NiceEval

NiceEval/NiceEval

Skill Claude CodeCodex

Start NiceEval documentation development with the repository-owned Mint version and cache repair workflow.

NiceEval/NiceEval

Skill Claude CodeCodex

Check or regenerate NiceEval before-and-after integration example pages and their shared assets.

NiceEval/NiceEval

Skill Claude CodeCodex

Check or regenerate NiceEval public API reference regions from their source owners.

NiceEval/NiceEval

Skill Claude CodeCodex

Maintain NiceEval documentation banned wording and diagnose writing-rule failures. Use when listing, adding, removing, or checking entries in docs/writing-rules.json; use docs/concepts.md instead when establishing a preferred domain term.

NiceEval/NiceEval

Skill Claude CodeCodex

Prepare, check, and finalize disjoint NiceEval documentation work items for parallel Herdr agents.

NiceEval/NiceEval

Skill Claude CodeCodex

Build the current NiceEval candidate and install it into an authorized downstream project for dogfooding.

NiceEval/NiceEval

Skill Claude CodeCodex

Use when implementing, debugging, or reviewing NiceEval code whose correctness depends on Effect APIs or semantics, including typed failures, Schema, Scope, concurrency, services, layers, or Effect-backed tests. Do not use for domain questions that can be answered without Effect-specific reasoning.

NiceEval/NiceEval

Skill Claude CodeCodex

Use when migrating a codebase from Effect v3 to Effect v4, upgrading effect or any @effect/ package across the v3/v4 boundary.

NiceEval/NiceEval

Skill Claude CodeCodex

Check or apply NiceEval example tier synchronization and resolve declared conflicts.

NiceEval/NiceEval

Skill Claude CodeCodex

Inspect, design, trace, or revise NiceEval Feature and Use Case contracts. Use for adopted current product behavior; use Roadmap for finalized but unadopted directions and Design for competing plans.

NiceEval/NiceEval

Skill Claude CodeCodex

Audit, migrate, or maintain existing NiceEval Feedback records and their legacy relations. Do not use for new observations; use the Issue skill instead.

NiceEval/NiceEval

Skill Claude CodeCodex

A relentless interview to sharpen a plan or design.

NiceEval/NiceEval

Skill Claude CodeCodex

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

NiceEval/NiceEval

Skill Claude CodeCodex

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…

NiceEval/NiceEval

Skill Claude CodeCodex

Prepare, deduplicate, create, triage, update, close, or safely retry NiceEval GitHub Issues from public sanitized observations. Use for NiceEval Issue work; remote mutations require explicit authorization for the current action.

NiceEval/NiceEval

Skill Claude CodeCodex

Record, search, resolve, reopen, supersede, promote, or retire NiceEval development problems, decisions, and reusable insights.

NiceEval/NiceEval

Skill Claude CodeCodex

Create, update, or validate a NiceEval pull request body. Use when a task includes drafting, applying, checking, or creating a PR; do not invoke remote mutations without the user's authorization.

NiceEval/NiceEval

Skill Claude CodeCodex

Check or apply NiceEval repository setup such as Git hooks and local development prerequisites.

NiceEval/NiceEval

Skill Claude CodeCodex

Design, inspect, revise, or adopt NiceEval Roadmap directions. Use for finalized product targets that are not yet adopted as the current Feature contract; do not use for open alternatives or implementation status.

NiceEval/NiceEval

Skill Claude CodeCodex

Inspect, select, author, modify, or review NiceEval E2E and Unit test owners. Use when a change needs a test strategy, an existing test must be traced to its Feature or Use Case, or a bug requires public-entry E2E TDD.

NiceEval/NiceEval

Skill Claude CodeCodex

Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes…

NiceEval/NiceEval

Instructions file CodexOpenCode

Repository instructions for working on NiceEval, including discovery, bug fixes, tests, whole-repository rules, and downstream projects. An AGENTS.md file gives coding agents project-specific rules.

NiceEval/NiceEval

Instructions file

Claude Code instructions for NiceEval/NiceEval, a project described as: build eval for your agent in 10 mins.

NiceEval/NiceEval

Skill Claude CodeCodex

This project keeps a single shared convention documented here: every reviewer must be able to quote the project's magic word on request, to prove they actually read this file instead of guessing.