Inconvenient Skills

Agent skills for doing real engineering — not vibe coding.

Developing real applications is hard. Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control and make bugs in the process hard to resolve.

These skills are designed to be small, easy to adapt, and composable. They work with any model. They're based on decades of engineering experience. Hack around with them. Make them your own. Enjoy.

Installation (30-second setup)

Two installation modes, two philosophies. Managed plugins for Claude Code and OMP install the whole set as a read-only bundle that updates when releases ship — you subscribe rather than fork. skills.sh copies editable skill files into your project, so you can hack on them and make them your own. Pick one mode — installing both leaves you with every skill twice.

1. Get the skills

Claude Code

claude plugins install inconvenient-skills

Or, from inside a session:

/plugin install inconvenient-skills

It's in Claude Code's official marketplace, so there's nothing to add first, and updates arrive automatically.

OMP

omp plugin marketplace add the-inconvenience-store/skills
omp plugin install inconvenient-skills@inconvenient

The first command adds this repository's OMP marketplace; the second installs the plugin at user scope. Run /reload-plugins in an active OMP session, or restart OMP.

Codex, and other agents

npx skills@latest add the-inconvenience-store/skills

Pick the skills you want, and which coding agents to install them on. Select setup-inconvenient-skills, guardrails, and verification together: the setup skill calls the other two.

The repo also ships native Codex plugin metadata in .codex-plugin/plugin.json, an OMP marketplace, and a portable plugin.json. Every plugin format loads the same promoted skills directly from skills/.

For tinkerers

Use the same installer, on any agent — including Claude Code:

npx skills@latest add the-inconvenience-store/skills

It writes the skills into your repo as ordinary files you own and can edit. Nothing updates behind your back; pull the latest changes when you want them with npx skills update.

2. Run `/setup-inconvenient-skills`

In your agent, run it once per repo. It will:

Configure the issue tracker, applicable triage labels, and domain-doc layout
Invoke guardrails to propose, install, and prove the development quality baseline you approve
Invoke verification to create or maintain the real-surface driving instructions and prove one mapped feature

3. Bam - you're ready to go.

Why These Skills Exist

These skills address common failure modes in Claude Code, Codex, and other coding agents.

#1: The Agent Didn't Do What I Want

"No-one knows exactly what they want"

David Thomas & Andrew Hunt, The Pragmatic Programmer

The Problem. The most common failure mode in software development is misalignment. You think the dev knows what you want. Then you see what they've built - and you realize it didn't understand you at all.

This is just the same in the AI age. There is a communication gap between you and the agent. The fix for this is a grilling session - getting the agent to ask you detailed questions about what you're building.

The Fix is to use:

/grill-me - for non-code uses
/grill-with-docs - same as /grill-me, but adds more goodies (see below)

These are my most popular skills. They help you align with the agent before you get started, and think deeply about the change you're making. Use them every time you want to make a change.

#2: The Agent Is Way Too Verbose

With a ubiquitous language, conversations among developers and expressions of the code are all derived from the same domain model.

Eric Evans, Domain-Driven-Design

The Problem: At the start of a project, devs and the people they're building the software for (the domain experts) are usually speaking different languages.

Agents are usually dropped into a project and asked to figure out the jargon as they go. So they use 20 words where 1 will do.

The Fix for this is a shared language. It's a document that helps agents decode the jargon used in the project.

Example

Here's an example CONTEXT.md excerpt. Which one is easier to read?

BEFORE: "There's a problem when a lesson inside a section of a course is made 'real' (i.e. given a spot in the file system)"
AFTER: "There's a problem with the materialization cascade"

This concision pays off session after session.

This is built into /grill-with-docs. It's a grilling session, but that helps you build a shared language with the AI, and document hard-to-explain decisions in ADR's.

It's hard to explain how powerful this is. It might be the single coolest technique in this repo. Try it, and see.

Tip

A shared language has many other benefits than reducing verbosity:

Variables, functions and files are named consistently, using the shared language

As a result, the codebase is easier to navigate for the agent

The agent also spends fewer tokens on thinking, because it has access to a more concise language

#3: The Code Doesn't Work

"Always take small, deliberate steps. The rate of feedback is your speed limit. Never take on a task that’s too big."

David Thomas & Andrew Hunt, The Pragmatic Programmer

The Problem: Let's say that you and the agent are aligned on what to build. What happens when the agent still produces crap?

It's time to look at your feedback loops. Without feedback on how the code it produces actually runs, the agent will be flying blind.

The Fix: You need the usual tranche of feedback loops: static types, automated tests, and a repeatable way to drive the real application.

For automated tests, a red-green-refactor loop is critical. This is where the agent writes a failing test first, then fixes the test. This helps give the agent a consistent level of feedback that results in far better code.

The /tdd skill slots into any project. It encourages red-green-refactor and gives the agent plenty of guidance on what makes good and bad tests.

The /verification skill creates, runs, and maintains that real-surface route. Passing tests support the proof; they do not replace observing the behavior a user or consumer was promised.

For debugging, I've also built a /diagnosing-bugs skill that wraps best debugging practices into a simple loop.

#4: We Built A Ball Of Mud

"Invest in the design of the system every day."

Kent Beck, Extreme Programming Explained

"The best modules are deep. They allow a lot of functionality to be accessed through a simple interface."

John Ousterhout, A Philosophy Of Software Design

The Problem: Most apps built with agents are complex and hard to change. Because agents can radically speed up coding, they also accelerate software entropy. Codebases get more complex at an unprecedented rate.

The Fix for this is a radical new approach to AI-powered development: caring about the design of the code.

This is built in to every layer of these skills:

/to-spec quizzes you about which modules you're touching before creating a spec

And crucially, /improve-codebase-architecture helps you rescue a codebase that has become a ball of mud. Run it on your codebase once every few days.

Summary

Software engineering fundamentals matter more than ever. These skills condense those fundamentals into repeatable practices, to help you ship the best apps of your career. Enjoy.

Reference

These split on one axis — who can invoke them. User-invoked skills are reachable only when you type them (e.g. /grill-me); their job is to orchestrate. Model-invoked skills can be invoked by you or reached for automatically by the agent when the task fits; they hold the reusable discipline. A user-invoked skill may invoke model-invoked skills, but never another user-invoked one.

Engineering

Skills for daily code work.

User-invoked

ask-inconvenient — Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
grill-with-docs — Grilling session that also builds your project's domain model, sharpening terminology and updating CONTEXT.md and ADRs inline.
triage — Move issues through a state machine of triage roles.
improve-codebase-architecture — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
setup-inconvenient-skills — Configure the issue tracker, triage labels, and domain docs; establish approved development guardrails; then create and prove the repository's real-surface verification route. Run once per repo.
to-spec — Turn the current conversation into a spec and publish it to the issue tracker. No interview — just synthesizes what you've already discussed.
to-tickets — Break any plan, spec, or conversation into a set of tracer-bullet tickets, each declaring its blocking edges — written as text in a local file, or as native blocking links on a real tracker.
implement — Build work from a spec or tickets: select the relevant engineering principles, drive TDD at pre-agreed seams, run Standards and Spec review, address findings, then prove the final behavior through real-surface verification.
wayfinder — Plan a huge chunk of work, more than one agent session can hold, as a shared map of investigation tickets on the issue tracker — resolve them one at a time until the way to the destination is clear.

Model-invoked

guardrails — Inspect a project, then propose and verify its lint, format, test, reproducible setup, dependency upkeep, optional task runner, CI, hooks, and applicable React standards with the user in control.
prototype — Build a throwaway prototype to answer a design question — a shareable HTML demo for state/logic questions, or several radically different UI variations toggleable from one route.
diagnosing-bugs — Disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test.
research — Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file in the repo, run as a background agent.
tdd — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
domain-modeling — Actively build and sharpen a project's domain model — challenge terms against the glossary, stress-test with edge-case scenarios, and update CONTEXT.md and ADRs inline.
codebase-design — Shared discipline and vocabulary for designing deep modules: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface.
engineering-principles — Selective vocabulary for 21 recurring engineering decisions. Workflows proactively scan its trigger index and load only the matched leaves; user-named principles receive extra emphasis rather than enabling selection.
verification — Create, run, or maintain portable project instructions for proving behavior through the real UI, CLI, service, mobile app, or public library interface.
code-review — Two-axis review of the diff since a fixed point: Standards (does it follow the repo's coding standards, plus a Fowler smell baseline?) and Spec (does it faithfully implement the originating issue/spec?), run as parallel sub-agents so neither pollutes the other.
resolving-merge-conflicts — Work through an in-progress git merge or rebase conflict hunk by hunk, resolving by intent traced to each side's primary source, then finish the operation — never --abort.
wizard — Generate an interactive bash wizard for setup steps only a human can perform, such as credentials, dashboards, migrations, and cutovers.

Productivity

General workflow tools, not code-specific.