agentsclimarketplace

The catalog

608,666 rows, by stacks then stars

  • Viva prep

    khaichonggg/viva-prep Skill

    no license1★

    Evidence-based Agent Skill for project viva preparation and mock questioning.

    The same file is in 1 other repository

  • Octopus cli

    olsh/octopus-deploy-skills/plugins/octopus-cli/skills/octopus-cli Skill

    no license1★ repo

    Drive the Octopus Deploy CLI (`octopus`) for releases, deployments, runbooks, task logs, projects, environments, tenants, spaces, deployment targets, packages and variables. Use this whenever the user mentions Octopus Deploy, pastes a `*.octopus.app` URL, asks why a deployment failed, wants to cut/promote/deploy a release, run a runbook, check deployment or task status, read a task log, or push packages and build information — even if they never say "CLI". Read this before running any `octopus` command: the CLI prompts interactively by default and has hard gaps (no task list, no log retrieval, no approvals) that require a documented REST escape hatch.

  • Fog ask

    leoncuhk/defog/skills/fog-ask Skill

    1★ repo

    Resolve open decisions in the ledger by interviewing the user, one evidence-priced question at a time. Use when FOG.md has open KU decision items, or the user asks to be grilled about a plan.

  • Content gap analysis

    vibe-marketer-sandbox/competitor-content-audit/skills/content-gap-analysis Skill

    1★ repo

    Runs competitive content gap analysis: research a company and competitors, fetch sitemaps, categorize URLs, write strategy reports, and compare gaps. Use when the user asks for content strategy analysis, sitemap analysis, competitor content gaps, or content-gap-analysis.

  • Easyreading academic paper

    szddddddd/easyreading-academic-paper/easyreading-academic-paper Skill

    1★ repo

    将计算机视觉、计算机图形学、多视图与前馈式三维重建(feed-forward 3D reconstruction)、世界模型、生成式深度学习、Gaussian Splatting 等领域的 arXiv、PDF、HTML 或论文文本,转换为按原论文结构组织、内容覆盖完整、公式与实验逐项讲清、适合逐篇学习的中文学术 HTML 长文。用于用户要求“完整读懂论文”“不省略论文内容”“比原论文更易读但保持强学术性”、需要逐节精读、公式/图表/算法/代码对应或附录与补充材料解读的场景。

  • Verity scribe

    Florent2025/verity-scribe/skills/verity-scribe Skill

    1★ repo

    Evidence-first academic writing, revision, and peer-review support for manuscripts, theses, literature reviews, research proposals, grants, abstracts, reviewer reports, rebuttal letters, and scholarly translations in English or Chinese. Use when planning or drafting a paper, strengthening argument structure, mapping claims to sources, verifying citations, preserving facts during revision, calibrating an author's voice, removing formulaic AI-style prose without detector evasion, checking reporting integrity, simulating peer review, or preparing a response-to-reviewers package.

  • Deai zh gpt style

    YanhanLi/deai-zh-gpt-style/skills/deai-zh-gpt-style Skill

    1★ repo

    Use when editing Chinese or mixed Chinese-English/number text to reduce GPT-5.5/GPT-5.4 style habits, formulaic AI phrasing, over-structured wording, unnatural chat phrasing, or unwanted spaces between Chinese and English/digits.

  • Start ai short drama cn

    caoproAI/start-ai-short-drama-cn Skill

    no license1★

    面向中国大陆AI短剧新手、个人创作者、小团队、企业内容人员和想用作品接单的人。用户不知道AI短剧第一步做什么,或需要梳理目标、故事、形式、工具、预算、平台、赚钱验证路径、发布日期和制作进度时使用。通过每次一道简单选择题,诊断当前缺口,选择一条首发路线,生成30至60秒第一集的剧本、分镜、生成提示、制作清单、正推或倒推时间表与可继续更新的项目进度卡;不承诺播放、签约、分账、涨粉或收入。

  • Tech copywriter skill

    ReneHdzGtz/tech-copywriter-skill Skill

    1★

    Specialized tech copywriter for startups, SaaS, developer tools, fintech, and Web3. Writes landing pages, product copy, release notes, B2B sales copy, social posts, and technical blog content with audience-calibrated depth. Use this skill whenever the user asks to write, rewrite, or review copy for a tech product, website copy, hero sections, CTAs, feature descriptions, product emails, changelogs, one-pagers, cold outreach, or announcements. Also trigger for phrases like "write copy for", "escribe el copy", "necesito un texto para mi landing", "redacta el anuncio del feature", "make this sound less corporate", "this copy feels generic", or any request where the deliverable is persuasive or explanatory text about a technical product. Also handles auditing and cleaning AI-generated copy to remove AI-writing tells, and voice-matching copy to a writing sample. Supports English and Mexican Spanish output with natural code-switching.

  • Idea discovery interview

    bglglzd/agent-workflows/plugins/agent-workflows/skills/idea-discovery-interview Skill

    1★ repo

    Interview a user with a vague product, feature, or application idea before planning implementation. Use when Codex must ask at least ten high-signal questions, capture a durable discovery brief, expose constraints and risks, and produce an evidence-based plan without inventing requirements.

  • Clear thinking

    kopon1/clear-thinking/skills/clear-thinking Skill

    1★ repo

    A deliberate decision-making process for consequential choices, delivered in clear, well-spoken prose that doesn't read as AI slop. Use when you need to make or evaluate a real decision — comparing options, exposing hidden assumptions, deciding build-vs-buy, weighing a strategy, or turning a vague thought into a clear recommendation. Not for quick factual questions or trivial choices.

  • Customs extend

    FrancoisChastel/sydonia-toolkit/skills/customs-extend Skill

    1★ repo

    Add or modify tables and columns in the Sydonia Toolkit customs schema while preserving its conventions (snake_case, ref_/sys_ prefixes, identity PKs, FK-to-ref coded columns, numeric money/mass types) and — critically — its provenance trail (every CREATE TABLE tagged -- src: or -- inferred, coverage updated). Use when the user wants to extend, customise, add a table/column to, or adapt the customs / ASYCUDA schema for their own needs.

  • Untangle inner voice

    YuLulu-Dewkind/untangle-inner-voice/skills/untangle-inner-voice Skill

    no license1★ repo

    Guide a reflective, non-clinical analysis of recurring inner voices, internalized rules, and action stalls. Use when a user feels pierced by criticism, repeatedly thinks they are not good enough, suspects old expectations still control them, says they have no motivation or execution, keeps preparing but cannot start or submit, or wants to distinguish chosen values from approval-, shame-, perfectionism-, people-pleasing-, avoidance-, or result-driven behavior. Produce an evidence-labeled map, a rule audit, an optional action-stall reality check, a keep/update/release/test decision, and, when appropriate, one safe 24-72 hour experiment. Do not diagnose, recover memories, assign blame, or treat an inferred origin as fact.

  • Ib suite

    luyangkk/ib-suite/skills/ib-suite Skill

    1★ repo

    Read-only Interactive Brokers toolchain index and onboarding. Use when orienting across the ib-suite skills, running first-run setup (venv + live/paper config), or deciding which IB skill to run and in what order: ib-sync ingestion, live account/positions/daily-P&L/options overviews, Flex trade or dividend history, or the offline ib-analyze report. It runs nothing itself — the sub-skills do the work and never place, modify, or cancel an order.

  • Okf author

    kodepapa/okfleet/skills/okf-author Skill

    1★ repo

    Create, edit, and enrich Open Knowledge Format (OKF) bundles — directories of markdown concept documents with YAML frontmatter that describe data assets, APIs, metrics, playbooks, and other knowledge. Use this skill whenever the user wants to create a knowledge bundle, document a dataset/table/schema/API as markdown knowledge, add or update a concept in an existing OKF bundle, maintain index.md or log.md files, or mentions OKF, knowledge bundles, knowledge catalogs, or "markdown + frontmatter" knowledge bases — even if they don't say "OKF" explicitly.

  • Wrap

    ravsau/wrap/plugins/wrap/skills/wrap Skill

    1★ repo

    Check whether the current session is safe to close. Use when the user says "wrap", "safe to close?", "is this done?", or "any loose threads?"

  • Paif

    Odinary-AI/paif-skill/plugins/paif/skills/paif Skill

    1★ repo

    Use when Codex is asked to simulate a named persona profile, validate or score supplied persona constraints, compare localized constraint reports, track a persona session, or arbitrate a decision involving multiple personas.

  • Organize files safely

    jocielle-tech/organize-files-safely/organize-files-safely Skill

    1★ repo

    Safely inventory, classify, rename, organize, and archive personal files with explicit approval gates, collision protection, audit journals, rollback plans, duplicate reports, and copy verification. Use when Codex needs to organize macOS folders such as Desktop or Downloads, propose a folder taxonomy, prepare completed projects for external storage, standardize filenames, identify cleanup candidates without deleting them, or execute an already approved batch of file moves.

  • Madosho kb

    hogu-dev/madosho/skills/madosho-kb Skill

    1★ repo

    Use when you want to work with a knowledge base through madosho - import a pre-made llmkb folder into a corpus as one flat document, or read/browse/search/populate a server-owned KB (a corpus's own curated wiki of pages). Complements the llmkb kb-* skills, which operate on a KB folder directly; this skill is the "through madosho" route. Covers the KB agent tools: read (list-kbs / get-kb-page / semantic search-kb) and write (add-kb-page / edit-kb-page).

  • Groundwork

    harsh220601/groundwork-agent-skill/groundwork Skill

    1★ repo

    Evidence-first engineering methodology that makes a coding agent work and verify like a senior engineer. Use for ANY software task - writing code, building features, debugging, fixing bugs or failing tests, repairing broken builds or red CI, refactoring, code review, investigating errors, exploring or onboarding onto an unfamiliar codebase, researching a library/API/framework, scripting, configuration, performance work. Also use when about to state facts about code or APIs, when tests pass but confidence is low, when a task seems done, or on first contact with any repository. Provides a verification loop, an anti-hallucination protocol with claim tagging, a debugging playbook, a deep-research protocol, and a project map + learnings log that make every session smarter than the last. Includes the standing-orders reasoning layer for any answer, code or not: intent reading, Certain/Likely/Assumption markers, self-attack, completeness, refusal rules, and a final gate before sending.

  • Cold email drafter

    AirDoogle/claude-skills/skills/cold-email-drafter Skill

    1★ repo

    Draft a short, human cold email for a prospect in the Notion Prospecting Clients table with ZERO LLM tokens. One editable template fills from the row's columns (Website Status gap, add-on, sector, area, name). Two no-flag paths: click the row's Draft Email link to open a pre-filled Gmail, or invoke by name to save it straight to Gmail drafts. Pairs with local-lead-prospector.

  • Ultra Plan Mode

    JoaquinRuz/Ultra_Plan_Mode Skill

    1★

    Generate a self-contained, offline clickable HTML report for human-in-the-loop review. Turns N complex items (email/chat threads, signals, discrepancies, candidates, findings, queue items, audit recommendations) into scannable cards with ✅ keep / ⚠️ review / ❌ drop toggles, a free-text note per card, a deep link to each item's source, and a one-click "Copy selection" that exports the reviewer's decisions as plain text to paste back. Use whenever a person must review, approve, filter, triage, or audit many items without reading a wall of text — the reviewer's filtering becomes training signal for the agent's next pass. Includes a "master questions" preset for auditing a whole project/area. Triggers: Ultra Plan Mode, clickable review, decision cards, human-in-the-loop, review/approve/filter/triage N items, audit a project, "let me pick which ones". Spanish: revisión clickeable, dejá que yo elija cuáles, preguntas maestras, armá un HTML para revisar/aprobar/filtrar/seleccionar.

  • Coding max

    xi9644737-arch/coding-max/coding-max Skill

    1★ repo

    Diagnose and repair software defects, trace root causes, handle hotfixes, verify fixes, and review completed implementations. Use for bugs, errors, crashes, production incidents, root-cause analysis, code review, quality audits, or regression-safe repair.

  • Cosmosdb vnext emulator

    abhirockzz/cosmosdb-vnext-emulator-skill/skills/cosmosdb-vnext-emulator Skill

    no license1★ repo

    Operate a local Azure Cosmos DB Linux emulator vNext through its bundled Cosmos DB Shell. Use when a request targets the local emulator: inspect resources, create databases or containers, seed, import, export, query, update, verify state, or troubleshoot its bundled cosmoshell.sh. Live Azure accounts and SDK application development are outside this skill.

  • Broken yaml

    aneesh-a7/skill-lint/examples/bad/broken-yaml Skill

    1★ repo

    [this is an unterminated flow sequence

  • Padawan no more

    seyonv/padawan-no-more Skill

    1★

    Use when the user wants to know how often Claude stopped for human input, reduce permission prompts or approval gates, measure time spent waiting for answers, audit AskUserQuestion/plan-mode interruptions, or make Claude Code more autonomous ("need me less", "padawan no more", "knight my claude", "run the jedi trials", "stop asking me so many questions", "why did you block on that", "intervention audit").

  • Clics

    P-Essonam/clicsdev/skills/clics Skill

    1★ repo

    Query Clics analytics and manage projects, goals, funnels, and sessions through the Clics MCP server (`@clicsdev/mcp`), with the `clics` CLI (`@clicsdev/cli`) as a fallback. Use when a user asks about their analytics, mentions Clics, works with the Clics toolset, verifies Clics manually, or needs to choose between MCP and CLI.

  • Capsule

    realbakari/capsule Skill

    no license1★

    Agent control plane for governed, replayable execution. Discovers instruction files, docs and skill folders in a workspace, condenses them into a compact run context, routes a task to exactly one skill pack, and rebuilds skills as portable, license-gated, validated packages. Use when asked to inventory or index available skills, choose which skill applies to a task, reconstruct or port a skill into a distributable pack, or enforce deny-by-default policy over what an agent may read and write. Not for authoring brand-new skills from scratch: route to skill-creator for that.

  • Github research podcast

    Stephen-creater/github-research-podcast/skills/github-research-podcast Skill

    1★ repo

    Research one GitHub repository from primary sources and turn the verified findings into a Chinese two-speaker podcast script and audio episode. Use when the user asks to track GitHub trends, discover or evaluate a repository, explain a project, maintain daily GitHub research, create a repo-to-podcast episode, or run the complete repository research-to-audio workflow.

  • Let him grill

    pengusto/let-him-grill Skill

    1★

    Stress-test a plan or design with project evidence, triage decisions and their options, automatically resolve reversible low-risk choices, and pause at genuine human decision gates. Supports compact text-first and visual persistent-tree modes. Use when the user invokes interactive or autonomous Grill with Docs, wants fewer step-by-step interruptions, asks to explore branches until human judgment is required, or wants to revisit earlier recommendations.

  • Clean git branches

    lilabrooks/lila-agent-skills/skills/clean-git-branches Skill

    1★ repo

    Audit and safely clean local and remote Git branches, especially after merged pull requests, squash merges, stale remote-tracking refs, or branch drift. Use when asked which branches are stale or safe to delete, to prune or delete merged branches, to reconcile local and remote branch pointers, or to confirm that the default branch and its upstream point to the same commit.

  • Explain my own code

    khaichonggg/explain-my-own-code Skill

    no license1★

    Agent Skill for teaching learners how their existing code actually works.

    The same file is in 1 other repository

  • Change with contracts

    nicolasapr/contract-tree/skills/change-with-contracts Skill

    1★ repo

    Use when about to change code in a repo that has a contract tree. Locates the affected module via `.contract-tree/tree.md`, classifies whether the change touches the module boundary, computes the downstream blast radius, and requires an explicit preserve-vs-cascade decision from the user before touching boundary-affecting code.

  • Skill

    Odinary-AI/ai-system-engineer-skill/skill Skill

    1★ repo

    Use as a proportional lifecycle control layer for AI-assisted system development when Greenfield or existing system work crosses product intent, architecture, authority, lifecycle, cross-module implementation planning, validation claims, system refactoring, migration, recovery, or release boundaries. Do not use for routine coding, mechanical local refactors, or a single prompt unless they expose a system-level boundary or claim.

  • Glw

    Aver005/gitlab-worker/skills/glw Skill

    no license1★ repo

    Operate the `glw` GitLab work-items CLI to manage issues/work items from natural-language requests: create/view/update/close/reopen issues, set status/assignee/labels/weight/dates, add comments, track time (estimate/spend), search and bulk-edit by filter, and switch projects. Use whenever the user wants to manage GitLab issues or work items, create/update/ close issues, do time tracking, run bulk issue operations, or explicitly says "через glw" / "using glw".

  • Bad skill

    YogiAdhik/skillcheck/test/fixtures/bad-skill Skill

    1★ repo

    tests for your agent skills — lint free, behavioral runs against the real agent

  • Discover project skills

    laojin1900/365Skill/skills/discover-project-skills Skill

    1★ repo

    Discover, inventory, summarize, audit, and extract reusable Agent Skills from the current repository. Use when users ask what skills a project has, want a project skill map, need to identify reusable workflows or domain knowledge, want to audit existing SKILL.md files, or ask to turn proven practices into portable skills. 中文:发现、盘点、总结、审计并提炼当前仓库中的可复用技能;当用户询问项目已有技能、需要项目技能地图、希望识别可复用流程或把成熟实践沉淀成标准技能时使用。

  • Writing gpt 5 6 prompts

    CodingCossack/writing-gpt-5-6-prompts Skill

    1★

    Use when creating, rewriting, optimising, reviewing, or handing off prompts, system prompts, developer instructions, agent briefs, delegation prompts, task specifications, or reusable prompt templates for GPT-5.5 or GPT-5.6, especially when wording is procedural, repetitive, over-scaffolded, vague about success, or unclear about evidence, autonomy, tools, validation, output, or stopping.

  • App sdlc

    ivopogace/skills/skills/app-sdlc Skill

    1★ repo

    This skill should be used when adopting a disciplined SDLC on a project (first act — the tooling-map onboarding interview), or when starting or continuing feature work in a repo that has adopted app-sdlc — refining a fuzzy idea, creating or picking up a ticket, planning or implementing a change, reacting to CI or quality-gate findings, opening or merging a PR, documenting a merged ticket, or preparing a release. Also use when the user asks how we work in this repo.

  • Visual companion

    socekin/Visual-Companion/skills/visual-companion Skill

    no license1★ repo

    Use when a discussion involves visual questions — mockups, layout or style comparisons, diagrams, visual hierarchy — that are better shown in a live browser than described in text.

  • Refine prompt

    basuev/pi-prompt-refiner/skills/refine-prompt Skill

    1★ repo

    Refines a rough prompt into a precise, ready-to-send Codex prompt. Use when the user asks to refine, improve, rewrite, optimize, or make a prompt more effective.

  • Readme skill

    loveranmar/readme-skill/skills/readme-skill Skill

    1★ repo

    Design and write beautiful, professional README.md files for any repo or project. Use this whenever the user asks to create, write, improve, redesign, or polish a README or project documentation page — including casual asks like "add a readme", "document this project", "make my repo look presentable", "my readme sucks", or when they're about to publish/open-source a project that lacks a proper README.

  • Chatgpt

    sheepxux/SuperLoop/adapters/chatgpt Skill

    1★ repo

    Design, review, and advise on SuperLoop workflows (loop.yaml specs, fixed Work Plans, run logs, evaluator evidence). Use when the user wants to create or improve a recurring or finite long-horizon agent loop from an environment that cannot execute it.

  • Accessibility

    Deadlymind/nanolama/skills/accessibility Skill

    1★ repo

    Builds WCAG 2.2 AA accessible React UI on shadcn/Radix primitives — keyboard operability with a visible focus ring, dialog focus trap and restore, labelled form fields wired to aria-describedby errors, token-based color contrast, and Arabic RTL mirroring. Use when adding or reviewing an interactive component, an icon-only button, a dialog or menu, a form field's error wiring, or a keyboard/focus/contrast/screen-reader fix, and when making a screen work in RTL. Not for translation plumbing or bidi text setup (see i18n-rtl) or design-token definition (see tailwind-shadcn).

  • Httrack cloner skill

    Redux0223/httrack-cloner-skill Skill

    1★

    Use when an authorized website URL or HTTrack mirror must become an editable local React and TanStack Router project without automatic external runtime dependencies.

  • Ai council

    alidevai/chiron_agent/.claude/skills/ai-council Skill

    no license1★ repo

    Claude bir problemde TAKILDIGINDA diger AI modellerinden fikir/ikinci gorus alma proseduru. Ayni hata iki kez tekrarladiginda, bir yaklasim tikandiginda, zor bir tasarim/mimari karari verilirken ya da kullanici "en iyi yaklasim/baska fikir/farkli acidan bak" dediginde uygulanir. Ana beyin Claude kalir; kurul yalnizca GEREKTIGINDE danisilir (her gorevde degil). Ek saglayici anahtari yoksa Claude tek basina devam eder.

  • Shooting athlete multiagent system Skills

    shuhaolin63-hash/shooting-athlete-multiagent-system-Skills Skill

    1★

    10米气步枪射击训练多智能体系统,涵盖动作要领、室内外场景区分、体能/心理/恢复训练、保障团队架构、学术论文支撑。当用户提到射击训练、气步枪、10米气步枪、射击技巧、射击评分、射击体能、射击心理、射击团队、射击装备时触发。

  • App best practices

    kopon1/app-best-practices/skills/app-best-practices Skill

    1★ repo

    Checklists for the expected-but-forgotten parts of any app — CRUD flows, destructive-action confirmations, undo/redo, loading and cursor feedback, empty and error states, forms, tables, settings pages, import/export, AI chat UI and response parsing, auth and permissions, routing and redirects, page/header anatomy, visual design and spacing, microcopy, performance, security, payments, email and notifications, legal/consent, and i18n. Use in BUILD mode when implementing any user-facing feature (a table, a form, a delete button, a header, a settings screen, an AI panel, a checkout, an importer) so nothing obvious is missed, and in AUDIT mode when asked to review a screen/flow/app for missing states, rough edges, "what's missing here", "make this feel finished/production-ready", or a UX/quality pass. Framework-agnostic.

  • Clean skill python

    RudrenduPaul/skillguard/examples/clean-skill-python Skill

    1★ repo

    A second minimal, well-behaved fixture skill (Python hook) used to test SkillGuard's happy path (zero findings, exit code 0).

  • Project code study

    1bkunnn-cyber/project-code-study Skill

    1★

    This skill should be used when a user asks to study a software or ML repository step by step, "按调用顺序读源码", "逐个类/函数学习", connect code with a paper, trace tensor shapes, reproduce or modify a project, preserve questions across sessions, or discover related methods and extension ideas.

  • Find unknown

    Odinary-AI/find-unknown/skills/find-unknown Skill

    1★ repo

    Use when the user explicitly asks for a blindspot scan, unknowns preflight, 发现未知, or omissions and assumptions that could change direction; also use before a high-cost or hard-to-reverse decision when a material unknown remains. Do not use for routine execution, factual lookup, or speed-first requests.

  • Card schema

    ljf06853/keepfire/.claude/skills/card-schema Skill

    1★ repo

    The recipe-card Markdown and frontmatter format is a parser contract. Read this before changing card structure, headings, frontmatter fields, or the render/parse functions in src/store.ts — a mismatch silently corrupts every card in the user's library.

  • Task Compass Skill

    RTPI-ltc/Task-Compass-Skill Skill

    1★

    Classify agent tasks into a planner profile, execution tools, safety policy, model tier, context policy, and next action. Use when deciding how a task should be planned or delegated, selecting CLI, file, mobile GUI, mobile CLI, MCP, or deployment executors, determining whether to continue, replan, refuse, or await human approval, or evaluating routing behavior across benchmark tasks.

  • Scholarship strategy report

    piyushomanwar16/scholarship-strategy-report-skill/skills/scholarship-strategy-report Skill

    1★ repo

    Produces a professional, consulting-style scholarship / study-abroad strategy report PDF for an applicant. Use when a user wants a personalized scholarship report, a study-abroad strategy, ranked funding combinations, or to compare their profile against past recipients and receive a charted PDF. The skill gathers the applicant profile and preferences through a structured questionnaire, performs the analysis including political and geopolitical risk and benchmark comparisons, and renders a polished PDF with tables, radar charts and bar charts using the bundled Python generator.

  • Evolve ai instructions

    tardis-labs/agent-instruction-kit/skills/evolve-ai-instructions Skill

    1★ repo

    Improve AI skills, rules, prompts, agent instructions, and reusable development workflows from observed sessions, reviews, incidents, or evaluations. Use when repeated agent behavior suggests an instruction should be created or revised, when a proposed instruction change needs evidence and regression testing, or when an accepted change must be versioned, approved, promoted, or rolled back without binding the workflow to a project, stack, architecture, model, or agent vendor.

  • Blindspot audit

    MJL-ren/blindspot-audit/plugins/blindspot-audit/skills/blindspot-audit Skill

    1★ repo

    Project-level blind spot audits and consent-gated BLINDSPOT_LEDGER.md triage. Use when the owner asks to find unknown unknowns, overlooked risks, missing decisions, stale assumptions, or readiness and health gaps beyond their checklist; during unfamiliar-domain planning, cross-project sanity checks, or post-implementation review; and when they ask in any language to organize, close, process, decide, or go through existing ledger rows. For ledger cleanup, collect owner choices before changing awareness, status, decisions, or archives. Do not trigger for routine bug fixes, ordinary code review, formatting, or implementation-only work unless the owner also asks what may be missing or wants the blindspot ledger handled. Works across software, games, writing, research, content, and business projects.

  • Prove it

    loyalmemories/prove-it/skills/prove-it Skill

    1★ repo

    Require concrete, task-relevant evidence before declaring coding work complete. Use when implementing, fixing, refactoring, migrating, reviewing, or preparing software for release; when a user asks to verify, validate, test, prove, double-check, or show that a change works; or when completion claims should be backed by tests, builds, static checks, runtime checks, screenshots, or other observable results. Apply to code and configuration changes across ecosystems, including agent-authored work. Do not use evidence from an earlier revision as proof of the current revision.

  • Business idea evaluation

    gordonling-labs/skills/skills/business-idea-evaluation Skill

    1★ repo

    Critically evaluates business ideas, startup concepts, product directions, and market-entry plans using market, competition, business-model, unit-economics, execution-risk, and validation lenses. Use when a user asks whether an idea is viable, requests a neutral critique or stress test, compares opportunities, or says "should I build this?", "評估這個商業想法", or "分析這個創業點子". Produces steelmanned arguments for and against, labeled assumptions, a scored rubric, concrete validation tests, and a calibrated verdict. Do not invoke for standalone idea brainstorming, business-plan writing for an already approved concept, technology-stack selection after the product decision, or specific contract advice without a business evaluation. When a business-evaluation request also asks for personalized investment allocation, specific legal advice, or illegal optimization, invoke only to apply the boundary and redirect safely; do not provide that advice.

  • Developing with agentsquire

    TacoTakumi/AgentSquire/src/agentsquire/skills/developing-with-agentsquire Skill

    1★ repo

    Use when building a Python CLI that carries its own Agent Skills with agentsquire - wiring the skills subcommand group, the staleness notice, console entry points, and package-data layout into a consumer package.

  • Opencode commander

    stone623101-cloud/opencode-commander/plugins/opencode-commander/skills/opencode-commander Skill

    1★ repo

    Orchestrate multiple OpenCode CLI workers from Codex, Claude Code, Cursor, or another coding agent. Use when the user explicitly asks to split a complex research, analysis, planning, review, or implementation task across OpenCode agents; requests parallel OpenCode execution; wants iTerm split-pane visibility; or asks the host agent to act as the overall coordinator and synthesize worker results.