Language

General / language-agnostic

AI instructions for General / language-agnostic projects — coding rules, agent setup files, and prompts, organized by proficiency.

121 published items · Filter in browse

Skill✓ sealedCC0-1.0

Prompt Engineering

Write effective prompts and system prompts for current LLMs, including reasoning models, tool use, structured output, and prompt caching. Use when the user asks to improve a prompt, design a system...

Skill✓ sealedCC0-1.0

PR title and body from branch diff

Generates a PR title and body with purpose-grouped changes, evidence-based testing notes, and a risks section from the branch diff.

Skill✓ sealedCC0-1.0

Parallel Exploring

Explore a large codebase in parallel by launching several read-only subagents that each investigate a different area at once. Use when onboarding onto a new project, understanding architecture, or ...

Skill✓ sealedCC0-1.0

Blameless incident postmortem

Blameless postmortem template with timeline anchors, TTD/TTM metrics, why-chains, owned action items, and a responder interview guide.

Skill✓ sealedCC0-1.0

Dark Mode Testing

Toggle between light and dark mode in the harness's browser tool, screenshot both states, and flag missing token mappings or contrast issues. Use after theme or styling changes, or when the user as...

Skill✓ sealedCC0-1.0

Conventional Commits from a diff

Writes a Conventional Commits message from the staged diff, matching the repo's existing type and scope style.

Skill✓ sealedCC0-1.0

Codebase onboarding map

Time-boxed procedure to map an unfamiliar repo (entry points, layers, entities, commands, hotspots) and persist it to a notes file.

Skill✓ sealedCC0-1.0

API design review with scoring rubric

REST and GraphQL contract review checklist (naming, errors, pagination, versioning, auth) with an 8-dimension, 40-point rubric in references/.

Rule✓ sealedCC0-1.0

Definition of done: verify before reporting

Always-on rule: run tests, typecheck, lint, and build before reporting completion, and report exactly what ran.

Rule✓ sealedCC0-1.0

Cursor Rule: Testing Conventions

Auto-attached .cursor/rules/testing.mdc that loads when test files are in context and fixes naming, structure, mocking, and flakiness rules.

Rule✓ sealedCC0-1.0

Always-on agent guardrails

Always-on rule: scope discipline, git and dependency approval, planning format, and when to ask before acting.

Rule✓ sealedCC0-1.0

ConnectionGuide.txt format rule

Auto-attached rule that keeps a per-repo ConnectionGuide.txt of ports, routes, connections, and integration env vars current.

Rule✓ sealedCC0-1.0

Cursor Rule: Commit and PR Hygiene

Always-applied .cursor/rules/git-hygiene.mdc covering commit scope, message format, branch names, PR descriptions, and what never to run.

Rule✓ sealedCC0-1.0

Cursor Rule: API Security

Agent-requested .cursor/rules/api-security.mdc the agent pulls in when work touches auth, sessions, route handlers, or anything that reads untrusted input.

Rule✓ sealedCC0-1.0

Clean Code Cursor rule

Language-agnostic .mdc rule covering naming, constants, comments, single responsibility, DRY, encapsulation, refactoring and testing hygiene.

Agent instructions✓ sealedCC0-1.0

Solidity Foundry CLAUDE.md

CLAUDE.md for a Foundry project: forge fmt/build/test gates, fuzz and invariant test conventions, a security checklist, and a hard no-deploy rule.

Agent instructions✓ sealedCC0-1.0

Minimal CLAUDE.md

A 30-line universal CLAUDE.md skeleton: summary, commands table, definition of done, conventions, do-not-touch list, and when to ask.

Agent instructions✓ sealedCC0-1.0

Legacy Codebase CLAUDE.md

CLAUDE.md for an old or brownfield codebase: strangler-fig rules, no rewrites, characterization tests before changes, and a discoveries log.

Agent instructions✓ sealedCC0-1.0

Minimal AGENTS.md

A universal AGENTS.md skeleton read natively by Codex, Cursor, Copilot, Gemini CLI, Claude Code, and 20+ other agents.

Agent instructions✓ sealedCC0-1.0

AGENTS.md with Nested Packages

Root AGENTS.md for a monorepo plus a per-package AGENTS.md template, with a precedence note that matches how agents resolve nested files.

Agent instructions✓ sealedCC0-1.0

AGENTS.md template with commands table and definition of done

Fill-in-the-blanks AGENTS.md: purpose, stack, commands table, definition of done, gotchas, and a pointer to shared rules and skills.

Agent instructions✓ sealedCC0-1.0

AGENTS.md for Open Source Maintainers

AGENTS.md for a public OSS repo: issue linking, changelog entries, test requirements, CLA/DCO sign-off, and PR template compliance.

Skillintermediate✓ sealedMIT

Changelog writing skill

Agent Skill that drafts user-facing changelog entries from merged PR titles.

Promptintermediate✓ sealedMIT

Structured code review prompt

Reusable prompt that turns a model into a rigorous code reviewer with a fixed output format.

General / language-agnostic — Language directory · Waxmark