symbolpeek
49Skill Codex
Token-efficient code, JSON, and Markdown navigation; use before whole-file reads.
not rated 20 1mo ago A 19 tokens
original MIT
tanso
50Skill Claude CodeCodex
Use Tanso, an AI Search CLI for exploring Chinese internet signals. Use when the user asks to search Chinese web sources, Zhihu, Zhihu hotlists, Bocha, Volcengine Ark, Chinese internet topics, source-backed briefs, contradiction checks, counterintuitive topic discovery, popular answers, live provider testing, or…
not rated 19 2mo ago A 74 tokens
original MIT
mduongvandinh/ai-best-practices-skills
Skill Claude CodeCodex
Audit toàn diện Node.js project (Express/NestJS/Fastify + TypeScript). Phát hiện violations bằng regex patterns, chấm điểm theo domain có trọng số. Tất cả nội dung báo cáo bằng tiếng Việt.
not rated 18 6mo ago A 0 tokens
succubus
52Skill Claude CodeCodex
Coordinate with other AI agents working on this same project. Use at the start of every session, and before editing any file, to adopt your identity, read the shared plan and task board, and lease the files you are about to change so two agents never edit the same file at once.
not rated 17 1mo ago A 62 tokens
copy · 100% MIT
Skill Claude CodeCodex
Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…
not rated 17 17d ago A SkillSpector: pass 73 tokens
original MIT
kb-create
54Skill Claude CodeCodex
Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts.
not rated 17
+1 today A SkillSpector: warn 24 tokens
original Apache-2.0
Skill Claude CodeCodex
Load this skill when you want persistent agent memory across coding sessions. Mnemovela stores decisions, facts, workspace state, project constraints, errors, and task narratives as typed, searchable, branch-aware records. The agent retrieves them at session start instead of re-discovering everything from file reads.
not rated 15 15d ago B 0 tokens
code-review
56Skill Claude CodeCodex
Systematic code review checklist.
not rated 15 6d ago A 5 tokens
original Apache-2.0
Skill Claude CodeCodex
Reusable agent skill for migrating command-line interfaces from any programming language to Go.
not rated 11 2mo ago A 21 tokens
original MIT
pkup-enchant
58Skill Claude CodeCodex
Enrich an existing PKUP report directory — group commits into tasks, filter out non-creative groups, and write Polish descriptions. Use when the user has already generated a PKUP report and wants to clean it up or add "Zaprojektowałem..." descriptions.
not rated 11 26d ago A 59 tokens
original MIT
samurai
59Skill Claude CodeCodex
Samurai scoped testing framework for Go (github.com/zerosixty/samurai). MUST use when writing, modifying, reviewing, or debugging Go tests that import samurai, or reference samurai.Run, samurai.RunWith, samurai.Scope, samurai.TestScope, samurai.W, or samurai.BaseContext.
not rated 11 3mo ago A 69 tokens
original MIT
pachca-bots
60Skill Claude Code
A local MCP server for creating diagrams with the GenAI DrawIO Creator package. MCP is a way for an agent to call an external tool or service.
not rated 10 10d ago A SkillSpector: warn 192 tokens
original MIT
Skill Claude Code
Use when the user asks for a recap, status readout, or check-in across Ideate ideas (a logical work item; "session" is one facet of an idea, not the unit). Scope is the local Ideate workspace exposed by the ideate MCP. Use work-idea instead when the user wants to focus on or switch into a single idea.
not rated 9 today A 75 tokens
original MIT
Skill Claude CodeCodex
Use when designing or reviewing the tools an LLM agent will call — choosing tool boundaries, argument and result shapes, retrieval/search/get decompositions, MCP or goa-ai toolset surfaces — or when an agent misuses existing tools (wrong tool picked, IDs carried between calls, wrong dates computed, confident answers…
not rated 8 today A 71 tokens
original MIT
Skill Claude CodeCodex
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
not rated 7 4mo ago A 45 tokens
original MIT
Dankosik/go-service-template-rest
Skill Claude CodeCodex
Go version idioms. Use when the module's Go version can change a language or standard-library choice in the planned diff, or modernization is requested.
not rated 7
+1
changed yesterday A 34 tokens
original MIT
gh-pr-review
65Skill Claude CodeCodex
Review GitHub pull requests for correctness, design quality, test coverage, security, performance, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
not rated 6 yesterday A 58 tokens
original MIT
Skill Claude CodeCodex
Generate Go CLIs from OpenAPI 3.x specs with climate, inspect generated CLIs, and emit Markdown skill prompts so those CLIs can be attached to agent workflows.
not rated 6 1mo ago A 39 tokens
original Apache-2.0
siyuan-cli
67Skill Claude CodeCodex needs its repo
A command-line tool for managing SiYuan notebooks, documents, blocks, tags, searches, imports, exports, resources, and synchronization. SiYuan is a note-taking application, and the tool requires a running, authenticated SiYuan instance.
not rated 6
+1 4mo ago A 73 tokens
original MIT
gospec
68Skill Claude CodeCodex
A Chinese-language guide for building and maintaining Go backend services. It covers how to organize code, design APIs, store data, test changes, deploy services, and handle operations.
not rated 6 4mo ago A 155 tokens
original MIT
Skill Claude CodeCodex
Discover and assemble a task-specific prompt from the embedded PromptKit catalog through the PromptKitty CLI. Use when the user wants to select a PromptKit template, compose a prompt for an engineering task, run an interactive PromptKit intake, write a requirements or design artifact, investigate a bug, review code…
not rated 5 1mo ago A 78 tokens
original MIT
using-rnix
70Skill Claude Code
Drive Rnix — the Agent OS — from the command line: spawn AI agents as OS-style processes, orchestrate multi-agent workflows, decompose high-level intents into sub-task DAGs, and inspect, trace, suspend or resume agent processes. Use this whenever you need to run the rnix CLI, launch or manage agents, compose several…
not rated 5 1mo ago A 162 tokens
original MIT
Skill Claude CodeCodex
One iteration of an unattended development loop. Use when invoked by name.
not rated 5 8d ago A 19 tokens
original MIT
herd
72Skill Claude CodeCodex
Operate the Herdforge self-forging software factory with Kaneo, Herdr, isolated worktrees, verification, review, and cleanup.
not rated 5 today A 30 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: