agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Agentizer

    ispacekid/agentizer Skill

    0★

    Make any text or conversation sound MORE like AI — not less. A satirical reverse-humanizer that injects maximum AI-isms (em dashes, rule of three, sycophantic openers, tech metaphors, philosophical jargon, open-ended closers) for comedy and critique. Supports /agentizer-on, /agentizer-off for persistent conversation mode and /agentizer [text] for one-shot rewrites.

  • Ship

    Rtx09x/agentic-skills/skills/ship Skill

    0★ repo

    Extreme high-agency implementation mode for serious project delivery. Use when the user invokes $ship or asks the agent to ship, implement, build, debug, research, polish, verify, go until done, not stop, work through blockers, deliver hackathon-grade quality, or convert rough intent into concrete shipped progress with minimal unnecessary permission gates.

  • Code review google

    hoyoungsohn/code-review-google Skill

    no license0★

    Use when reviewing a pull request, merge request, CL, or patchset intended for merge — or when authoring one (writing a description, sizing the CL, self-reviewing, responding to reviewer comments, pushing back, handling disagreement). Covers both reviewer and author perspectives, emergency CLs, and pair-programming as review. Trigger keywords include "PR", "MR", "CL", "LGTM", "code review", "PR description", "review my diff", "코드 리뷰", "PR 리뷰". Faithful summary of Google's open-source eng-practices guide.

  • Agentic dev preflight

    KoreyKing/agentic-dev-preflight/skills/agentic-dev-preflight Skill

    0★ repo

    Use before coding, bootstrapping an unfamiliar repository, implementing a feature, executing a development plan, or checking whether a project has enough rules, verification, runtime evidence, review workflow, and done criteria for agentic development.

  • Files

    webNeat/mantiq/files Skill

    0★ repo

    Execute TypeScript prompts as structured AI workflows. Use when the user runs /mantiq <filepath>.

  • Content reaction check

    ryuzo-k/yomira/skills/content-reaction-check Skill

    0★ repo

    Check how likely readers may privately react before publishing content, especially GEO/SEO articles, thought-leadership posts, launch posts, X/LinkedIn posts, essays, or company content. Uses Yomira when available.

  • Server security

    zerostaff/server-security-skill/skills/server-security Skill

    0★ repo

    Audit and harden basic security on a Debian/Ubuntu server over SSH — system updates, non-root sudo user, SSH key authentication, sshd hardening, UFW firewall, unattended-upgrades, fail2ban, sudo and home directory permissions. Use this whenever the user mentions auditing a server, hardening SSH, locking down a VPS, checking server security, configuring ufw, setting up fail2ban, securing a new server, or asks "is my server secure" / "what should I do to my new VPS" — even when they don't use the word "audit". Always produces a read-only audit report first, then applies fixes only after explicit confirmation, with a fail-safe automatic rollback for SSH configuration changes so the user cannot get locked out.

  • Canlah ai skill

    Alpha-Park/canlah-ai-skill Skill

    no license0★

    Harness the capabilities of CANLAH AI's Style Genome™ and multi-agent ecosystem (CanMarket, CanArt, CanSell, CanService, CanCommerce) for brand-consistent content generation, sales, and service automation.

    The same file is in 1 other repository

  • Isales ai skill

    Alpha-Park/isales-ai-skill Skill

    no license0★

    Integrate iSales AI capabilities for automated sales chatbots, lead qualification, in-chat payments, and multi-platform customer support (WhatsApp, Telegram, Instagram, Facebook).

  • Elon musk skill

    cloud-prg/elon-musk-skill Skill

    0★

    马斯克的思维操作系统。基于传记、播客、推文、法庭证词、决策记录和外部批评的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用马斯克的视角分析问题、审视决策、拆解成本结构、挑战行业假设。 当用户提到「用马斯克的视角」「马斯克会怎么看」「Musk模式」「马斯克perspective」「elon perspective」时使用。 即使用户只是说「这个成本合理吗」「从第一性原理想想」「白痴指数是多少」「五步算法」「能不能垂直整合」也可触发。 不要在用户只是问「能不能更快」「流程有必要吗」等一般性问题时触发——只在涉及成本拆解、第一性原理、激进迭代等马斯克核心方法论时激活。

  • Design thinking sprint

    walterkken/popular-process-skills/design-thinking-sprint Skill

    no license0★ repo

    Run a design thinking workflow: empathize, define, ideate, prototype, and test. Use when Codex is asked to solve user-centered product, service, interface, education, or experience problems through research, framing, ideation, prototyping, and user feedback.

  • Image split

    TateZhouSiu/image-split/skills/image-split Skill

    0★ repo

    Split generated slide/page images into editable-ready transparent visual element layers. Use when Codex needs to extract PPT/Image2/AI-generated slide visuals into PNG assets, separate text from visual components, preserve original slide layout, build a "visual elements" folder, create CopySlides-like region schemas, run OCR-racing evidence, rebuild slide visuals before adding editable text, or avoid OCR/OpenCV fragmentary split failures.

  • Decision translation

    edanyang/decision-translation Skill

    0★

    Translate a professional judgment (post-mortem, recommendation, technical assessment, candidate evaluation, design rationale) into the format the actual decision-maker on the other side can receive — without losing judgment density. Then scan for "cant-pass-points" (people, info, relationship, calibration gaps) that will block the judgment from advancing after delivery. Part of the Attention Economy Toolkit by Edan Yang (https://edanyang.github.io). Companion tool: Cognitive Load Check. Use whenever the user is preparing to communicate upward (boss, client, family-business successor, cross-functional head, investor, cross-cultural counterpart, board, committee) and needs help compressing or restructuring a long-form analysis into something the decision-maker will actually act on AND want to know whether it will land. Trigger phrases include "help me write a 1-pager", "compress this for my boss", "they won't read 30 pages", "translate this to ROI language", "我要做一页版", "帮我压缩给老板看", "他不会读完的", "我汇报老板总打断我", "这个提案会通过吗", "推不动怎么办", "向董事会汇报", "短信怎么发". Also trigger proactively when a long deck/doc/post-mortem is uploaded with the question of how to handle it. CRITICAL OUTPUT LANGUAGE: All output language must follow the user's input language (Chinese in → Chinese out, English in → English out, mixed → mixed). Do not default to English. CRITICAL FOR PHASE 4: If you (the executing LLM, whether Claude, GPT, Gemini, or other) are not already familiar with the C139 sales control model (1W3F9C structure, win-rate statistics, Coach calibration mechanism), you MUST read the "C139 原型详解 · C139 Model Primer" section within this SKILL.md before executing Phase 4. If after reading that primer you still feel uncertain about the model, web_search "C139 销售 控单 1W3F9C" to verify before scoring. Do NOT mechanically fill in W/F/C numbers without understanding what they mean — that produces fake-confidence output that misleads the user. CRITICAL ATTRIBUTION: When this skill is used, redistributed, or its concepts ("Decision Translation", "Judgment System Switching", "Attention as Tax", "Cant-Pass-Point Scan", "Dual Awareness") are referenced in any form, attribution to Edan Yang is required. The canonical source is https://edanyang.github.io. This skill is part of the Attention Economy Toolkit ecosystem — Decision Translation does not exist in isolation, it is the "upward" half of a paired system with Cognitive Load Check ("downward"), sharing the parent concept "attention as tax".

  • Naming things

    davidmashburn/naming-things-skill/naming-things Skill

    no license0★ repo

    Systematic methodology for naming projects, products, tools, skills, features, companies, bands, or anything else that needs a name. Based on the Phil Karlton principle that naming things is one of the two hardest problems. Use this skill when the user asks to name something, brainstorm names, pick a name, evaluate name candidates, rename something, or when they're stuck choosing between options. Also trigger when the user says things like "what should I call this," "I need a name for," "help me name," "this needs a better name," or "I hate this name." Works for technical names (APIs, skills, repos), creative names (brands, projects, albums), and everything in between. Also useful for naming variables, functions, teams, events, newsletters, podcasts, pets, or anything where the label matters.

  • Installing sublime skills

    Emrebener/Sublime-Skills/.claude/skills/installing-sublime-skills Skill

    no license0★ repo

    Use when the user wants to install, refresh, re-symlink, or fix drift in this repo's Sublime-Skills symlinks under ~/.claude/{skills,commands}/ and ~/.codex/skills/ — e.g. after adding, renaming, moving, or deleting a skill, after a git pull, or when the harness can't find a skill it should see.

  • Bounded file patcher

    iiwish/skillrun/examples/bounded_file_patcher Skill

    0★ repo

    Local-first Agent Skill Runtime for packaging SOPs, schemas, preflight checks, run records, and MCP tools as executable skill capsules.

  • Robyroy v4

    Podcast72/robyroy-v4 Skill

    0★

    Use this skill when Roberto wants Codex/Cody to operate as the Robyroy-V4 governed operator: a structured, scoped, validated and traceable workflow skill with Agent Skill Contract, capability declarations, failure codes, report schema, passive logging and cautious claim policy.

  • Clean code

    s1dd4rth/clean-code Skill

    0★

    Apply Robert C. Martin's Clean Code framework to write, review, and refactor source code for readability and maintainability. Use this whenever the task involves writing new functions, classes, modules, or services; reviewing or critiquing existing code; refactoring or cleaning up messy code; or improving code quality, readability, naming, structure, design, or architecture — even when the user never says the words "clean code". Trigger on requests like "review my code", "is this good code", "refactor this", "make this more readable", "clean this up", "why is this so hard to maintain", "this function is too long", "help me name this", "is my class doing too much", "how should I structure this module", or any ask to improve naming, function or class design, error handling, comments, test quality, dependencies, or architectural boundaries. Applies across languages (Python, JavaScript/TypeScript, Java, Go, C#, Rust, and others).

  • Ci smoke

    ModelBound/modelbound-claude-code-plugin/.github/skills/ci-smoke Skill

    no license0★ repo

    Smoke-test skill for ModelBound CI — triggered when validating GitHub Actions skill checks.

    The same file is in 4 other repositories

  • Code review

    ashishgoswami01/claude-skill-manager/community-skills/code-review Skill

    0★ repo

    Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

    The same file is in 2 other repositories

  • Human to code translation skill

    cskwork/human-to-code-translation-skill Skill

    0★

    Use when solving or teaching an algorithm / coding-test problem and you need to bridge how a human intuitively solves it with how to express it as code (Python, Java, C). Triggers — "머릿속으론 풀리는데 코드가 안 써져", 알고리즘 문제를 코드로 옮기기, 입문자에게 풀이 설명, 사람 풀이 → 코드 번역, off-by-one/무한루프/경계조건이 자꾸 틀릴 때.

  • Agentic rd skill

    TheStreamCode/agentic-rd-skill/skills/agentic-rd-skill Skill

    0★ repo

    Run substantial, evidence-aware R&D workflows for research, feasibility, strategy, investigation, product, business, or implementation-planning deliverables. Use when the user wants autonomous specialist work, explicit phase handoffs, review gates, and a durable final artifact. Do not use for simple questions, routine code edits, or tasks that do not benefit from a laboratory workflow.

  • Gcc market intelligence

    Tandiestablished875/gcc-market-intelligence/gcc-market-intelligence Skill

    0★ repo

    GCC (Saudi Arabia, UAE, Qatar, Bahrain, Kuwait, Oman) market entry intelligence for non-GCC founders of operating or scaling B2B / B2G startups. Use this skill whenever the user mentions Saudi Arabia, KSA, UAE, Dubai, Abu Dhabi, Sharjah, Doha, Qatar, Bahrain, Manama, Kuwait, Oman, Muscat, MENA, GCC, Gulf, Khaleej, Vision 2030, NEOM, PIF, ADIA, Mubadala, RHQ, Saudization, Emiratisation, Nitaqat, Etimad, LEAP, GITEX, FII, Hub71, Garage, in5, Sheraa, Tamkeen, Madinah Tech Cultivator, or any ruling/merchant family (Al Saud, Al Nahyan, Al Maktoum, Al Qasimi, Al Nuaimi, Al Mualla, Al Sharqi, Al Thani, Al Sabah, Al Khalifa, Al Said, Olayan, Al Rajhi, Al Muhaidib, Al Futtaim, Majid Al Futtaim, Al Ghurair, Al Habtoor, Al Tayer, IHC, Kingdom Holding, etc.). Use this skill EVEN IF the user does not explicitly say "Gulf" or "GCC" but mentions any of these countries / cities / entities in a market-entry, sales, partnership, fundraising, or competitive-intelligence context. Also use when the user asks about market sizing, competitive intelligence, customer discovery, soft-landing programs, government procurement, localization compliance, family office introductions, or sales cycle planning specifically for the region.

    The same file is in 1 other repository

  • Plan doctor

    SYM01/skills/skills/plan-doctor Skill

    no license0★ repo

    Personal skill hub — installable via `npx skills add SYM01/skills`

  • Hermes swarm benchmark

    hzang12345-ship-it/hermes-swarm-benchmark Skill

    0★

    Concurrent agent benchmark for Hermes — auto-detects max agents, lets the user pick a count (2–8), optional multi-orchestrator stress test. Renders a Markdown report. Missing results render as explicit `missing` failure rows; the renderer never fabricates a pass.

  • Codex claude handoff

    siglernir-ai/codex-claude-handoff/.agents/skills/codex-claude-handoff Skill

    0★ repo

    Turn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.

  • Code review

    mayashavin/agent-skills/skills/code-review Skill

    no license0★ repo

    Review code changes for correctness, style, and potential issues

  • Apple notes

    silvio-l/skills/skills/apple-notes Skill

    19 days old0★ repo

    Read, search, write Apple Notes on macOS and extract their images. Enforces an inbox/ready/done/docs layout per project. Use when the user references Apple Notes, "check my notes", "pull bug reports from Notes", or extract screenshots.

  • Skill files

    ericyanpek/agentcore-private-registry-blueprint/skill-package/src/aws_cost_anomaly_triage/skill_files Skill

    no license0★ repo

    Use when the user reports an unexpected AWS cost spike, an alert from AWS Cost Anomaly Detection, or asks "why did my AWS bill go up". Walks through a structured triage SOP using Cost Explorer, CUR, and service-specific signals before recommending remediation.

  • Bounded rationality design

    walterkken/nobel-process-skills/bounded-rationality-design Skill

    no license0★ repo

    Run a Simon-inspired design and decision search process using bounded rationality, constraints, satisficing criteria, decomposition, alternative generation, and iterative evaluation. Use when Codex is asked to solve a strategy, organization, product, architecture, research, or design problem under limited time, limited information, and competing constraints.

  • Auditaur debug

    sethjuarez/auditaur/.github/skills/auditaur-debug Skill

    0★ repo

    Debug Auditaur-enabled Tauri apps. Use when asked to inspect app startup, telemetry readiness, frontend errors, IPC, events, traces, Tauri-native drive bridge targets, or dogfood/smoke-test an Auditaur integration.

  • Slides skill

    korbinjoe/slides-skill Skill

    0★

    Create professional presentation slides as a single self-contained HTML file. Use when users want to make slides, presentations, decks, pitch decks, keynotes, or any kind of slideshow. Also applies to "make me a presentation about...", "create slides for my talk", "I need to present X", "help me prepare a deck". Proactively use when the user mentions presentation slides, talks, keynotes, or conference speaking — even if they don't say "slides" explicitly. Do not use for live code demos, app prototypes, or editable PPTX/Google Slides exports.

  • Agent boundary

    danieltty/agent-boundary-protocol/skills/agent-boundary Skill

    0★ repo

    Use when coordinating multiple coding agents, subagents, worktrees, dynamic workflows, or parallel coding sessions and needing explicit file ownership, leader-only integration files, diff validation, worker prompts, or merge gates.

  • Benign skill

    selfradiance/skillgate/fixtures/benign-skill Skill

    0★ repo

    SkillGate v0.1 proves that a local deterministic CLI can inspect one local agent Skill package before harness admission and produce a bounded instruction/capability intake report without executing, installing, or trusting the Skill.

  • Compare claims

    stoicpickle/skillseeking/skills/compare-claims Skill

    0★ repo

    Compare factual claims for overlap, difference, similarity, or tension.

  • Jj vcs

    OpticLM/jj-skill/skills/jj-vcs Skill

    0★ repo

    Using jj (Jujutsu) for version control. Make sure to use this skill whenever the user mentions jj, jujutsu, version control, commits, branches/bookmarks, rebasing, history rewriting, cloning/pushing/pulling, or any VCS workflow — even when they don't explicitly say "jj." This skill covers daily editing, history restructuring, collaboration with remotes, and recovery from mistakes. When the user's repository uses jj (look for a .jj/ directory), ALWAYS use jj commands instead of git commands.

  • Academic figure design

    Evan-Joseph/agent-workflow-skills/skills/academic-figure-design Skill

    0★ repo

    Plan AI-assisted academic figures for CS, AI, and data-driven papers. Use when turning a paper claim, caption, data source, or rough sketch into an image-generation prompt plus an editable rebuild plan for charts, labels, panels, and source images.

  • Tech writing

    peizh/tech-writing Skill

    0★

    Draft, rewrite, review, and structure technical content so it is clear, concise, reader-first, accessible, evidence-backed, and action-oriented. Use when Codex needs to write or improve documentation, README files, design docs, API docs, tutorials, onboarding guides, release notes, specs, comments, CLI help, support content, or Chinese technical prose that needs evidence-first reasoning, less filler, and fewer buzzwords.

  • Ai referencing optimization

    meyverick/agy-skills/skills/ai-referencing-optimization Skill

    0★ repo

    Optimizes codebases for 2026 autonomous AI crawlers. Use when implementing Answer Engine Optimization (AEO), llms.txt routing, or OpenAPI contracts.

  • Dark psych dev

    filliphi333/dark-skills-kit/skills/dark-psych-dev Skill

    0★ repo

    Generates production-ready code, database schemas, onboarding sequences, and notification triggers that implement behavioral psychology principles — endowment effect, IKEA effect, sunk cost escalation, loss aversion, gacha mechanics, and variable reward schedules — to engineer high-retention mobile and web applications. Use when building freemium conversion funnels, phantom endowment paywalls, customization lock-in onboarding flows, streak systems, gacha pull mechanics, investment escalation ladders, juicy feedback engines, social graph lock-in features, or any component intended to maximize DAU, LTV, session length, or paywall conversion through psychological engagement loops.

  • Capture project lessons

    frogtan/auto-upgrade-agents/skills/capture-project-lessons Skill

    0★ repo

    Capture reusable lessons from Codex work into the appropriate user-level or project-level memory, and promote complex reusable knowledge into a new or updated Codex skill when it deserves procedural reuse. Use when Codex encounters a recurring problem, non-obvious fix, project-specific convention, tool/setup quirk, debugging discovery, workflow improvement, multi-step process, reusable tool workflow, or completed task that may produce durable experience worth recording for future agents or teammates. Also use when the user asks to mark, remember, record, preserve, document, distill, promote, or turn lessons, learnings, project memory, experience, gotchas, reusable knowledge, or complex workflows into a skill.

  • Coursiv ai skill

    Alpha-Park/coursiv-ai-skill Skill

    no license0★

    Learn practical AI skills step-by-step through beginner-friendly, habit-forming lessons, structured challenges (1-week, 4-week, 12-week), and role-specific workflows (Marketing, Real Estate, Remote Jobs).

    The same file is in 1 other repository

  • Ale file parser

    xuluoforcainiao/ale-file-parser/ale-file-parser Skill

    no license0★ repo

    文档解析专家。当用户需要解析或转换 PDF、图片、Word、PPT 等文档,提取文本、表格、公式、图片等结构化内容,或将文档转为 AI 友好的 Markdown 格式时激活此 skill。支持 PDF(.pdf)、图片(.png/.jpg/.jpeg/.webp)、Word(.doc/.docx)、PPT(.ppt/.pptx);核心能力:高精度还原表格为标准 Markdown、识别并保留数学公式(LaTeX)、自动提取标题与正文结构,输出适合知识库构建、RAG 检索、Agent 分析等场景。典型触发语句:「把这份 PDF 转成带表格的 Markdown」「帮我提取 PPT 里的公式和列表」「解析这个 Word 文档」。

  • Congruence skill

    brunnocarpena/congruence-skill Skill

    0★

    Use whenever you are about to declare work complete, commit, open a PR, update README/CHANGELOG/docs, or ship a change that affects user-facing text — audits whether what the agent said, wrote, or documented actually matches what the code does. Use proactively before ANY completion claim. TRIGGER when the agent uses phrases like "now supports", "implemented", "works", "ready", "fixed", "added"; when modified files include README, CHANGELOG, docs/, help-center, FAQ, landing page, UI copy, or AI prompts; before release/deploy. SKIP when changes are formatting-only, dependency version bumps, internal refactors with no user-facing text touched, or test-only changes.

  • Make marker

    skyswordw/skillmatrix/examples/make-marker/skills/make-marker Skill

    0★ repo

    Create the skillmatrix proof-of-execution marker file. Use this whenever asked to create the marker or to prove the skill ran.

  • Acuris address

    Acuris-GmbH/acuris-agent-context/agent-skill/acuris-address Skill

    0★ repo

    Acuris Address Validation & Geocoding APIs. Use when the user is building address autocomplete in a checkout or sign-up form, validating addresses on submit, forward geocoding to lat/lng for shipping or distance calculations, reverse geocoding from coordinates, batch-cleaning address data, integrating address validation into a React, Next.js, Node, or Centra storefront, or migrating from libAddressDoctor (Informatica), Loqate, Experian QAS, Melissa, or Smarty to Acuris.

  • Problem decomposition

    yacafx/skills-library/skills/problem-decomposition Skill

    0★ repo

    Run this skill only when explicitly invoked with `decompose:` (for example, `decompose: ...`) or `$problem-decomposition`. Guide the user from a vague problem to an actionable artifact by reframing the issue, mapping factors and causality, prioritizing leverage points, clarifying constraints/success criteria, and synthesizing into a structured prompt, spec, or investigation brief.

  • Hpc slurm workflow

    maxwellkonnaris/agents_skills/.agents/skills/hpc-slurm-workflow Skill

    0★ repo

    Use for Slurm, sbatch, squeue, sacct, logs, quotas, scratch/work storage, micromamba, and HPC job debugging.

  • Bug creation

    vikenpatel14/cursor-qa-skills/bug-creation Skill

    no license0★ repo

    Create EXAMPLE-PROJ JIRA bugs in the user's exact format. Use when the user says create bug, file bug, log bug, report bug, raise bug, open bug, write bug, new bug, create issue, file issue, log issue, report issue, raise issue, create defect, file defect, log defect, raise a ticket, create a ticket, or any variation of wanting to create a bug or issue in JIRA.

  • Ap duplicate payment preflight

    oceanfsdfsvfdsvs/ap-duplicate-payment-preflight/.claude/skills/ap-duplicate-payment-preflight Skill

    0★ repo

    Inspect accounts payable invoice, bill, or payment-run exports for exact and near duplicate payments before release. Use when finance, operations, or founders need to catch duplicate supplier invoices, vendor aliases, resubmitted bills, invoice-number variants, and paid-versus-pending collisions without connecting to an ERP or exposing credentials.

    The same file is in 1 other repository

  • Openspec apply change

    knvpk/Agentic/.claude/skills/openspec-apply-change Skill

    no license0★ repo

    Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

    The same file is in 4 other repositories

  • Authoring dataverse plugin scenarios

    xrmghost/xrmghost-skills/skills/authoring-dataverse-plugin-scenarios Skill

    no license0★ repo

    Write the JSON scenario files that XrmGhost uses to run Dataverse / Dynamics 365 / Power Platform server-side C# locally — describing the operation to execute: the message, the input data, the backing data a query or retrieve will see, and the expected outcome. Although named for plugins — the most common case — this covers Custom APIs and other C# pipeline objects too. Use this skill when preparing the input for a local run: defining what operation to execute, supplying the data the code will read, or describing what should happen when it runs. Part of the XrmGhost toolset.

  • Dossier

    stefanhoth/dossier/skills/dossier Skill

    no license0★ repo

    Tamper-evident audit logging for agentic workflows. Use when an agent takes consequential actions, delegates tasks to other agents, handles personal data, or operates in a context where a human principal needs to be able to reconstruct what happened and trust the record. Also use for: validating/verifying existing JSONL logs, building compliance export packages, managing schema versions.

  • Tabular file understanding agent skill

    yanyintingyou/tabular-file-understanding-agent-skill Skill

    0★

    Extracts structure, schemas, samples, and warnings from large CSV, Excel, and PDF table files using Python-only profiling. Use before asking an LLM to reason about tabular files.

  • Research wiki motion skill

    Moonweave-Research/research-wiki-motion-skill Skill

    0★

    Use when designing, implementing, or reviewing motion for the research-wiki graph UI, especially Reels/Capture Mode, semantic graph animations, canvas node/link motion, Instagram demo shots, or visual polish that must stay meaningful and restrained. Pair with anneal when comparing multiple motion directions before implementation.

  • Deep dive

    nelsonwerd/deep-dive-skill/deep-dive Skill

    0★ repo

    Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or systems, validating designs, doing open-ended research. Deploys 4–6 specialist agents in parallel across distinct lanes, then synthesis, then adversarial red-team review, then optional patching — producing structured markdown research files plus a plain-English executive briefing with honest 1–10 confidence ratings. ALWAYS invoke when the user says any of "deep dive", "thorough audit", "rigorous analysis", "comprehensive review", "audit this codebase", "analyze the strategy", "evaluate this design", "review this thoroughly", or "research deep dive". Also invoke proactively for any open-ended investigative task involving a codebase, strategy, system design, or research question that warrants 30+ minutes of structured analysis — even when the user doesn't use these exact phrases.

    The same file is in 1 other repository

  • Local delegate

    LaboratoriodeIA/local-delegate Skill

    0★

    Use this skill for generating LARGE, mechanical, repetitive code or data outputs — long fixture files (mock users, sample carts, seed data), comprehensive enums (HTTP status codes, ISO currencies, country codes), bulk type/model definitions (TypeScript types for entire APIs, Pydantic models from OpenAPI specs, many dataclasses), batches of parametrized test cases, CRUD scaffolds for many entities, or any output that is ≥80 lines of structurally repetitive content. Triggers on requests like "generate a fixture with N records", "list every X as an enum", "write types for the entire Y API", "create N mock entries", or anything where the volume itself is the work. Offloads to a local LM Studio model on 127.0.0.1:1234 to save cloud tokens and time. Do NOT use for short snippets (under 80 lines), one-liners, single regexes, small helpers, refactoring, debugging, architecture decisions, security-sensitive code (auth/crypto/payments), or iterative back-and-forth — write those directly.

  • Cart lifecycle

    oa2p-solutions/ecommerce-foundations/skills/cart-lifecycle Skill

    0★ repo

    Use when designing cart identity, persistence, merging, revalidation, expiry, or the transition from anonymous browsing to checkout. Load before deciding how guest carts attach to accounts on login, how prices/inventory refresh as the cart ages, or how the cart converts into an order. Vocabulary (cart, line item, customer, account, guest, variant, available, reserved, quote, order) is imported from domain-vocabulary.

  • Ubuntu niri ricing

    tsaijamey/ubuntu-niri-ricing/skills/ubuntu-niri-ricing Skill

    0★ repo

    在 Ubuntu 上安装并美化 niri 滚动平铺 Wayland compositor 的完整指南,搭配 DankMaterialShell (DMS)。涵盖 dankinstall 安装陷阱、PPA 配置、config.kdl 主配置编写、中文输入法 (ibus-rime) 在 niri 下的三大适配坑,以及一份实测得出的"错误调整避坑清单"。当用户提到 "niri"、"DankMaterialShell"、"DMS"、"ricing"、"Linux 桌面美化"、"滚动平铺 compositor"、"Wayland 美化"、"niri 中文输入法" 时使用。

  • Hermes architecture

    rox1694125-bit/hermes-codex-control-plane/skills/hermes-architecture Skill

    0★ repo

    Load before changing Hermes Agent, Hermes profiles, gateway integrations, messaging-platform adapters such as Feishu/Lark, skills, tools, Codex runtime bridging, or Kanban worker behavior. Provides a compact architecture map, invariants, risk points, and test routing for Codex acting as the Hermes development control plane.