude Code, Codex 등 멀티툴 지원).

Personal dotfiles repo for AI agent-assisted coding. Manages custom slash commands, sub-agents, skills, and per-tool symlinks for any CLI that follows the AGENTS.md convention (Claude Code, Codex, and easily extensible to Gemini / Cursor / Aider / Continue via tools/<name>.sh).

Architecture

agcoco architecture

Quick Start

git clone <repo-url> ~/agcoco
cd ~/agcoco
./install.sh

What's Included

Commands (20개)

Category	Commands
Plan Lifecycle	`/create-plan`, `/implement-plan`, `/iterate-plan`, `/validate-plan`
Research & Debug	`/research`, `/debug`
Session	`/handoff`, `/resume-handoff`
Test	`/workcheck`, `/affected-endpoints`, `/smoke-test`, `/branch-diff`, `/test-affected`
Commit & PR	`/workfinish`, `/commit-mailplug`, `/commit-suggest`, `/pr-description`
Claude Usage	`/claude-usage-collect`, `/claude-usage-analyze`, `/claude-usage-report`

Agents (12개)

Commands trigger these automatically — you don't call them directly.

Agent	Role
`codebase-analyzer`	Code implementation analysis
`codebase-locator`	File/component location (Super Grep)
`codebase-pattern-finder`	Find similar patterns + code examples
`docs-locator`	Search past plans/research/handoffs
`docs-analyzer`	Extract insights from past documents
`web-search-researcher`	Web search for up-to-date info
`architecture-review`	Architecture risk analysis
`endpoint-analysis`	API endpoint behavior analysis
`pr-review-assistant`	PR risk-focused review
`consistency-check`	Data snapshot comparison
`document-summarizer`	Document summarization
`pr-description-generator`	PR description generation

Skills (22개)

Ported from mattpocock/skills (MIT). Skills auto-fire when your phrasing matches their description field — no slash command needed.

Category	Skill	Triggers when you say…
engineering	`setup-matt-pocock-skills`	"set up the engineering skills for this repo" — run first in any new project
	`grill-with-docs`	"stress-test this plan against our domain model"
	`to-prd`	"turn this conversation into a PRD"
	`to-issues`	"break this plan into issues"
	`triage`	"triage these incoming issues"
	`tdd`	"let's TDD this", "red-green-refactor"
	`diagnose`	"diagnose this bug", "this is broken/throwing/failing"
	`improve-codebase-architecture`	"find refactoring opportunities", "improve architecture"
	`prototype`	"let me prototype this", "try a few UI variations"
	`zoom-out`	"zoom out", "give me the bigger picture"
productivity	`grill-me`	"grill me on this plan", "interview me"
	`caveman`	(terse output mode)
	`write-a-skill`	"create a new skill"
misc	`git-guardrails-claude-code`	"block dangerous git commands", "add git safety hooks"
	`setup-pre-commit`	"set up pre-commit hooks", "add Husky + lint-staged"
	`migrate-to-shoehorn`	"replace `as` with shoehorn in tests"
	`scaffold-exercises`	"scaffold an exercise structure"
personal	`edit-article`	"edit/revise this article"
	`obsidian-vault`	"find/create a note in Obsidian"
in-progress	`writing-fragments`	"ideate", "fragments", "raw material"
	`writing-shape`	"shape these notes into an article"
	`writing-beats`	"assemble this as a narrative"

Commands vs Agents vs Skills:

Commands (/foo) — you invoke explicitly. Full workflows.
Agents — Claude spawns them automatically inside commands. Specialized single tasks.
Skills — auto-fire from your phrasing. Trigger via description matching.

Multi-Tool Support (`tools/` registry)

Tool-agnostic — install.sh runs a generic loop over tools/*.sh, auto-detects whatever CLIs are installed, and creates the declared symlinks. AGENTS.md is the canonical agent context (openclaw pattern); each tool's expected memory filename is a symlink to it.

Shipped (verified):

File	Tool	Detection	Symlinks created
`tools/claude.sh`	Claude Code	`command -v claude`	`~/.claude/CLAUDE.md` → `AGENTS.md`, `commands`, `agents`, `skills`, `settings.json`
`tools/codex.sh`	Codex CLI	`command -v codex`	`~/.codex/AGENTS.md` → `AGENTS.md`, `skills` (same SKILL.md format)

Add any other tool — Gemini, Cursor agent, Aider, Continue, etc:

cp tools/_template.sh tools/<your-tool>.sh
$EDITOR tools/<your-tool>.sh    # fill in 4 vars: TOOL_NAME, TOOL_CMD, TOOL_DIR, TOOL_SYMLINKS
./install.sh                    # auto-detected from the next run on

View full README on GitHub

Similar Plugins

context7-plugin

55.5k·277·

Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.

3mo

[email protected]

upstash

llm-wiki

43·67·

Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.

v0.3.0

praneybehl

atlassian

794·48·

Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.

v1.0.0

atlassian

deep-wiki

2.3k·39·

AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.

2mo

v2.0.0

microsoft

claude-obsidian

7.7k·28·

Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).

v1.9.2

AgriciDaniel

golang-skills

119·28·

20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.

v1.8.0

cxuu

engineering-skills

Popularity

What's Inside

Confidence

README

agcoco

Architecture

Quick Start

What's Included

Commands (20개)

Agents (12개)

Skills (22개)

Multi-Tool Support (tools/ registry)

Similar Plugins

context7-plugin

llm-wiki

atlassian

deep-wiki

claude-obsidian

golang-skills

More by bradykim7

git-tools

planning

workflow

testing

claude-usage

agcoco

Architecture

Quick Start

What's Included

Commands (20개)

Agents (12개)

Skills (22개)

Multi-Tool Support (tools/ registry)

Popularity

Health & Quality

More by bradykim7

git-tools

planning

workflow

testing

claude-usage

Similar Plugins

context7-plugin

llm-wiki

atlassian

deep-wiki

claude-obsidian

golang-skills

Multi-Tool Support (`tools/` registry)

Multi-Tool Support (`tools/` registry)