Skills For Real Engineers

skills.sh npm

Agent skills for doing real engineering with opencode - 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.

Quickstart

1. Install the skills globally from the fork repo (via skills.sh):

npx skills@latest add ecology9191/skills -g

The install menu is grouped by bucket (engineering, productivity, misc). Toggle a whole category or pick individual skills in one screen.

1. Or install from a git checkout or the published npm package:

npx --package @ecology91/skills ecology91-skills

This opens an interactive menu grouped by bucket (engineering, productivity, misc). Toggle a whole category or pick individual skills in one screen. Use --all to skip the menu, or --bucket / --skill for non-interactive partial installs.

From a git checkout this symlinks into ~/.agents/skills so edits in the repo are live. From the published package it copies files instead.

npx --package @ecology91/skills ecology91-skills --all
npx --package @ecology91/skills ecology91-skills --bucket engineering --skill tdd

1. Force a copy install from a checkout with --copy.

OpenCode auto-loads ~/.agents/skills alongside its own config tree, so one global install works across harnesses.

1. Quit and restart your agent so it reloads the skill list.
2. Run /setup-agent-skills in your coding agent. It will:

• Recommend Beads when the repo already uses or explicitly configures Beads; otherwise recommend local .scratch
• Offer GitHub, GitLab, or another hosted tracker only when you explicitly opt in
• Ask you what labels you apply to issues when you triage them (/triage uses labels)
• Ask you where you want to save any docs we create

3. Bam - you're ready to go.

This repo also includes opencode.json, so opencode loads the promoted skill buckets automatically when you open this repo directly.

Why These Skills Exist

I built these skills as a way to fix common failure modes I see with opencode, 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.

I felt the same tension with my agents. 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 a before-and-after example. 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, browser access, and automated tests.

For automated tests, a red-green loop is critical. The agent writes one failing behavior test, then adds only enough implementation to pass it before moving to the next slice. This gives the agent a consistent feedback signal and produces tests worth keeping.

I've built a /tdd skill you can slot into any project. It defines good seams, good tests, and the rules of the red-green loop.

For debugging, I've also built a /diagnose 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
• /zoom-out tells the agent to explain code in the context of the whole system

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

Summary

Software engineering fundamentals matter more than ever. These skills are my best effort at condensing these 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 I use daily for code work.

User-invoked

• ask-matt — Ask which skill or flow fits your situation. A router over the 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.
• implement — Implement work from a spec or set of issues, using TDD at pre-agreed seams and closing with code review.
• improve-codebase-architecture — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
• setup-agent-skills — Configure a local-first issue tracker, triage labels, and domain-doc layout; existing Beads wins, otherwise .scratch is the default.
• to-spec — Turn the current conversation into a spec and publish it to the configured issue tracker without re-interviewing the user.
• to-issues — Break a plan, spec, or conversation into context-sized tracer-bullet issues with explicit blocking edges.
• triage — Move issues and external PRs through a state machine of triage roles.
• wayfinder — Plan an effort too large for one session as a shared map of investigation issues, resolving them until the route is clear.
• zoom-out — Tell the agent to zoom out and give broader context or a higher-level perspective on an unfamiliar section of code.

Model-invoked

• code-review — Review a diff in parallel against repository standards and its originating spec, including a Fowler smell baseline.
• 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.
• diagnose — Disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test.
• 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.
• prototype — Build a throwaway prototype to answer a state, business-logic, or UI design question.
• research — Investigate a question against primary sources in a background agent and capture a cited Markdown report.
• resolving-merge-conflicts — Resolve an in-progress git merge or rebase conflict.
• setup-coding-quality-checks — Set up strict local formatters, linters, typechecks, tests, scanners, and git hooks that make agent coding safer.
• tdd — Test-driven development at pre-agreed seams, one red-green vertical slice at a time.
• to-qa — Create a local QA To Do session from completed source work under an explicit issue, including older non-parent Beads issues.

Productivity

General workflow tools, not code-specific.

User-invoked

• grill-me — Get relentlessly interviewed about a plan or design until every branch of the decision tree is resolved.
• handoff — Compact the current conversation into a handoff document so another agent can continue the work.
• teach — Teach the user a new skill or concept over multiple sessions, using the current directory as a stateful teaching workspace.
• writing-great-skills — Reference for writing and editing skills well: the vocabulary and principles that make a skill predictable.

Model-invoked

• caveman — Ultra-compressed communication mode that cuts filler while keeping technical accuracy.
• grilling — Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved. The reusable loop behind grill-me and grill-with-docs.
• write-a-skill — Create new skills with proper structure, progressive disclosure, and bundled resources.

Misc

Tools I keep around but rarely use.

Model-invoked

• git-guardrails-opencode — Set up opencode permissions to block dangerous git commands (push, reset --hard, clean, etc.) before they execute.
• migrate-to-shoehorn — Migrate test files from as type assertions to @total-typescript/shoehorn.
• scaffold-exercises — Create exercise directory structures with sections, problems, solutions, and explainers.
• setup-pre-commit — Set up Husky pre-commit hooks with lint-staged, Prettier, type checking, and tests.