Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 44851–44880 of 53520 skills

plan-write-reviewVumb-VibeCoder/haiku-delegateProduces long outputs by having the main model plan and classify, cheap subagents (Haiku) draft routine sections in parallel, the main model write the hard core itself, then skim and cross-check the routine drafts before merging and publishing. Use when the user asks for a long report, article, documentation, or multi-section write-up that splits into independent parts, or says to save tokens. Skip for short outputs.Stars: 1Updated Claude CodeCodexUnverifiedInstall
skim-then-verifyVumb-VibeCoder/haiku-delegateReads and evaluates long documents by having a cheap subagent (Haiku) read everything, then having the main model verify only the decisive figures and claims. Use when the user asks to review, assess, fact-check, or summarize a long report, research paper, multi-page file, or large attachment, or says to save tokens or not read it all. Skip for documents under about 8,000 words unless the user says not to read it yourself.Stars: 1Updated Claude CodeCodexUnverifiedInstall
crucibleismailrhassan1991-maker/crucible-CRUCIBLE is an 8-agent code production pipeline built on Loop Engineering principles. It takes any coding task through Architect → Coder → Reviewer → Tester → Optimizer → Security Auditor → Documenter → Deployer before delivering production-ready, tested, optimized, secured, documented, and shippable code. A Loop Sentinel governs all feedback cycles with stagnation detection, progress thresholds, and a global step budget — the pipeline always converges or halts with a clear reason. Use CRUCIBLE for any task where quality, correctness, and production-readiness matter. Trigger whenever the user says: "build", "write", "code", "implement", "create a function / class / module / app / script / API / service", "refactor this", "I need code that does X", or invokes /crucible. Always prefer CRUCIBLE over a single-pass response when the task is non-trivial — more than ~30 lines, any business logic, any external integration. Also trigger on: "do this properly", "production-ready", "I want this reviewed", "build this right", or "make this shippable".Stars: 1Updated Claude CodeCodexUnverifiedInstall
multi-agent-system-architect-v2ingcontartese-netizen/multi-agent-system-architect-v2Design, audit, build, verify, or port governed agentic systems for one host or optional teams. Triage no-system, workflow, agents; govern authority, state, tools, security, evals. Not for one-offs.Stars: 1Updated Claude CodeCodexUnverifiedInstall
python-health-auditlaurentvv/python-health-auditRuns a **read-only** static audit of a **Python** project (dead code via Ruff/Vulture, cyclomatic complexity hotspots via Radon, duplication via Pylint) using uvx, and writes a single Markdown health report with a machine-readable YAML header, an A-F grade and a 3-item action plan. Use this skill whenever the user asks to audit Python code, find technical debt, hunt dead code or unused imports, measure cyclomatic complexity, detect copy-pasted code blocks, or get a due-diligence / pre-refactor health check on a Python codebase. An opt-in extended pass also checks dependency vulnerabilities (pip-audit), docstring coverage, TODO/FIXME census and git churn. **Do NOT use for** security audits, performance profiling, test coverage, writing new code, dependency upgrades, CI setup, or non-Python languages (TypeScript, Go, etc.).Stars: 1Updated Claude CodeCodexUnverifiedInstall
second-opinionPGHQdev/second-opinionUse this skill to get an adversarial second opinion on a plan or brainstorm from a different AI model (Codex/GPT-5, Gemini, or another installed CLI) before committing to a risky implementation. Use whenever the user requests a "second opinion", "sanity check", or "another model's view"; whenever a PreToolUse hook blocks ExitPlanMode with a second-opinion-required message; whenever a plan touches migrations, auth, billing, infrastructure, production data, destructive operations, or >3 files; or whenever the user expresses genuine uncertainty about which approach to pick. This skill MUST be executed inside a general-purpose subagent — never run it directly from the main session, because the reviewer's output is large and would pollute the main context.Stars: 1Updated Claude CodeCodexUnverifiedInstall
mori-decision-hardeningrobertdevore/agent-moriUse Mori when an idea, plan, strategy, architecture, argument, presentation, roadmap, or decision needs Socratic clarification, adversarial red-teaming, or final hardening before commitment.Stars: 1Updated Claude CodeCodexUnverifiedInstall
testuiuxyanzyuyu/testuiuxMANDATORY: Execute during or immediately after creating, serving, or modifying ANY frontend UI, web page, HTML template, CSS styling, or responsive layout. Autonomous visual UI/UX defect detector and responsive layout verification engine. Captures multi-viewport screenshots (mobile 375x812, tablet 768x1024, desktop 1440x900) via Playwright, evaluates visual defects with Qwen2.5-VL (element collision, text overlap, truncation, horizontal overflow, broken assets, contrast issues), exports structured report.json, and triggers a compact triage model (qwen2.5:1.5b) to deliver a high-priority executive briefing directly to the primary coding AI.Stars: 1Updated Claude CodeCodexUnverifiedInstall
counterfactual-premortem-oracleEmincanozen/counterfactual-premortem-oracleZero-dot whitespace skill for pre-execution Counterfactual Pre-Mortem failure simulation, hidden assumption extraction, rollback symmetry verification, and Epistemic Drift Forensics. Use BEFORE executing mutating scripts, risky diffs, deployments, or complex multi-turn plans to simulate silent data corruption, race conditions, irreversible side effects, and hallucinated invariants.Stars: 1Updated Claude CodeCodexUnverifiedInstall
t1yOSt1yOS/t1y-skillsExpert knowledge for the t1yOS Serverless platform. Use this skill whenever the user mentions t1yOS, cloud functions, .jsc files, serverless development, or needs help with t1yOS platform features (cloud database, MCP tools, SDKs, crypto, JWT, file storage, scheduled tasks). Also use when the user asks about writing or debugging t1yOS cloud functions, integrating t1yOS SDKs, managing platform resources via MCP, or understanding t1yOS security mechanisms (HMAC-SHA256 signing, AES-256-GCM encryption). This skill provides the authoritative rules, API references, and best practices that even experienced developers need — the platform has specific conventions (.jsc extension, onRequest entry point, require-based modules) that differ from standard Node.js or other serverless platforms.Stars: 1Updated Claude CodeCodexUnverifiedInstall
skill-manager971184676/skill-manager管理所有已安装的 AI 技能(Skills),支持 Claude Code、OpenClaw、Codex、Trae、Hermes 等多种智能体。在编程/开发任务的计划阶段自动分析项目并推荐技能组合,推荐尽可能简洁且必须基于已有的技能。若现有技能无法满足需求,再推荐可下载的技能。询问用户是否按以上技能组合,想替换哪些技能?如果有的话可以说。在同一任务的后续步骤中,询问用户是保持原有技能组合还是推荐新的组合。安装新 Skill 时自动同步到 Excel 仓库。用户询问技能管理、计划推荐、技能调换时触发:列出、推荐、分类、调换。Manage all installed AI skills for Claude Code, OpenClaw, Codex, Trae, Hermes and other agents. Automatically analyzes projects and recommends skill combos during task planning. Recommendations must be concise and based on already installed skills first. Only recommend downloadable skills when existing skills cannot meet needs. Ask user whether to use this combo and which skills to replace if any. In follow-up steps of the same task, asks user whether to keep existing combo or recommend new one. Auto-syncs to Excel database when new skills are installed.Stars: 1Updated Claude CodeCodexUnverifiedInstall
apex-code-architectEmincanozen/apex-code-architectDeterministic multi-file code engineering, AST blast-radius mapping, and automated verification workflow covering the most saturated domain in the AI skills ecosystem (Frontend/Backend coding, testing, and Git quality). Use when architecting new modules, refactoring multi-file repositories, auditing cyclomatic complexity, or enforcing pre-commit code quality gates.Stars: 1Updated Claude CodeCodexUnverifiedInstall
ai-detectorValentinNikolaev/agent-skillsAssess AI-like prose (ai-detector, is-AI), including targeted phrase and structure audits, with improvement advice. A direct human request also runs ChatGPT's detector; calls from other workflows stay local. Not proof of authorship.Stars: 1Updated Claude CodeCodexUnverifiedInstall
api-and-interface-designValentinNikolaev/agent-skillsDesign API or module contracts before implementation; not diff review or system-wide architecture review.Stars: 1Updated Claude CodeCodexUnverifiedInstall
audit-docsValentinNikolaev/agent-skillsAudit repository docs read-only for broken links and paths, stale indexes or ADR pointers, duplicate canonical facts, migration gaps, and language or script violations defined by repository policy. Not memory stores, code review, or fixes.Stars: 1Updated Claude CodeCodexUnverifiedInstall
audit-memoryValentinNikolaev/agent-skillsAudit an agent memory store read-only for schema or index drift, broken relationships, review-due content or sources, duplicate or conflicting facts, and capacity. Not editing memory or auditing ordinary docs.Stars: 1Updated Claude CodeCodexUnverifiedInstall
business-viability-assessmentValentinNikolaev/agent-skillsAssess whether a software product, startup idea, MVP, repository, or PRD is commercially worth building, covering demand, competitors, costs, unit economics, risks, and a GO, VALIDATE_FIRST, PIVOT, or NO_GO verdict. Advisory in chat unless files are requested.Stars: 1Updated Claude CodeCodexUnverifiedInstall
claude-apiValentinNikolaev/agent-skillsBuild Claude API clients; not Agent SDK, other providers, or read-only review.Stars: 1Updated Claude CodeCodexUnverifiedInstall
clean-code-commentsValentinNikolaev/agent-skillsRemove or shorten redundant source-code comments without changing behavior. Use for explicit comment cleanup or dry audits of user-specified files and directories; do not use for general refactoring, documentation generation, or generated-output cleanup.Stars: 1Updated Claude CodeCodexUnverifiedInstall
code-reviewValentinNikolaev/agent-skillsReview local or PR diffs for defects, including UI/UX and accessibility failures, and test gaps without edits. Route standalone plans, specs, and feedback elsewhere.Stars: 1Updated Claude CodeCodexUnverifiedInstall
code-simplificationValentinNikolaev/agent-skillsSimplify existing code while preserving its behavior and contracts. Use for requested refactoring; not read-only review or comment-only cleanup.Stars: 1Updated Claude CodeCodexUnverifiedInstall
console-ux-designValentinNikolaev/agent-skillsDesign or improve command-line and console commands (structure, signatures, help, prompts, progress, errors, output, machine formats, automation), including Artisan and Symfony Console. Not GUIs, terminal themes, full-screen TUIs, shell scripting without UX changes, or report-only audits.Stars: 1Updated Claude CodeCodexUnverifiedInstall
councilValentinNikolaev/agent-skillsRun independent advisor passes and anonymized peer review for a consequential choice. Use when the user requests a council, debate, or stress test; prefer specialist reviews otherwise.Stars: 1Updated Claude CodeCodexUnverifiedInstall
create-memoryValentinNikolaev/agent-skillsBootstrap the first project-memory baseline from the current repository when no usable memory index exists. Not external imports, routine updates, audits, or replacing a healthy baseline.Stars: 1Updated Claude CodeCodexUnverifiedInstall
debugging-and-error-recoveryValentinNikolaev/agent-skillsDiagnose a failing test, build, runtime path, or incident and verify the fix. Use for an observed failure; not a speculative diff review.Stars: 1Updated Claude CodeCodexUnverifiedInstall
deprecation-and-migrationValentinNikolaev/agent-skillsPlan or implement a safe API, feature, data, or schema migration. Use when retiring a live contract; not for ordinary code cleanup.Stars: 1Updated Claude CodeCodexUnverifiedInstall
discussion-replyValentinNikolaev/agent-skillsPrepare grounded replies to social-media or forum discussions, from source context through exact-copy review. Not private correspondence, code-hosting replies, original posts, or wording-only edits.Stars: 1Updated Claude CodeCodexUnverifiedInstall
editorial-writingValentinNikolaev/agent-skillsDevelop standalone posts or articles from an idea or source through evidence, structure, drafting, and bounded review. Not discussion replies, private correspondence, profile copy, or wording-only edits.Stars: 1Updated Claude CodeCodexUnverifiedInstall
fastapi-developmentValentinNikolaev/agent-skillsImplement FastAPI APIs and streaming; not diff review or generic Python.Stars: 1Updated Claude CodeCodexUnverifiedInstall
fix-prValentinNikolaev/agent-skillsTriage existing GitHub PR comments and apply valid minimal fixes; not for a fresh code review.Stars: 1Updated Claude CodeCodexUnverifiedInstall