Plugin Claude Code
mihaiserban-skills. AI Skills I personally use for my day to day tasks.
2 21d ago A
tokens not measured
Instructions file CodexOpenCode
AGENTS.md instructions for mihaiserban/skills, covering agent instructions, buckets, manifest rules, invocation rules and structure rules.
2 21d ago A 755 tokens
Skill Claude CodeCodex
Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
2 21d ago A 30 tokens
Skill Claude CodeCodex
Fan out independent sub-jobs across fresh-context workers using file-based task specs and results. Use when a goal branches into many independent pieces.
2 21d ago A 35 tokens
design
05Skill Claude CodeCodex
Route every design request to the right sub-skill. Use when the user asks to design a website, landing page, dashboard, app shell, or UI. Pipeline: picker → apply → audit. For taste capture, use /design-taste-distiller.
2 21d ago A 0 tokens
Skill Claude CodeCodex
Apply a selected voltagent/awesome-design-md DESIGN.md aesthetic to an actual product UI, website, dashboard, app shell, or redesign. Use when the user names a style or brand from DESIGN.md, provides a DESIGN.md path, asks to build in the same style/aesthetic, or wants Codex to translate a reference design language…
2 21d ago A 79 tokens
Skill Claude CodeCodex
Audit an implemented UI against a DESIGN.md source aesthetic. Use when reviewing visual consistency, finding design drift, or producing concrete style fixes.
2 21d ago A 33 tokens
Skill Claude CodeCodex
Choose an appropriate source aesthetic from voltagent/awesome-design-md DESIGN.md profiles for a product, app, landing page, dashboard, or redesign brief. Use when the user wants design direction, asks what style to use, or gives a product brief without a clear visual system and needs a DESIGN.md profile selected…
2 21d ago A 70 tokens
Skill Claude CodeCodex
Distill visual taste from references, screenshots, prior designs, notes, DESIGN.md files, brand examples, workflow preferences, or user feedback into a compact TASTE.md for future design agents. Use when the user asks how to capture taste, create taste guidelines, make agents design with better judgment, define…
2 21d ago A 89 tokens
show-first
10Skill Claude CodeCodex
Plan a feature with a low-fidelity UI wireframe and a systems plan before writing any code.
2 21d ago A 23 tokens
Skill Claude CodeCodex
Decompose a document into atomic axioms, get user approval on each, then reassemble a fresh document from only the approved axioms. Use when rewriting, distilling, or restructuring an existing document and every claim must be intentional.
2 21d ago A 52 tokens
Skill Claude CodeCodex
Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.
2 21d ago A 32 tokens
Skill Claude CodeCodex
Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
2 21d ago A 27 tokens
Skill Claude CodeCodex
Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.
2 21d ago A 54 tokens
Skill Claude CodeCodex
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
2 21d ago A 0 tokens
Skill Claude CodeCodex
Test the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.
2 21d ago A 27 tokens
Skill Claude CodeCodex
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.
2 21d ago A 43 tokens
Skill Claude CodeCodex
Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.
2 21d ago A 22 tokens
Skill Claude CodeCodex
Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.
2 21d ago A 23 tokens
secret-scan
20Skill Claude CodeCodex
Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.
2 21d ago A 29 tokens
setup-skills
21Skill Claude CodeCodex
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
2 21d ago A 39 tokens
sql-review
22Skill Claude CodeCodex
Review SQL and ORM queries for correctness, safety, and performance before they ship.
2 21d ago A 19 tokens
Skill Claude CodeCodex
Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.
2 21d ago A 36 tokens
Skill Claude CodeCodex
Run runtime evals on a skill to measure whether it actually improves agent behavior. Use when the user asks to run evals, evaluate a skill's effectiveness, benchmark a skill, or measure skill impact. Also use to iterate on a skill after making changes — rerun evals to see if pass rates improved.
2 21d ago A 69 tokens