个人作者

Karim Ben Boubaker

AI Engineer

机构 · Offenburg University of Applied Sciences所在地 · Germany访问官网 ↗更新于 2026-11-10

Skills
31
仓库
1
职业覆盖
0
场景覆盖
0
Stars
★ 1

Karim Ben Boubaker 的 Skills 31

Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-walkthrough

Guide you through running a demo yourself that shows a fix or a new feature working: a few numbered steps in the chat, each a command to copy or a click to make, with what you should see.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-spec

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-questionnaire

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-pr

Writes a PR or MR from a fixed template: the tickets it closes, a summary sketch, before and after evidence that proves each acceptance criterion (screenshots for visible changes), and merge danger (one-way or two-way door, blast radius). Use when opening, writing or updating a pull request or merge request.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-issue

Files and moves issues on the repo's tracker (GitLab, GitHub or local files): one kind (bug, feature, chore) and one stage each, a title, the kind's template, and what each later stage needs. Use when filing, relabelling, moving or closing an issue, when work should be recorded instead of done now, or to split big work into child tickets.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

write-for-agents

How to write documents an agent reads: context pointers, information hierarchy, completion criteria, leading words and pruning, plus skill frontmatter and invocation mechanics. Use when creating or editing a skill, AGENTS.md, CLAUDE.md, or any doc an agent reaches through a pointer.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

wait-what

Stop. That last message did not land: re-pitch it.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

tdd

Test-driven development in vertical slices: one failing test through a public interface, the minimum code to pass, repeat, with FIRST tests (fast, isolated, repeatable, self-validating, timely). Use when building features or fixing bugs test-first (red-green-refactor), writing or reviewing any test, or when tests are slow or flaky. For pacing multi-step work, use principle-take-small-verified-steps.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

set-up-repo

Configure a repo for the engineering skills: issue tracker, labels and templates, checks and test policy, domain docs, and the run recipe and its sandbox. Run once before first use, or again to reorganise.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

run-retro

Conduct a retrospective on a coding session.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

review-code

Reviews the changes since a fixed point (commit, branch, tag, merge-base) in three parallel sub-agents: Standards (coding standards and principle checks), Spec (what the issue asked for) and Demo (a fresh agent runs the app against the acceptance criteria and captures evidence). Use when reviewing a branch, a PR or work in progress, or asked to 'review since X'.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

research

Investigates a question against primary sources (official docs, source code, specs, first-party APIs) in a background agent and saves the cited 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.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

remove-comments

Deletes the comments in a diff with a fresh subagent, keeping only license headers, outside constraints and public API docstrings, then fixes the code each deleted comment was propping up. Use before review, when implement or implement-spec finish their build, or when review-code flags comments.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

prototype

Builds throwaway code that answers one design question: a single-file HTML walkthrough for a logic or state model, or switchable UI variations on one route. Use when the user wants to sanity-check whether a state model or logic holds up, explore what a UI should look like, or settle a design fork by running something instead of debating it.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

principle-take-small-verified-steps

Advances work in small steps, each proven on the real artifact with the narrowest check that can go red; runs the full suite once, on the way into the default branch; backs every number with a measurement. Use when planning or executing multi-step work, choosing which tests to run, optimising or benchmarking, and before declaring any task done.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

principle-let-models-judge

Splits LLM work from code: the model judges fuzzy input, code checks the answer's structure; prompts teach the class, never the case; a wrong model answer is fixed with prompt, more reasoning or another model, not like a code bug; evals run rarely. Use for any AI engineering work: code that calls an LLM, prompts, agents, tools, model choice, evals.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

principle-keep-it-simple

KISS, YAGNI and obvious code: decides whether a feature, option, flag, layer, dependency or abstraction should exist, presents the minimal version first, keeps what stays readable, and lands each change as if the design had planned for it. Use when proposing, designing, scoping, writing, changing or reviewing code, plans or specs.

★ 1
Med-Karim-Ben-Boubaker
Med-Karim-Ben-Boubaker/karim-skills

principle-fix-root-causes

Fixes wrong behaviour where it first went wrong (data model, schema, algorithm, prompt) instead of patching the symptom, lets failures surface as errors, and fixes the whole class, never one instance. Use when fixing a bug, failing test, error or wrong model answer, before adding a guard, fallback, default, retry or special case.

★ 1