9,122 tagged cli, measured the same way as everything else here.
Browse within: agent 299bun 232LLM 213ai-coding 149agentic 146coding-agent 129ml 114gemini-cli-extension 96discovery-api 95tui 91agent-swarm 82mimo 80mimo-code 80bash 78
amirkiarafiei/subagent-cli-skills
Skill Claude Code
Delegates large multi-step work to OpenCode CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for deep architectural changes, complex code generation, and CI automation.…
Skill Codex
A session-goal tool that keeps a long-running task active across repeated work sessions. It can create, inspect, pause, resume, delay, or clear a goal.
Skill Codex
Package and publish one local agent Skill, or audit and release a Registry-driven public Skill portfolio, as polished installable GitHub packages. Use when the user gives a SKILL.md, Skill directory, or multi-Skill repository and asks to open-source, publish, release, share, validate, detect drift, synchronize…
wangjs-jacky/jacky-skills-learning
Skill Claude CodeCodex
A research tool for studying Claude Code Skills, which are add-ons that give Claude Code extra abilities or workflows.
Skill Claude CodeCodex
Teaches AI agents how to use the AgentSkills Registry CLI to search, pull, and push skill bundles.
Skill Claude CodeCodex
Describe when this skill should be used.
Skill Claude CodeCodex
Use Stet to measure whether an AI coding change is safe to ship. Trigger on model comparisons, AGENTS.md or CLAUDE.md effectiveness, shared instruction, policy, skill, harness, tool-policy, reasoning, or runtime rollouts, repo eval setup, dataset building, regression detection, benchmarking, promote/rollback…
Skill Claude CodeCodex
Reverse-engineer a website's internal APIs, encrypted endpoints, WebSocket streams, and obfuscated JavaScript. Activates when the target data isn't in the HTML, when the site uses encrypted CloudFront/CDN payloads, when real-time streaming data is needed, or when the scrape skill's Phase 0-1 finds API calls that are…
Skill Claude CodeCodex
You are a payment integration assistant. Help users operate the agenzo-token-cli CLI to manage developers, API keys, payment methods, and payment tokens.
Skill Claude Code
Fetch open GitHub issues, classify each as bug, feature, or chore, then DELEGATE to the correct extension: bugs → bug.fetch (saved under .specify/bugs/), chores → chore.fetch (saved under .specify/chores/), features → speckit.specify (saved under specs/). Never save bugs or chores as specs.
jamditis/prompt-engineering-journalists
Skill Claude CodeCodex
Enforces AP Style and newsroom conventions when writing or editing.
Skill Claude CodeCodex
Manage Zilliz Cloud vector databases via zilliz-cli. Use when the user wants to: (1) set up zilliz-cli (install, login, configure), (2) manage clusters (create, list, describe, suspend, resume, delete, modify), (3) manage collections, indexes, partitions, databases, or aliases, (4) perform vector operations (search…
Skill Claude CodeCodex
Extract UI designs from screenshots and iteratively refine implementations to match a reference image pixel-perfectly using comparison and fix suggestions.
Skill Codex
A command-line tool for static reverse engineering, which means examining compiled files without running them, including ELF, PE, Mach-O, object files, and identified shellcode.
Skill Claude CodeCodex
Persistent file-based notebook (.carnet/ / .md, auto-expiring after 30 days of disuse) for AI agents and humans. Use whenever saving, recalling, or organizing notes across sessions — IMPLICIT cues include the user recapping a tricky fix worth not redoing, asking 'what did we decide about X', handing off mid-task…
Skill Codex
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
Skill Claude CodeCodex needs its repo
Derive BDD scenarios and TDD test skeletons from approved SDD specifications. ATDD acceptance test tables are optional output for specialized needs. Use when: spec is approved, starting BDD/TDD implementation, generating test structures. Keywords: forward derivation, spec to test, BDD generation, TDD skeleton, test…
Skill Claude CodeCodex
Use the sidecarsync CLI to read, update, and synchronize Sidecar notes or state in repos with .sidecar configurations. Covers peer selection, standalone repos, per-file rules, and fork recovery.
Skill Claude CodeCodex
Adding auth guards, permission checks, role management, or session handling.
Skill Claude Code
Learn about hailux features, slash commands, keyboard shortcuts, @file/@folder mentions, and how to configure AGENTS.md, Skills, custom commands, MCP servers, and Subagents.
Skill Claude CodeCodex
NextDNS integration guides for third-party platforms and services. This skill should be used when integrating NextDNS with routers, home automation systems, network management platforms, or other third-party services. It also guides transport selection across DoH, DoT, DoQ, DoH3, IPv6, and legacy DNS. Triggers on…
Skill Claude CodeCodex
Analyze your OpenClaw API spend — total cost, cost last 7 days, top cost leaks by model and provider, and concrete steps to reduce your bill. Use when the user asks about their AI spending, costs, budget, or which models are costing the most.
Skill Codex
Dispatch independent coding tasks to Google Jules through the jules-dispatch CLI or MCP server, then monitor sessions and report PR URLs. Use when Codex or Claude Code needs to fan out implementation, testing, refactoring, review, migration, or documentation work into parallel Jules sessions; when a user asks to use…
Skill Claude Code
Draft a pull-request message (title + Markdown body) for the current branch into main. Use when the user asks for a "PR message", "PR description", "pull request message", or says "write a PR message" / "give me a PR message". Output is Markdown text only — does not call gh or open a PR.
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: