coding-assistant agents

yujiosaka/knowhub

Instructions file GitHub Copilot

Instructions for yujiosaka/knowhub, covering instructions, tools, screenshot verification, take a screenshot and verify with llm.

yujiosaka/knowhub

Instructions file

Instructions for yujiosaka/knowhub, covering claude code configuration, commit message format, required format rules, commit types and scope guidelines.

ngocquang/source-of-truth

Plugin Claude Code

A self-maintaining Spec-Driven Development (SDD) catalog skill that keeps a docs/ folder as the project's source of truth — read before touching code, sync after a feature ships.

ngocquang/source-of-truth

Instructions file Gemini CLI

Instructions for ngocquang/source-of-truth, a project described as: Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI stops rebuilding, deleting, and breaking things it never knew were there. Works with Claude, Codex, Cursor…

ngocquang/source-of-truth

Skill Claude CodeCodex

Use when a project keeps (or should keep) a docs/ spec catalog and the task touches it: before writing, modifying, or deleting production code (refactors and bug fixes included) or checking whether a capability already exists; after a feature ships or the user signals completion; when the user wants to change the…

junkyard22/Orca

Instructions file

Claude Code instructions for junkyard22/Orca, covering orca agent instructions, contract check, miranda architecture lock and where miranda is wired today.

neuron-core/maestro

Skill Claude CodeCodex

Create custom tools and toolkits for Neuron AI agents. Use this skill whenever the user mentions tools, functions, capabilities, agent actions, building tools, extending agent functionality, or wants to add custom capabilities to Neuron agents. Also trigger for tasks involving tool properties, tool execution…

neuron-core/maestro

Skill Claude CodeCodex

Build custom Neuron AI workflows with nodes, events, middleware, and human-in-the-loop patterns. Use this skill whenever the user mentions workflows, orchestration, event-driven systems, custom agents, complex multi-step processes, human-in-the-loop patterns, or wants to build a custom agentic system from scratch.…

neuron-core/maestro

Skill Claude CodeCodex

Help developers create and implement extensions for the Maestro CLI application. Use this skill whenever the user mentions creating a Maestro extension, adding custom tools or commands, building UI components for Maestro, registering memory files or event handlers, packaging a Composer package with Maestro extensions…

fanqingxuan/awesome-skills

Skill Claude CodeCodex

Eino LLM/AI application development framework assistant (Golang). Use when the user needs to: (1) Build AI agents, (2) Create LLM applications, (3) Implement tool calling, (4) Build multi-agent systems, (5) Create workflows with Graph/Compose, (6) Implement streaming, (7) Human-in-the-loop patterns, or any other Eino…

fanqingxuan/awesome-skills

Skill Claude CodeCodex

GORM (Go ORM) development assistant. Use when the user needs to: (1) Create GORM models, (2) Define database schemas, (3) Perform CRUD operations, (4) Handle associations and relationships, (5) Write complex queries, (6) Implement migrations, (7) Use hooks and callbacks, (8) Query data, (9) Insert data, (10) Update…

fanqingxuan/awesome-skills

Skill Claude CodeCodex

Laravel 12 framework development assistant. Use when the user needs to: (1) Create Laravel controllers, (2) Create Laravel models, (3) Create Laravel commands, (4) Create middleware, (5) Create facades, (6) Implement services, (7) Configure routes, (8) Use dependency injection, (9) Handle validation, (10) Work with…

hatch3r/hatch3r

Plugin Claude Code

Tool-agnostic agentic coding setup: 30 agents, 55 skills, 74 rules, 33 commands, 7 hooks, MCP servers, and a CLI-tool surface generated for 3 AI coding tools from a single canonical source. Counts derived from governance/inventory.json.

hatch3r/hatch3r

Hook Claude Code

Runs when a session starts, executing session-start-registry.mjs. From hatch3r/hatch3r.

hatch3r/hatch3r

Hook Claude Code

Runs on the ConfigChange event for project_settings tool calls, running echo 'hatch3r: .claude/settings.json changed — review new al. From hatch3r/hatch3r.

hatch3r/hatch3r

Settings file Claude Code

Agent settings declaring 2 hook events (SessionStart, ConfigChange) and 7 allowed tools.

hatch3r/hatch3r

Skill Claude CodeCodex

Create a new agent, skill, rule, command, hook, adapter, or pipeline module — runs duplication block, dispatches parallel sub-agents (T2/T3), delegates body authoring to the matching author skill, runs full gates, stops before commit.

hatch3r/hatch3r

Skill Claude CodeCodex

Rename, split, merge, or restructure an existing canonical artifact with cross-reference scrubbing and an explicit rename-map deliverable.

hatch3r/hatch3r

Skill Claude CodeCodex

Prepare a hatch3r release — version bump, changelog completeness + sync, repo + website docs currency, quality gates, adapter output verification, and release-notes reconciliation with CI.

hatch3r/hatch3r

Instructions file

Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).

hatch3r/hatch3r

Agent

Focused implementation agent for a single issue. Receives issue context, delivers code changes and tests. Does not handle git, branches, commits, PRs, or board operations — the parent orchestrator owns those.

hatch3r/hatch3r

Agent

Expert code reviewer for the project. Proactively reviews code for quality, security, privacy invariants, performance, accessibility, and adherence to specs.

hatch3r/hatch3r

Agent

Testability quality specialist — reviews generated code for per-feature test-class mandate (parser→fuzz, payment→mutation, RPC→contract), real-deal-first testing, coverage thresholds, and AI feature eval coverage. Use when test plans or test code are authored or modified.

hatch3r/hatch3r

Command

Create epics and issues/work items from todo.md, reorganize the board with dependency analysis, readiness assessment, and implementation ordering. Supports GitHub, Azure DevOps, and GitLab.