agentsclimarketplace

The catalog

608,666 rows, by stacks then stars

  • Alerting sla

    almasumdev/awesome-mobile-observability-agent-skills/.github/skills/alerts/alerting-sla Skill

    no license1★ repo

    Define SLIs, SLOs, error budgets, and rollout halts for mobile apps, with multi-window burn-rate alerts. Use when formalizing reliability targets or gating staged releases.

  • Codebase onboarding check

    Agent-Hellboy/codebase-onboarding-check Skill

    1★

    Onboard quickly by reading design docs, plans, READMEs, or the codebase to extract key concepts, surface gaps, and generate comprehension checks with answer keys. Includes an adaptive proficiency probe with learning resources and persistent session memory so the user can resume onboarding where they left off. Use when a user wants help understanding a project, validating their grasp of the architecture, or creating a readiness plan before contributing code.

  • Ifrs

    babu9893/ifrs-skill/ifrs Skill

    1★ repo

    Use when answering questions about IFRS standards, IAS standards, IASB, financial reporting, revenue recognition, lease accounting, impairment, financial instruments, expected credit loss, ECL, consolidation, business combinations, fair value measurement, first-time adoption, deferred tax, provisions, insurance contracts, journal entries, disclosure requirements, IFRS compliance checks, audit support, GAAP differences, goodwill, or transitioning from local GAAP to IFRS.

    The same file is in 1 other repository

  • Motrix cli

    nufegia/motrix-cli/skills/motrix-cli Skill

    1★ repo

    Control Motrix Next and legacy Motrix downloads through the motrix-cli command-line tool and their local aria2 JSON-RPC backend. Use when an agent needs to install motrix-cli, diagnose Motrix RPC connectivity, add download URLs, list or inspect tasks, pause/resume/remove tasks, wait for downloads to finish, or automate downloads with machine-readable JSON output on macOS.

  • Big five assessment

    aqws6361/big-five-personality-skill/skills/big-five-assessment Skill

    no license1★ repo

    A psychological engine for the Big Five (OCEAN) model. This skill provides a validated 50-item IPIP inventory to assess real users or generate high-fidelity synthetic personas. Supports interactive personality profiling for users, and simulating realistic behaviors for agents. Triggers on: personality assessment, OCEAN model, user persona generation, UX testing, character simulation, psychological profiling.

  • Askproof

    happiness9527/askproof-skill/askproof Skill

    1★ repo

    Use this skill when a non-engineer needs to ask AI agents for proof, check whether “done” is actually verified, rewrite vague feedback such as “still broken” into actionable prompts, request minimum evidence, prevent task drift, or create handoff memory.

    The same file is in 1 other repository

  • Skills doctor

    leacent/skills-doctor Skill

    1★

    Use only for doctor, skills doctor, skills check, audit skills, scan skill directories, diagnose existing local AI agent skills, or generate a local skills health report. Do not use for creating, installing, finding, recommending, or learning to write skills.

  • Code review

    coreline-ai/claude-devflow-plugin/skills/code-review Skill

    1★ repo

    Dual-mode review skill — review implementation plans before coding (plan mode) or review code changes after implementation (code mode) with architecture, risk, and test analysis

  • Commit message

    contextosai/skills/skills/commit-message Skill

    1★ repo

    Write a clear, conventional git commit message from staged changes. Use when the user asks to commit, write a commit message, or describe what changed.

  • Ansible kamal

    mauriciovieira/skills/skills/engineering/ansible-kamal Skill

    1★ repo

    Use when bootstrapping a Rails project that needs Ubuntu VPS provisioning (Ansible) and Kamal 2 deploy (kamal-proxy on 80/443) — scaffolds infra/ansible, infra/kamal, config/deploy*.yml, .kamal/secrets* templates from a hardened reference layout, asking IP, DNS, and whether the host runs both staging+production or only a single domain.

  • Popup

    richard-kim-79/popup-skills/popup Skill

    1★ repo

    Create instant shareable web pages on popup2026.com — no login, no PIN, 30-second setup. Use when the user wants to make a "팝업 페이지", "공유 링크", "랜딩 페이지", "이벤트 안내", "링크 모음", host a raw HTML file, or host a PDF. Tools are reached via the Remote MCP server at https://popup2026.com/api/mcp.

  • Knowledge base

    jakebrownscombe/science-lab-AI-framework/knowledge_base Skill

    1★ repo

    A customizable framework for using LLMs in scientific workflows.

  • Learn quiz

    ringoshiina/learn-quiz-skill/skills/learning/learn-quiz Skill

    1★ repo

    Use when the user wants to deeply understand source material already present in context, available in the workspace, or supplied or pointed to by the user, such as a session, implementation, bug, design decision, code change, PR, generated artifact, or prior handoff, through incremental teaching, source-grounded explanation, restatement, quizzes, misconception correction, and continuation handoff until mastery is demonstrated.

  • Vibe coding playbook

    ayi-ai/vibe-coding-playbook Skill

    1★

    A lightweight engineering workflow for turning an idea into a real, shippable product with an AI coding agent. Core = Karpathy's four coding disciplines (think before coding / simplicity first / surgical changes / goal-driven; battle-tested), plus an Explore→Plan→Build→Polish→Ship process, task tiers (skip the process for small changes, full process only for shipped products), and the "AI is an amplifier" mindset (good habits ×10, bad habits ×100; controlling complexity is still the human's job). For everyone: terse for engineers, explained for newcomers, no jargon dumps. Ships with a paste-in kickoff prompt, a drop-in .cursor/rules discipline file, and PRD/architecture/status doc templates. Use when building an app/product/website/tool from scratch with Cursor/Codex/Claude Code, when asked to set rules before coding, when worried about code rotting into a mess or the AI changing unrelated code on its own, when asked how to do "vibe coding", whether to write a PRD/architecture, how to start a new project, or when "amplifier / spaghetti code / minimal loop / surgical change / complexity / task tier" come up.

  • Arxiv monitor

    Moonweave-Research/groundcheck/arxiv-monitor Skill

    1★ repo

    Fetches new arXiv papers matching a research watchlist, scores relevance with LLM, and delivers a filtered daily digest. Invoke when the user wants to check new arXiv papers on a topic, set up a daily paper monitoring routine, asks 'what's new on arXiv about X?', or wants to scan recent preprints in their field. Also use as a Claude Code Routine template for scheduled daily briefings. Do NOT invoke for finding a specific known paper (use ref-verify) or for general web research.

  • Imagegen

    yzp100911/skillgate-agent/cclaw/data/codex-home/skills/.system/imagegen Skill

    1★ repo

    Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

    The same file is in 3 other repositories

  • Ts npm oxlint starter

    kongyo2/agent-primary-ts-starters/ts-npm-oxlint-starter Skill

    1★ repo

    Add Oxlint to a TypeScript npm project with agent-friendly defaults that focus error-level diagnostics on real bugs, silence stylistic noise, and emit output in oxlint's `agent` format for downstream LLM consumption. Use when bootstrapping a new TS project that needs linting, or when adding Oxlint to an existing TS npm project — even if the user doesn't explicitly say "oxlint" or "linter".

    The same file is in 1 other repository

  • Just product factor

    Just-Agent/just-product-factor Skill

    1★

    Route product, UI, frontend, app, Agent, RAG, MCP, CLI, GitHub Actions, docs, security, observability, and release-readiness tasks to the right Factor Skill. Use when auditing, refactoring, packaging, or improving a project and the best review lens is not yet obvious.

  • Open pr

    stella/skillguard/.agents/skills/open-pr Skill

    1★ repo

    Prepare the current worktree branch for a pull request: rebase, self-review, quality checks, and open a draft PR.

  • Actor template

    NVZver/claude-marketplace/core/skills/actor-template Skill

    1★ repo

    Use when authoring or editing an actor — a Skill, slash command, or workflow that prescribes how to act (not just what is true). Enforces the Goal/Input/Steps/Output/Constraints shape, separates Knowledge from Actor, and demands every step produce an observable result.

  • Claude skill safe debug loop

    Shavy72/claude-skill-safe-debug-loop Skill

    1★

    Multi-session skill for the strategic remediation of a complex dashboard/app module that is already built but has too many bugs for an MVP launch. Triggers on "/safe-debug-loop", "/safe-debug-loop Phase 1", "/safe-debug-loop Phase 2", "clean this up", "sweep the bugs", "too many bugs", "module remediation", "dashboard remediation", "bug swamp", "too many bugs for beta", "can't launch", "MVP launch impossible", "module refactor", "systematic bug sweep", "iterative bug fixing", "from bug-mess to MVP" — plus the German aliases "sanieren", "durchkehren", "viele Bugs", "Modul-Sanierung", "Dashboard-Sanierung", "Bug-Sumpf", "zu viele Bugs für Beta", "kann nicht launchen", "MVP launch unmöglich". MANDATORY TRIGGER whenever a user describes a module that is live, has UI/UX plus program flow, BUT has too many bugs to launch. The skill orchestrates 2 MAX-effort Claude sessions: Phase 1 = fully autonomous researcher + detective cross-check (no code touched, bug-plan markdown only). Phase 2 = iterative one-bug-at-a-time loop with an explain-it-to-a-12-year-old step, an isolated smoke test, and cleanup. Use this AGGRESSIVELY whenever a user shows signs of "module built but stuck in a bug mess".

  • Halucatch

    CoderMoray/HaluCatch/halucatch Skill

    1★ repo

    Evaluates the reliability of AI Skill execution. Assesses whether a Skill's output is trustworthy, reproducible, and withstands business scrutiny when executed by an AI agent. Covers four dimensions: data pipeline integrity, code risk, business logic ambiguity, and interpretation guardrails. Used for auditing AI skills, detecting hallucinations or unreliable outputs, verifying reproducibility, and reviewing safety before deployment. Requires a specific skill directory path as input.

  • Github smoke canary

    Ryan2128/skills-to-the-moon/skills/github-smoke-canary Skill

    1★ repo

    Use when the user asks to run the GitHub feedback smoke canary or asks for the smoke token for this repository.

  • Loopify bootstrap

    AndreRatzenberger/loopify/plugins/loopify/skills/loopify-bootstrap Skill

    1★ repo

    Use when seeding a repository with loop materials such as a goal prompt, Loop Contract, quality gate, trace template, acceptance checklist, and test skeletons.

  • Review

    lxb12123/agent-plugin-kit/examples/review-plugin/.claude/skills/review Skill

    1★ repo

    Review the current changes (deterministically read the diff + LLM review) Before committing or merging, when you need to review the correctness and quality of code changes

  • Flight monitor agent

    xunyuAI/skills/flight-monitor-agent Skill

    no license1★ repo

    机票实时查价 Skill:RollingGo 查价、精简/全量穷举、暖色 HTML 分页报告。 用户说「查机票」「穷举搜索」「RollingGo 查价」「国庆特价」「开口程」「东南亚/日本/菲律宾机票」时使用。 适配 Cursor、Claude Code、Codex、OpenClaw 等支持 Skills 协议的 Agent 工具。

  • Redjudge

    gaoyechen/redjudge Skill

    1★

    Evidence-aware adversarial review skill for AI agents

  • Clean skill

    SuperMarioYL/skillprov/testdata/clean-skill Skill

    1★ repo

    Look up the current weather for a city via a public API and print it.

  • Deck a11y audit

    RanaCM/marpsmith/skills/deck-a11y-audit Skill

    1★ repo

    Audit a Marp slide deck or theme CSS for accessibility — WCAG 2.1 AA/AAA contrast ratios, APCA Lc (WCAG 3 draft), color-blind safety under deuteranopia/protanopia/tritanopia simulation, presentation-distance text-size legibility, heading-hierarchy correctness, and reliance on color alone to encode meaning. Output is a structured markdown report ranking issues by severity with suggested palette fixes. Use when the user asks to "audit this deck for accessibility", "check the theme's color contrast", "is this deck colorblind-safe", "run a WCAG audit on this deck", or "is this readable for low-vision users".

  • Doc audit

    s-frantz/agent-memory-trellis/skills/doc-audit Skill

    1★ repo

    Full documentation audit — reads every authoritative doc, checks it against the code, and resolves the inconsistencies found. A comprehensive pass, not a lightweight session check.

  • Mog rating preview

    roooo-798/mogscore-skill/claude-code/mog-rating-preview Skill

    1★ repo

    Use when a user provides an authorized 18+ face, selfie, or portrait photo and asks for an official MogScore, mog rating, AI face rating, face score, or free Mog Rating preview through the existing MogScore website.

  • Agent control

    Timur00Kh/cmux-agent-control-skill/skills/agent-control Skill

    1★ repo

    Run and orchestrate multiple Pi AI agents inside cmux on macOS. Covers pane creation, non-disruptive layout management, interactive Pi sub-agent spawning, sending task prompts, reading screens, and monitoring worker sessions.

  • Agy delegate

    adelsayed2/agy-delegate/skills/agy-delegate Skill

    1★ repo

    Delegate a coding task to the Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to agy — phrasings like "have agy do X", "delegate this to agy", "run it through agy", "use agy to implement/fix/refactor", or "ask agy to..." — or wants to run a task through agy while staying the reviewer. The loop: write the brief → dispatch via relay.mjs → wait → review diff → commit. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly.

  • Github oss contribute

    hyt315/github-oss-contribute Skill

    1★

    开源贡献全程导航:从选 Issue 到 PR 被合并的全流程引导。 自动分析目标仓库规则(CONTRIBUTING、CI、Branch Protection、AI Policy), 提供 Fork/Clone/Branch 操作指导、PR 质量自检(反 AI Slop)、CI 失败诊断、 Review 反馈处理、等待期策略建议和批准门禁。支持官方 GitHub 连接、MCP、CLI、网页与公开 API 回退。 触发词:开源贡献、第一次贡献、提 PR、first contribution、contribute、 找个 issue 做、提交 PR、PR 被拒了怎么办、CI 红了、review 意见。

  • Lookdev auto skill

    connerkward/lookdev-auto-skill Skill

    1★

    Tune a visual/animation/render parameter by eye using a VISION or VIDEO model as the judge — render several labeled variants into ONE artifact, ask the model to rate them and suggest better values, render the suggestions, ask it to pick the best, repeat until good. Use whenever "looks/feels right" is the success criterion and there's no cheap numeric metric — animation easing/timing, zoom/camera feel, color grade, layout/spacing, design params, render/encoder settings, prompt params. The model is the eye; you do the rendering and the loop.

  • Repo sentinel

    hzs0623/repo-sentinel-ai-skill/repo-sentinel Skill

    1★ repo

    Repo guardrail for Claude Code & OpenAI Codex to validate code edits, refactor, bugfix and project development.

  • Capture concept

    lionellau/capture-concept/skills/capture-concept Skill

    1★ repo

    Obsidian knowledge distillery for capturing concepts from conversations, URLs, articles, debugging, decisions, meetings, feedback, aha moments, and domain onboarding into a user-selected Obsidian vault. Auto-detects S1-S12 scenarios, calibrates reference/working/comprehensive depth, researches gaps, generates tags and backlinks, creates MOCs/logs, and writes wiki-grade Obsidian notes. Use when the user says capture this, save this concept, add to my notes/wiki/vault, remember this, what did I learn, document this decision, file this bug fix, or asks to turn useful knowledge into reusable notes.

  • Motion craft

    propiter/motion-craft/skills/motion-craft Skill

    1★ repo

    Trigger: web animation, motion design, micro-interactions, transitions, hover/press/scroll effects, page reveals, route/view transitions, Framer Motion / Motion, GSAP + ScrollTrigger, Lottie, easing curves, spring physics, prefers-reduced-motion, 60fps. Two modes — BUILD motion (pick the right tool and ship it with craft) and REVIEW motion (audit existing animation against a checklist).

    The same file is in 1 other repository

  • Dark tech report generator

    purpose1004/dark-tech-report-generator Skill

    1★

    Turn a report.json into an editable, dark-tech-style PowerPoint (.pptx) work report. Use for monthly / quarterly / half-year / annual reports when the user wants an editable PPTX deck. Supports zh/en labels, configurable fonts and status colors. 把 report.json 生成暗黑科技风、可编辑的 PPTX 工作汇报(月报/季报/半年报/年报),支持中英文与可配置字体、状态色。

  • Android compose diff reviewer

    Small-snake/android-code-review-skills/skills/android-compose-diff-reviewer Skill

    1★ repo

    Review changed Jetpack Compose UI code in a local Android diff, focusing on lifecycle collection, state modeling, side effects, recomposition risk, previews, and UI test gaps.

  • Repo proof

    Gary06868/repo-proof Skill

    no license1★

    Use this skill when a user needs to prove that a repository README or release instructions work from a fresh clone: audit install/run/test/demo steps, create cleanroom evidence, classify README/script/config/package failures, generate minimal fixes, or add a GitHub Action for README truth verification. Do not use for ordinary README writing, generic code review, broad QA checklists, or tasks that do not require repository-grounded fresh-clone evidence.

  • Vercel eve framework

    Xtqm/skills/skills/vercel-eve-framework Skill

    1★ repo

    Expert guidance for building AI agents with Vercel's Eve framework — an open-source, filesystem-first, TypeScript-native agent framework (public beta since June 17, 2026). EXPLICIT triggers — activate when user mentions: "eve agent", "vercel eve", "eve dev", "eve framework", "npx eve@latest", agent.ts, agent/instructions.md, agent/tools/, agent/skills/, agent/channels/, agent/connections/, agent/schedules/, agent/subagents/, "defineTool", "defineAgent", "defineEval", "defineMcpClientConnection", "eve eval", "eve channels add", Vercel Sandbox in agent context, Vercel Workflows in agent context, AI Gateway in agent context. SEMANTIC triggers — activate even without "Eve" keyword when user describes: "durable AI agent on Vercel", "long-running AI agent", "agent that survives crashes or deploys", "workflow-backed agent", "checkpointed agent sessions", "agent that runs for hours / days / weeks", "agent with human-in-the-loop approvals", "filesystem-driven agent framework", "Vercel agent framework", "agent directory structure", "agent that deploys to Vercel", "agent with sandboxed code execution", "agent with isolated compute". ACTION triggers — activate when the user wants to: scaffold a new agent project on Vercel, add channels (Slack, Discord, Teams, GitHub) to an existing agent, add approval gates to agent tools, connect an agent to MCP servers, set up agent observability with OpenTelemetry, test agent behaviour with scored evals, migrate from another agent framework to Eve. This skill covers the complete Eve surface. For deep topics it routes to focused reference files, each loaded only when relevant, reducing context overhead by ~70%.

  • Briefing loop

    RandyHaddad/briefing-loop/skills/briefing-loop Skill

    1★ repo

    Set up and run a harness-agnostic briefing loop that learns a user's reading taste over time, builds recurring digests from articles, feeds, newsletters, papers, X posts, videos, podcasts, or existing digests, verifies links/dates/recency, maintains transparent memory, delivers digests to the user's chosen surfaces such as chat, email, Slack, or PDF/EPUB, and can send approved individual readings to Kindle. Use when the user wants a daily/weekly reading digest, a learned recommendation loop, source watchlist, Kindle send workflow, catch-up tracker, or feedback-driven reading system.

  • Canon

    sixgodgit/canon Skill

    no license1★

    技能生态图书管理员 — 不是判断器也不是园丁。 将 Hermes Agent 技能生态组织为四层架构(热气层/常驻层/种子库/隔离层), 负责分类上架、索引维护、定期轮转和借阅管理。 以目录管理员而非法官的身份维护生态健康。

  • Fan out fan in agent skill

    prerock/fan-out-fan-in-agent-skill Skill

    1★

    Use when a single LLM pass on a hard, open-ended, or high-stakes problem feels unreliable, order-dependent, or sensitive to context length — for example research, planning, design reviews, root-cause analysis, audits, or any task where rerunning the same prompt yields a different set or ordering of findings, or where the input is too large to reason over faithfully in one window.

  • Api routes and validation

    param087/saas-starter-skills/skills/api-routes-and-validation Skill

    1★ repo

    Use when building API endpoints or server actions — validate every input with zod, return consistent typed JSON errors, set correct status codes, and authenticate/authorize before touching data.

  • Ultimate idea watcher

    satishTheLegend/ultimate-idea-watcher Skill

    1★

    Transforms any informal, vague, or incomplete product idea into a deeply researched, gap-free, implementation-ready programme — deep research, full product architecture, dependency-ordered phases, complete UI/UX and design-system architecture, and ready-to-paste designer and engineering prompts, with end-to-end requirement traceability and continuous security, privacy, and accessibility auditing. Use whenever the user shares a product, app, SaaS, platform, or marketplace idea; wants to plan, scope, research, or validate a product; wants work split into phases; wants a complete screen inventory, workflow map, or design system; wants design-before-implementation prompts; wants to audit a plan for missing requirements, contradictions, or gaps; or wants to verify or continue a previously planned product. Trigger even when the user gives only a one-line idea or does not say 'plan' explicitly — e.g. 'I want to build X', 'here is my startup idea', 'turn this into a real product', or 'what should I build first'.

  • Project ninja

    made-on-weekends/vibe-code-ninja/project-ninja Skill

    no license1★ repo

    Maintain alignment between code and project documentation across AGENTS.md, CLAUDE.md, GEMINI.md, README.md, and the docs/ folder (PRODUCT, ARCHITECTURE, API, DATABASE, SCHEMA, DESIGN, BRAND, UX, COMPONENTS, DECISIONS, SECURITY, TESTING). Stack-agnostic — works for any language or framework. Use this skill at the start of any non-trivial coding session to load ONLY the relevant docs (token-efficient routing), before adding or removing features (to prevent scope drift and accidental deletions), and after changes are merged (to update only the docs that actually need updating). Trigger this skill whenever the user mentions align, drift, scope, documentation, project setup, init, update docs, refactor, or any feature add or remove — even if they do not explicitly ask for documentation work. Also trigger on phrases like "is this in scope", "did we decide", "what's the convention", or any time the user is about to delete code.

  • Rick rubin

    vinny380/rick-rubin-skill/skills/rick-rubin Skill

    1★ repo

    Judge decisions and artifacts the way Rick Rubin judges work - by taste, not by spec. Use when building or evaluating code, UI, prose, design, product calls, names, or structure and the user asks whether it is good, tasteful, alive, soulful, overbuilt, or worth shipping. Triggers on 'rubin', 'judge this', 'is this any good', 'make this tasteful', 'does this have soul', 'what would Rubin think', or similar critique requests. Runs as a silent operating mentality, not a persona: it changes what you decide, never how you speak.

  • Windows disk cleaner

    ScauYjj/windows-disk-cleaner-skill/skills/windows-disk-cleaner Skill

    1★ repo

    Diagnose, clean, and manage Windows disk space when users ask to free C drive or other drive space, clean Windows junk files, find large files, remove caches/logs/update leftovers, safely clean app data, schedule recurring cleanup, or migrate high-growth app data from C drive to another drive. Supports scan-only, conservative cleanup, standard cleanup, deep administrator cleanup, and long-term migration strategies with strict safety rules.

  • Mneme engine

    Aexagon/mneme/plugins/mneme/skills/mneme-engine Skill

    1★ repo

    The Mneme self-improving cache protocol — how to read the cache, when to save a learning (the relevance gate), the note schema, the lean-index and dedupe rules, and how skills read/write the cache. Use when capturing a learning to Mneme, writing a cache note by hand, pruning the cache, or building a skill that reads or writes Mneme.

  • Karpathy guidelines for codex

    guanbear/andrej-karpathy-skills-for-codex/skills/karpathy-guidelines-for-codex Skill

    1★ repo

    Apply Karpathy-inspired coding-agent discipline in Codex. Use when writing, reviewing, debugging, or refactoring code to state assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.

  • Critical second pass

    FlyingFSR/critical-second-pass Skill

    1★

    Use when the user explicitly asks for a second, harder look at something already produced: a prior answer, proposal, plan, findings, workflow or governance decision, diff, completed change, handoff, or written draft. Triggers include "re-review", "review again", "pressure-test this", "poke holes", "red-team this", "stress test", "sanity check this", "audit", "what risks am I missing", "can this be improved", "did we miss anything", "再 review 一遍", "二次 review", "再看一遍能不能更好", "挑挑刺", "看看有没有风险/遗漏", and "帮我 pressure test 一下". Do not use for casual first-pass feedback such as "what do you think?" or "review this" without an explicit second-pass or pressure-test intent.

  • Claude code cli

    Michaelihc/claude-code-cli-codex-skill/claude-code-cli Skill

    1★ repo

    Delegate work from Codex to the local Claude Code CLI with low-waste, current command patterns. Use when Codex needs to call `claude`, choose Claude Code model or effort settings, use `ultrathink` or `ultracode`, run print-mode JSON calls, resume or continue Claude sessions across turns, manage background Claude agents or workflows, cap spend with `--max-budget-usd`, restrict Claude tools, or compare Claude output against Codex work.

  • Debug

    DavisMcCracken/pyxis/skills/debug Skill

    1★ repo

    Diagnose hard or uncertain bugs, reproduce-first — build a feedback loop before hypothesizing. Use when reproduction or cause is unclear, the failure is intermittent or cross-system, or performance regressed.

  • Tls cert curl

    rtwsvj/skill-switch/tests/fixtures/home-audit-benign/.agents/skills/tls-cert-curl Skill

    1★ repo

    Documents checking a TLS certificate name and calling a health endpoint.

  • Agentpub blueprints

    agentpub-io/skill/skills/agentpub-blueprints Skill

    1★ repo

    Use when producing a consistent, on-brand, reusable artifact or deliverable with agentpub, when asked to create or use a blueprint, or when a user says "save this as a template" after liking a one-off output.

  • Developer

    matt-bat/agent-skill-foundry/packs/developer Skill

    no license1★ repo

    Use for general Agent engineering work that needs a compact operating policy for clarification, sequencing, safe command execution, regression control, documentation upkeep, quality review, frontend judgment, and the persistent --quizme clarification mode.

  • Claude daily log

    ShockRock2004/claude-daily-log Skill

    1★

    Compile everything Claude did today across ALL sessions and repos into one dated teaching-guide markdown saved in "~/Daily Log", render it as a phone-readable PDF, and upload to Google Drive. Safe to run multiple times a day — it appends only newly-uncovered work to that day's single file rather than overwriting. Use when the user runs /daily-log, or says "log today's work", "end of day log", "daily log", "wrap up the day", or any similar end-of-day trigger. Accepts an effort level (light/medium/heavy, default heavy) to control token usage — e.g. "/daily-log medium" — and optionally a past date (YYYY-MM-DD).

  • Production readiness audit

    P1tak4s/production-readiness-audit Skill

    1★

    Audit, scan, and harden a codebase for production across security, reliability, testing, data/compliance, operations, and accessibility. Use when the user asks to security-check, security-scan, security-review, audit, harden, or assess production-readiness of a project; when checking for injection, auth/authz, secrets, TLS, rate limiting, dependency/supply-chain vulns, multi-tenancy isolation, PII/GDPR/HIPAA handling, audit logging, error handling, retries/idempotency, circuit breakers, race conditions, caching, tests/coverage/load/chaos testing, RTO/RPO/disaster recovery, observability/alerting, deploy safety/rollback, architecture diagrams/ADRs, or accessibility; or when asked to scaffold these controls, a threat model, DR plan, or audit report. Combines a stdlib-only scanner script with deep reference checklists and ready-to-fill templates.