skills
A collection of software-engineering skills for Claude Code — code review, spec-driven implementation, bug diagnosis, domain modeling, and more. Based on Matt Pocock's skills (https://github.com/mattpocock/skills).
By Michiel van der MeerLicense: MIT8 GitHub starsUpdated 6 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 29 skill or MCP entries
- Source updated
- Sep 17, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install skills for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install skills-3@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/michielvandermeer/skillsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .claude-plugin/plugin.json├── skills/cleanup-specs/SKILL.md├── skills/code-review/SKILL.md├── skills/codebase-audit/SKILL.md├── skills/codebase-design/SKILL.md├── skills/diagnosing-bugs/SKILL.md├── skills/document-changes/SKILL.md├── skills/domain-modeling/SKILL.md├── skills/grill-me/SKILL.md├── skills/grill-with-docs/SKILL.md├── skills/grilling/SKILL.md├── skills/handoff/SKILL.md├── skills/implement/SKILL.md├── skills/implement-oneshot/SKILL.md├── skills/implement-yolo/SKILL.md├── skills/improve-codebase-architecture/SKILL.md├── skills/improve-data-structures/SKILL.md├── skills/migrate-doc-layout/SKILL.md├── skills/plain-language/SKILL.md├── skills/prototype/SKILL.md├── skills/refine/SKILL.md├── skills/research/SKILL.md├── skills/resolving-merge-conflicts/SKILL.md├── skills/retro/SKILL.md├── skills/review-spec/SKILL.md├── skills/to-spec/SKILL.md├── skills/triage/SKILL.md├── skills/validate-spec/SKILL.md├── skills/wayfinder/SKILL.md└── skills/writing-for-agents/SKILL.md
Included Skills29
Removes all Spec, Plan, and Idea documents that have been implemented.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Audit the whole codebase for simpler data structures and organizing models. Read-only.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Write product-facing Changelog entries beside each CONTEXT.md. Use when /implement, /implement-oneshot, or /implement-yolo finishes before Spec delete, when backfilling Changelog history from git, or the user runs /document-changes with an optional context name and date window.
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
A relentless round-by-round interview to sharpen a plan or design.
A relentless round-by-round interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.
Grill the user relentlessly about a plan or design, round by round. Use when the user wants to stress-test a plan before building, or when another skill needs the round format.
Compact the current conversation into a handoff document for another agent to pick up.
Implement a spec by slicing it into steps and running ready steps in parallel sub-agents.
Implement a spec in one sub-agent session, skipping the Planner. Still reviews and improves data structures after.
Implement a spec in one sub-agent session on this checkout and this branch. No worktree, no new branch, no merge onto master.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then write the Ideas and Specs you pick.
Review recent spike/work for data structures or organizing models that would materially simplify the code.
Move documents that predate this project's canonical .agents/ layout into it.
Plain language in the sense of ISO 24495-1:2023 — the house standard for every sentence a person reads. Use when writing a document, report, review, or interview round a person will read, or when another skill needs the plainness bar.
Build a throwaway prototype to answer a design question, then turn the answer into a Spec. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Take an Idea or Jira ticket through grilling, an optional Prototype, and a Spec, then write a plain-language summary back.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Resolve an in-progress git merge or rebase conflict.
Look at a finished session, apply high-priority changes this repository owns, and summarise the rest.
Re-evaluate a Spec's Solution on this session's model and write the edits you approve.
Turn the current conversation into a spec and publish it to .agents/specs/ — no interview, just synthesis of what you've already discussed.
Sort incoming reports into Specs and parked Issues — one document per distinct problem.
Validate a plan, spec, or the current conversation against this repo's own template rules and the current codebase — fix stale references and contradictions in place, flag real decisions as open questions.
Plan a change too big for one agent session as a shared map of decision tickets under .agents/issues/, resolved one at a time until the way is clear and the Spec can be written.
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Plugin manifests1
{
"name": "skills",
"displayName": "mvdmio Skills",
"description": "A collection of software-engineering skills for Claude Code — code review, spec-driven implementation, bug diagnosis, domain modeling, and more. Based on Matt Pocock's skills (https://github.com/mattpocock/skills).",
"author": {
"name": "Michiel van der Meer",
"email": "[email protected]"
},
"homepage": "https://github.com/michielvandermeer/skills",
"repository": "https://github.com/michielvandermeer/skills",
"license": "MIT",
"keywords": [
"skills",
"code-review",
"implement",
"spec",
"workflow",
"software-engineering"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[skills on Agent Plugins Marketplace](https://pluginsmp.com/plugins/skills-3)