Loading…
Showing 5311–5340 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| vibe-workstream-orchestrationash1794/vibe-engineeringRuns a multi-phase project from an orchestrating main thread that plans, routes and verifies but does not build. Defines a few long-lived workstreams, each owning a file area end to end in its own worktree, and routes every follow-up to the owning agent instead of spawning a one-off. Covers base-SHA recording, rebase-before-commit, stale-checkout detection, and shared-machine hygiene (ports, processes, measurement noise). Use when a project spans several phases or sessions with three or more agents working at once. | Stars: 163 | Updated | Claude CodeCodex | Verified | Install |
| wrap-agent-skillValentinNikolaev/agent-skillsImport, recover, normalize, or sync reusable skills into canonical sources and generated copies; not project memory. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| apollo-operatorcreatop-gtm/apollo-operatorThe four ways to run Apollo headless and how to choose: MCP (typed tools, results always through context), the apollo CLI binary (disk output, common filters), REST authenticated with the CLI's own OAuth token (full MCP filter surface WITH disk output, no API key), and REST with an API key. Includes measured context costs, credit costs per lane, verified command recipes, and the kill switch for stopping a live sequence. Use to decide which lane a task should run on. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| business-briefcreatop-gtm/apollo-operatorBuild one readable brief.md capturing the business: identity, offer, who buys and why, objections, proof, and voice. The narrative context layer every other skill reads. Use before ICP work, when copy comes out generic, or when the business changes. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| operator-contextcreatop-gtm/apollo-operatorOperator context for running B2B outbound on Apollo.io through the Apollo MCP. Load this first. Provides the Apollo tool map, universal deliverability and copy rules, the shared profile.yaml object, and routing to every other Apollo Operator skill. Use for any outbound task on Apollo: targeting, list building, sequences, deliverability, sending, or iteration. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| ineedsilencekishormorol/ineedsilencePut a paper or other document in front of a panel of independent AI judges from different vendors (by default Claude, GPT through Codex and Gemini through Antigravity; any number, and DeepSeek, Kimi, Qwen or a local model can be added), have each find its problems alone, merge and fix what they find, let them argue out their disagreements, and repeat until every judge signs off on the same unchanged text. Use when the user calls /ineedsilence, and whenever they want a draft checked by several models before it goes out — "run the three judges", "get Codex and Gemini to review this too", "I want all three to agree", "panel review", "make this paper bulletproof", "red-team my paper", "pre-submission check with GPT and Gemini", "cross-check with other models", or asks for a green signal on a draft. Also for proposals, rebuttals, reports and agent skills they want hardened the same way. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| writing-for-agentsVincent-the-gamer/skillsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| pm-career-coachkonglong87/superPMPM Career Coach — guides product managers through career transitions, skill development, and growth planning Use when: Planning your PM career path, preparing for promotion, navigating role transitions, or seeking career advice | Stars: 95 | Updated | Claude CodeCodex | Verified | Install |
| customer-followupZenUml/conf-appPrioritise Confluence customers for conversion, retention, win-back or pause using lifecycle, feedback, license, usage and conversation evidence. Draft follow-ups and update the tracker within the user's authorised scope; reuse existing query skills. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| x9-agent-instructionsxonika9/agent-skillsWrite or review prompts, task briefs, and agent-instruction files — «напиши промпт», «проверь инструкции», "review this agent prompt". Do not use as the primary workflow for repository onboarding files, skill authoring, ordinary prose, or executing or delegating the described task. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| x9-codex-imagegenxonika9/agent-skillsUse when an agent outside Codex, such as Claude Code or OpenCode on any model, should generate or edit a raster image through the user's Codex subscription — «сгенерируй картинку через Codex», «нарисуй иллюстрацию», "generate an image with Codex". Do not use inside a Codex session, where Codex's own imagegen skill applies, or for editable diagrams, crops, resizes, or other edits made locally without generation, or delegating non-image work to Codex. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| caveman-helpZenUml/conf-appQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman". | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| auto-laneZenUml/conf-appDecide whether an agent session may merge a PR on ZenUml/conf-app without asking (non-destructive rule), and operate the daily auto-lane merge job (classify a diff, dry run, backtest, kill switch). Use when a PR is green and the next step is "merge or ask", when asked "can this be auto-merged", "why did the auto lane skip PR N", "run the auto-lane dry run", "自动合并", "非破坏性", or before proposing any automation that merges. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| client-healthZenUml/conf-appRank active ZenUML Lite tenants on two independent 0-100 scores — Opportunity (upsell candidate) and Risk (disengagement) — to decide which clients to focus on. Use whenever the user asks "which clients should we focus on", "who's a good upsell candidate", "which tenants are at risk of churning", "health score", or wants a ranked list of Lite tenants by engagement strength or fragility. Scope: Lite only, active tenants only (macro_viewed > 0 in the scoring window). For a SINGLE named tenant's paid status/profile use the `tenant` skill instead; for lifetime revenue/renewals/overdue payers use `marketplace`. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| find-macros-on-pageZenUml/conf-appList ZenUML (and other) macros on any Confluence page in render order, with their customContentId, type, title, and ADF localId — and fetch a chosen macro's stored body (DrawIO XML / Mermaid / PlantUML / ZenUML DSL / OpenAPI). Two operations, one skill. Use whenever investigating a customer page, locating which macro to inspect/reproduce, correlating "the third diagram on page X" to a specific customContentId, or extracting a stored macro source for rebuild. Triggers on "what macros are on this page", "find the macro at <URL>", "fetch the macro source", "extract macro XML", "rebuild this customer's macro", or any starting step of a customer-page investigation. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| telegram-connecttonydzi/telegram-mcp-kitConnect your Telegram to Claude Code and Codex with a shared MCP server and a separate Telethon worker; verify both rails, protect sessions and repair reconnect failures. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| workflow-routingMinLeeV5/devkeel当已获授权的普通开发请求无法直接判定 Direct、Lite 或 Full,或实施中出现持久化与治理升级信号时使用;明确 Direct 或已由专项 skill 接管的请求不加载。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| git-prpappcorn/universeOpen a pull request from the current branch against the repo's base branch, and leave the working checkout free by moving the PR into its own worktree. Three independent guards make pushing to a protected branch impossible; if the user is standing on one with work in progress, it branches off first instead of refusing. Delegates to the `commit` skill when the tree is dirty, composes title and body from the commits (what changed, why, how to check it), assigns the author, and requests the changed paths' CODEOWNERS as reviewers. Never force-pushes, never merges. Use when the user says "open a PR", "PR this", "ship this branch", "abre el PR", "create the pull request", or finishes a branch and wants it up for review. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| worktreepappcorn/universeCreate, list, and remove git worktrees so several branches can be open at once without anyone switching a branch out from under anyone else — the default way to work when agents and humans share a repository. Modes: a new branch in its own checkout, an existing PR checked out for review, list, remove, prune. Worktrees land in a sibling directory, each with its own dependencies and its own local config, copied rather than symlinked. Backed by a zero-dep Node script. Use when the user says "worktree", "check out that PR locally", "work on two branches at once", "haz un worktree", "spin up a branch in parallel", or needs the current checkout free without losing what is in it. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ecosim-pftpar-extractorbioepic-data/ecosim-agentExtract one EcoSIM PFT parameter record from a PFT-parameter NetCDF file into a standalone NetCDF. Use when Codex needs to isolate all parameters for a given EcoSIM six-character PFT code such as ndlf34, or a four-character pfts_short value plus Koppen climate code, while preserving all non-PFT-specific variables such as pfts_short, pfts_long, and Koppen metadata. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| ecosim-trait-deriverbioepic-data/ecosim-agentUse this skill when deriving EcoSIM plant trait parameter recommendations for a named plant from web and online literature evidence, using a read-only `plant_trait.*.desc` file and the `ndlf43` tree block or `gr3s43` grass block as the starting archetype. Never edit or replace the `.desc` file. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| koppen-climate-codecbioepic-data/ecosim-agentUse this skill when you need to derive a Koppen-Geiger climate label from input latitude and longitude, then convert between the letter code such as `Csa` and the EcoSIM-style numeric code such as `34`. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| paper-site-ecosim-workflowbioepic-data/ecosim-agentExtract study sites, observational variables, coordinates, climate-forcing sources, and cited data sources from ecosystem-modeling papers, PDFs, supplements, or article text, then plan or create EcoSIM simulation workflows and run folders for those sites. Use when Codex is asked to read a paper for EcoSIM feasibility, including requests phrased as "read paper for ecosim feasibility"; read a paper for sites/data availability; reproduce a published site simulation in EcoSIM; compare EcoSIM outputs to paper observations; or convert paper-derived AmeriFlux, FLUXNET, US NLDAS-domain, non-US ERA5, crop, peatland, forest, grassland, wetland, or unmanaged field-site information into EcoSIM inputs and runnable cases. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| ssp-ghg-atmgas-generatorbioepic-data/ecosim-agentBuild EcoSIM atmospheric greenhouse-gas forcing files by combining a historical monthly atmgas NetCDF with RCMIP/CMIP6 SSP concentration pathways. Use when Codex needs SSP245/SSP585 or other SSP atmospheric CO2, CH4, and N2O concentrations, key-year tables, or scenario NetCDF files spanning historical years through 2100 for EcoSIM or related biogeochemical forcing workflows. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| common-quality-gatelihaozheCharlie/the-way-here验证 wiki 或 Skill 修改是否满足证据、归档、前置元数据、生成索引安全、链接和完成标准;纯健康检查保持只读。 | Stars: 154 | Updated | Claude CodeCodex | Verified | Install |
| c4-level1-contextkinhluan/skillsSpecialized in System Context diagrams (Level 1) with User Journey integration. Use this skill when the user requests high-level architecture, business value mapping, identifying system scope, or describing interactions between stakeholders and external systems. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| collaborative-engineering-agentkinhluan/skillsCoordinate a bounded software change from intent through implementation, review, and verification while preserving user ownership and repository conventions. Use for multi-step engineering delivery, task breakdown, cross-discipline risk review, or preparing issue/PR artifacts. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| federated-learning-dqnkinhluan/skillsFederated learning with Deep Q-Networks for privacy-preserving optimization. Domain-specific skill — only route when user explicitly mentions federated learning, FL, DQN, or privacy-preserving distributed RL. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| kinhluan-routerkinhluan/skillsSelect the smallest set of relevant skills from the kinhluan collection. Use when the user asks to choose a skill, several domains overlap, or the correct specialist is unclear; route from current intent and evidence without forcing a universal workflow sequence. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| pasturekinhluan/skillsWork well inside pasture, a macOS setup that runs several coding agents (Claude Code, Codex, Grok, Antigravity) side by side under herdr. Use when HERDR_ENV=1 or pasture-* commands exist, or when the user mentions pasture, herdr, the collie, parallel agents, pasture-task, pasture-duo, worktrees, Sapling stacks, agent-browser or agent-desktop; it maps each kind of task to the pasture tool and states the shared rules. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |