Engineering
98,246 rows, by stacks then stars
silbercue/SilbercueSwift/io.github.silbercue/silbercueswift MCP server
10★ repoFastest iOS MCP server. 40 tools: xcresult parsing, WDA automation, 0.3s screenshots.
nonlinear-xyz/factory-kit/skills/factory-api-route-engineer Skill
9★ repoUse when designing or implementing API endpoints — server actions, tRPC procedures, REST routes for external consumers. Carries the factory's API conventions — the server actions vs tRPC decision, procedure tier stacking, per-mutation Zod schemas, central router composition with manual registration, pagination (limit/offset/orderBy default; cursor only when needed), multi-field search via `ilike` + `or()`, aggregated stats in list queries, mutation lifecycle hooks, stale-time defaults, custom error class taxonomy, fetch adapter for tRPC in App Router. Outputs endpoints that fit the house style — not bespoke per-route handlers.
axel-pm/watch-n-learn/skills/watch-and-learn Skill
9★ repoWatch a how-to / tutorial / demo video and turn the procedure it teaches into one or more working Claude Code skills. Use when the user wants to "turn this video into a skill", "watch this tutorial and make a skill", "learn how to do X from this video", "build a skill from this screencast/demo/talk", or capture a repeatable workflow shown in a video. Sends an agent to watch the video (local file or URL) with a local, free, no-API toolchain, breaks the procedure down, authors the skill(s), and verifies they actually work.
yamanidev/claude-code-configuration/skills/devops Skill
9★ repoMentorship workflow for conceptual DevOps and infrastructure questions, design discussions, tool selection, deployment strategy, observability planning, and troubleshooting production systems. Covers cloud, CI/CD, Kubernetes, Terraform, monitoring, incidents, and SRE topics, calibrated to teach the why alongside the what. NOT for application code changes (use /ship) or code review (use /review-code).
oharu121/skills/skills/release Skill
no license9★ repoCreate a GitHub issue, commit, tag, and push a release. Detects repo type and runs mode-specific pre-flight checks with user confirmation at every step.
The same file is in 2 other repositories
vanara-agents/skills/skills/caching-strategies Skill
9★ repoDeep reference for caching — what to cache, cache-aside vs read/write-through/write-behind, TTLs with jitter, eviction (LRU/LFU/FIFO), invalidation, and surviving stampedes (thundering herd / dogpile). Worked examples and a runnable jitter check.
jiatastic/open-python-skills/skills/error-handling Skill
9★ repoPython error handling patterns for FastAPI, Pydantic, and asyncio. Follows "Let it crash" philosophy - raise exceptions, catch at boundaries. Covers HTTPException, global exception handlers, validation errors, background task failures. Use when: (1) Designing API error responses, (2) Handling RequestValidationError, (3) Managing async exceptions, (4) Preventing stack trace leakage, (5) Designing custom exception hierarchies.
gaelic-ghost/socket/plugins/agent-portability-skills/skills/hermes-agent-compatibility Skill
9★ repoMaintain a clear Socket-to-Hermes compatibility boundary across skills, Codex plugins, MCP configuration, and native Hermes plugins. Use when exporting Socket skills to Hermes or deciding whether an adapter is needed.
duthaho/skillhub/.claude/skills/blueprint Skill
9★ repoHuman-facing documentation, architecture docs, and mermaid diagrams for a codebase, a module, or a feature — "draw me the architecture, with receipts." Fans out read-only sub-agents to build a grounded component graph first: every node is a real path, every edge backed by a grep-verified import or call — unverifiable edges are dropped, not drawn. Diagrams render from that verified table per a fixed checklist (never freehand mermaid), capped at 5–8 top-level components with drill-down pages; every doc section cites its sources as file:line. Drafts in chat, writes docs/blueprint/ only on your yes, and stamps a manifest with date + commit so /blueprint refresh regenerates only what the diff touched. Use for "generate an architecture diagram", "document this codebase or module for people", "create a mermaid diagram of this feature" — e.g. "/blueprint", "/blueprint the payment flow", "/blueprint refresh". For agent-facing orientation (AGENTS.md) use map; blueprint is the human-facing sibling.
sherifabdlnaby/skills/skills/cicd Skill
no license9★ repoUse when setting up, shaping, or auditing a project's CI/CD: a build/test/scan pipeline, a release pipeline, or publishing an artifact (container image, binary, bundle) with signing/attestation. Optionally use the skill to transform a repo's CI/CD to the recommended shape, aka (cicd-fy).
WalterSumbon/claude-agent-sdk-skill/skills/claude-agent-sdk-typescript Skill
9★ repoExpert guidance for building AI agents with the Claude Agent SDK in TypeScript/JavaScript. Use when the user writes TypeScript or JavaScript code with the SDK, imports from "@anthropic-ai/claude-agent-sdk", uses query(), allowedTools, permissionMode, creates custom tools with createSdkMcpServer, sets up hooks, integrates MCP servers, manages sessions, or debugs SDK issues in TypeScript/Node.js. Also triggers on: "@anthropic-ai/claude-agent-sdk", "allowedTools", "permissionMode", "npm install", "for await", "AgentDefinition", or "settingSources".
The same file is in 2 other repositories
ceoimperiumprojects/imperium-brain/skills/api-discovery Skill
no license9★ repoHidden API discovery and intelligence tool. Detects internal APIs, REST/GraphQL endpoints, WebSocket connections, and authentication patterns on any website. Useful for competitive intelligence, integration building, and understanding how SPA applications work under the hood. Triggers on: hidden API, discover APIs, endpoint, SPA, intercept, XHR, fetch requests, websocket, internal API, reverse engineer API, API patterns, API endpoints, API mapping.
Notysoty/openagentskills/skills/agent-context-file-writer Skill
9★ repoWrites a high-quality CLAUDE.md, .cursorrules, or .windsurfrules file that gives a coding agent the right project context, conventions, and constraints to work effectively.
HasData/agent-skills/skills/hasdata Skill
no license9★ repoUse HasData to scrape any public web page, run real-time Google/Bing/Google-AI-Mode search queries, pull structured data from e-commerce, real-estate, lodging, jobs, maps, travel, video, and social platforms, or run async bulk-scraping and crawling jobs without managing proxies, browsers, or captchas. Reach for this skill when the user mentions web scraping, SERP/search results, Google Maps/Trends/Flights/Images, YouTube videos/transcripts/channels, Amazon, Zillow, Redfin, Airbnb, Booking.com hotels, Yelp, Indeed, Glassdoor, Instagram, Shopify, scraper jobs, website crawling, RAG/LLM data ingestion, lead/contact enrichment, or HasData itself.
bcanfield/agentic-tech-debt/claude-code/skills/init Skill
9★ repoWrite or refresh the `## Tech debt operations` section in CLAUDE.md so a team shares one source of truth for debt-ops disciplines and cached quality commands. Idempotent. Only the managed section changes; other sections are untouched. Invoked explicitly via /debt-ops:init (solo users get the same content from the SessionStart inject).
longligooo/pdf-to-editable-word-skill/src/pdf_to_editable_word/bundled_skill Skill
9★ repoConvert PDF to Word or PDF to DOCX while preserving the original page layout and keeping text editable, searchable, and selectable. Use for PDF-to-Word conversion, editable DOCX creation, fixed-layout documents, table-heavy PDFs, vertical text, resumable long-document conversion, or output validation. Works as a portable Agent Skill for Codex, Claude Code, and other agents that can run the CLI. Do not use for scanned PDFs without a text layer unless OCR is available.
The same file is in 1 other repository
mouadja02/skills/skills/agent-design/agent-owasp-compliance Skill
no license9★ repoCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/007 Skill
9★ repoSecurity audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
The same file is in 1 other repository
wcgomes/agents-workspace/templates/skills/skill-builder Skill
no license9★ repoCreate, refine, and validate Agent Skills following the agentskills.io specification. Use when writing a SKILL.md, creating a new skill directory, improving an existing skill's triggering or content, running evals, or diagnosing why a skill isn't activating.
figitaki/reviews/skills/using-reviews-locally Skill
9★ repoRun and use the Reviews app locally, including server startup, port checks, local token setup, CLI config, pushing local reviews or new patchsets, and Codex workflow conventions. Use when the user asks to spin up Reviews, push a local review packet or revision, mint/access local API tokens, debug localhost review pushes, or install repo-local Reviews skills by symlink.
samzong/agent-brains/agents/dify-rag-pm/skills/dify-rag-pm Skill
9★ repoAnalyze, plan, design, and review Dify Dataset, Knowledge, and RAG product work. Use for Dataset lifecycle, Workflow Knowledge Retrieval nodes, field contracts, user stories, and KnowledgeFS-to-Dify product translation.
Phantomlau3674/ai-film-director-workbench/skills/ai-video-prompt-generator Skill
9★ repoGenerate AI video prompts from clean structured prompt specs, validate prompt specs, run an isolated OpenAI-based prompt generator, and lint prompt outputs for viewpoint, action, reference, dialogue, negative prompt, audio prompt, safety tags, and legacy-contamination failures. Use when producing or repairing Flow/Veo/Omni/Runway/Kling/Dreamina-ready shot prompts from project data.
oghie/skillsets/skills/android-offsec Skill
9★ repoAndroid device offensive security, forensic extraction, and mobile app exploitation. Use this whenever the user needs to: break into or bypass the lock screen of an Android phone, extract data from a seized Android device for evidence, analyze or reverse-engineer an APK to find vulnerabilities, intercept communications on an Android device, exploit Android apps via deeplinks, steal crypto wallets or app data, set up rogue WiFi to target a phone, or plan any mobile device investigation or penetration test. Also trigger when the user mentions Android forensics, mobile pentesting, law enforcement phone extraction, device exploitation, WhatsApp or Telegram extraction from a phone, Android app reversing, CVE research for Android, or needing a chain of custody for mobile evidence. Even if the user describes the scenario casually or in another language, if they need to gain access to or pull data from an Android phone, use this skill.
Montimage/skills/skills/devops-pipeline Skill
9★ repoImplement pre-commit hooks and GitHub Actions for quality assurance. Use when asked to "setup CI/CD", "add pre-commit hooks", "create GitHub Actions", "setup quality gates", "automate testing", "add linting to CI", "setup code quality checks", "configure CI pipeline", "add automated checks", or any DevOps automation for code quality. Detects project type and configures appropriate tools. Trigger this skill whenever the user mentions CI, CD, pre-commit, GitHub Actions, linting automation, or quality gates — even if they don't use those exact terms.
sapiom/skills/skills/sapiom-deploy Skill
9★ repoDeploy and run code on Sapiom — scheduled jobs, batch execution, sandboxes. Use when user says "deploy this", "ship it", "run this on a schedule", "put this on a cron", "run these tasks in parallel", "spin up a server", "I need a dev environment", or already has a script and wants it running in the cloud.
sangmin7648/tacit/skills/tacit.memorize Skill
no license9★ repoSummarize the current session and save it to the tacit knowledge base (~/.tacit/memory/). TRIGGER when: the user invokes /tacit.memorize, wants to save the current conversation to memory, or asks to record what was discussed. DO NOT TRIGGER for: querying existing knowledge (use /tacit.knowledge instead).
risingwavelabs/agent-skills/skills/risingwave Skill
no license9★ repoUse when working with RisingWave — streaming SQL database, materialized views, sources, sinks, CDC from PostgreSQL/MySQL, Kafka ingestion, time windows (TUMBLE/HOP/SESSION), watermarks, EMIT ON WINDOW CLOSE, port 4566, risingwave-mcp, event streaming pipeline design, real-time analytics, stream processing
The same file is in 1 other repository
psenger/ai-agent-skills/.claude/skills/release Skill
9★ repoShips completed work in the ai-agent-skills repository. Two phases depending on context: WRAP UP (on a feature branch with committed work — updates CHANGELOG, README, marketplace.json, commits, pushes, creates a PR) and CUT RELEASE (on main after a merge — determines semver bump, updates CHANGELOG version section, tags, pushes, creates a GitHub draft release). Use when the user says "ship this", "I'm done", "create a PR", "cut a release", "tag a release", "wrap this up", or "release it". Always checks GitHub auth first. Load the `conventions` skill for commit and PR formatting rules.
The same file is in 1 other repository
navveenb/lean-agentic-ai/lean-agentic-ai-claude-implementation/.claude/skills/bloat-detector Skill
no license9★ repoDetect the 7 types of agentic bloat in a codebase or system design
Lenny Rachitsky Podcast Transcripts MCP Server
la-rebelion/hapimcp/ai.com.mcp/lenny-rachitsky-podcast MCP server
9★ repoMCP server for structured access to Lenny Rachitsky podcast transcripts. For content creators.
HewlettPackard/gl-mcp/io.github.HewlettPackard/greenlake-devices-mcp MCP server
9★ repoHPE GreenLake devices MCP Server
cherchyk/MCPBrowser/io.github.cherchyk/mcpbrowser MCP server
9★ repoBrowser automation using the user's Chromium session — JS execution, auth, and anti-bot support.
scopeblind/scopeblind-gateway/io.github.tomjwxf/protect-mcp MCP server
9★ repoSigned receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
vivid-money/vivid-mcp/io.github.vivid-money/vivid-mcp MCP server
9★ repoOpen a Vivid Business account from your AI chat via MCP.
nelson820125/iforgeai/copilot/skills/dba-designer Skill
8★ repoDatabase Architect / DBA role skill. Use when you need to design database schemas, performance strategies, security design, or data model reviews. Keywords: database design, schema design, table structure, index design, performance optimisation, data security, data integrity, ER diagram, database standards.
QBall-Inc/the-bulwark/skills/assertion-patterns Skill
8★ repoReal output verification vs mock calls. Use when transforming T1-T4 violating tests to verify observable behavior.
Victory-7291/project-scaffold-setup-skills/skills/cpp-project-setup Skill
8★ repoModern C++ project setup: CMake/CMakePresets, vcpkg, Ninja, VS Code/clangd, GoogleTest, clang-format/tidy, Doxygen, CI, macOS/Linux/Windows. Use for bootstrapping or modernizing host-side C++ apps and libraries; prefer embedded-project-setup for MCU firmware and cross-debug flows.
Pyroxin/opinionated-claude-skills/opinionated-apple-development/skills/swift-programmer Skill
8★ repoSwift-specific idioms, tooling, and philosophy. Use when working with Swift code. Emphasizes protocol-oriented programming, value semantics, strict concurrency (Swift 6+), and compile-time safety guarantees.
The same file is in 2 other repositories
aakashdhar/vibe-skill/vibe-agent Skill
no license8★ repoStandalone agentic architecture skill. Designs complete multi-agent AI systems from scratch — no other vibe-* skills required. Deep knowledge of LangGraph, LangChain, CrewAI, AutoGen, Vercel AI SDK, and custom implementations. Produces AGENT_ARCH.md covering pattern selection, agent roles, tool mapping, state design, HITL checkpoints, VerifierAgent rubrics, implementation order, stack recommendations, and boilerplate folder structure. Generates both an interactive inline topology diagram and an exportable static SVG. Triggers on "agent:" prefix, "design an agent system", "I want to build an agent", "multi-agent pipeline", "orchestrator and sub-agents", "agentic workflow", "which agent framework should I use", "how do I structure my agents", "build a workflow with AI agents", "human in the loop", "LangGraph architecture". Always use when designing any system involving AI agents — standalone, no dependencies.
JasonWarrenUK/goblin-mode/skills/artefact-introduction Skill
no license8★ repo{{ 𝛀𝛀𝛀 }} Render a visual HTML introduction to this codebase for a newly-joined developer
Neetx/ai-security-research-radar/.claude/skills/radar-lab-sweep Skill
no license8★ repoSweep the primary security feeds — vendor/lab red-team & security blogs, research venues, and advisory feeds — on EVERY daily run (not rotated) so no attack-technique, red-team tool release, or disclosure is missed. Prefer RSS/Atom over HTML to survive JavaScript-rendered indexes. Use at the start of every daily scan, before the rotating exploration slot.
vanducng/skills/skills/apidesign Skill
8★ repoDesign stable, hard-to-misuse interfaces - REST/GraphQL endpoints, module boundaries, type contracts, component props, anything where one piece of code talks to another. Use at design time, before implementing the surface. Triggers: 'design this API', 'API contract', 'endpoint design', 'module boundary', 'interface design', 'should this be one endpoint or two', 'how should this API look'.
mollyretter/forward-deployed-engineer-toolkit/skills/panel-review Skill
8★ repoMulti-agent panel review of a PR or current-branch diff. Three-model fan-out across Opus, Sonnet, and Haiku. Opus and Sonnet review for regressions, security issues, and bugs; Haiku reviews convention drift, naming, dead code, and comment quality. Discrete severity levels (nit, question, blocker). Sonnet confidence recheck plus draft polish merged into one pass. Dev approval gate before posting via gh pr review. Worktree-isolated. Build log committed to docs/build-logs/panel-review-pr-N.md.
anmolnagpal/devops-skills/skills/appsec Skill
8★ repoApplication-level security review: dependency manifests for known-vulnerable packages, missing HTTP security headers, permissive CORS configuration. Use when user says 'review my dependencies', 'check for vulnerable packages', 'run a dependency audit', 'audit security headers', 'review CORS config', or when working in package.json/package-lock.json, go.mod/go.sum, requirements.txt/poetry.lock, Gemfile.lock, Cargo.toml/Cargo.lock, pom.xml, or server/app config with CORS or header middleware.
Dev869/swift-tothemax/skills/apple-dev-conductor Skill
8★ repoOrchestrator for the swift-tothemax plugin — routes any Apple-platform development task (building an iOS/macOS app, adding a feature, preparing a release, fixing a rejection) to the right combination of skills in the correct order. Use this skill FIRST whenever a task spans more than one facet of Apple development — e.g. "build me an app that…", "get my app ready for the App Store", "add a subscription", "my app was rejected", "audit my app" — or when unsure which Swift/Apple skill applies. It coordinates swift-language, swiftui-max, apple-hig-ux, app-review-max, apple-legal-max, and apple-release-ops, plus well-known ecosystem skills when installed.
ontology-of-everything/SemanticSkills/skills/huawei-cloud-billing-scout Skill
8★ repoHuawei Cloud BSS billing read-only only (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.
The same file is in 1 other repository
kensaurus/cursor-kenji/skills-cursor/canvas Skill
8★ repoA Cursor Canvas is a live React app the user opens beside the chat. MUST use a canvas for standalone analytical artifacts — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Prefer canvas for MCP tool results (Datadog, Databricks, Linear, Sentry, Slack) over markdown tables or code blocks. MUST also read this skill when creating, editing, or debugging any .canvas.tsx file.
Zhonghao1995/Agentic-MIKE-Plus/skills/mike-params Skill
8★ repoRead and modify MIKE+ model parameters via the mike-plus MCP server — inspect or change values in any model table (pipe Diameter/Manning in msm_Link, node levels in msm_Node, catchment properties in msm_Catchment, etc.). Use when an agent must identify a current parameter and change it before re-running. Requires MIKE+ + license; mutating tools must run on a copy.
mcmespinaa/folder-structure-protocol/.claude/skills/pipeline-scaffold Skill
no license8★ repoCreates a new ICM pipeline from a domain description. Generates numbered stage folders with CONTEXT.md contracts (Inputs/Process/Outputs), reference and output directories, and a root CONTEXT.md. Use when: setting up a new staged workflow, creating a production pipeline, scaffolding an ICM workspace.
TheColliery/CoalFace/skills/coalface Skill
8★ repoFan-out discipline for swarm work. When a task decomposes into many units (a bulk refactor, a repo-wide sweep, a corpus batch), CoalFace runs it as a disciplined factory: mandatory SCOUT surveys the worksite, deterministic PARTITION merges overlapping/tiny spots, workers return anchor-edit orders as TEXT (propose-not-execute), QC checks scope+spec at collection, main = SINGLE WRITER (pre-swarm snapshot + domain gate), RECEIPT shows tokens-vs-solo. Wallet caps DOLLAR cost at ~solo via cheap tiers (raw tokens run HIGHER — fan-out ×N the per-sub baseline), not raw tokens. Modes: coalfaceMode auto (default, rides the contract at/above autoFanoutFloor units) | on (scout every prompt) | off. Manual "/coalface" or "swarm this" convenes it in any mode except off. Cross-agent (native subagent tool; no fan-out → sequential-pipeline degrade). Disciplines fan-outs that would happen anyway — does not make models smarter or guarantee correctness. Zero-dependency, offline, no API keys.
skills-lock/skil-lock/examples/drift-demo/baseline/.claude/skills/claude-hook-builder Skill
8★ repoScaffold Claude Code hook configs by reading your existing settings and skills.
Matematic mcp fastmcp instructions pl
matematicsolutions/awesome-matematic-skills-pl/dev-mcp/skills/matematic-mcp-fastmcp-instructions-pl Skill
8★ repoPolish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.
stark-ai-de/agent-skills/incubator/skills/engineering-workflows/debugging-diagnosis Skill
8★ repoDiagnose and fix bugs through reproduction, minimization, hypotheses, instrumentation, targeted fixes, and regression coverage. Use when the user reports failing behavior, a broken test, runtime error, flaky workflow, or asks for debugging before implementation.
hamzabellouch/agent-skills/AI API and Agent Platform/agent-platform-deploy Skill
8★ repoDeploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is deployable, query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval` skill).
Karthick-Ramachandran/persist-os/.agents/skills/capture-mcp-context Skill
8★ repoLocal-first CLI that gives your repo durable, AI-ready memory - features, ADRs, modules, architecture, standards & tests and a deterministic doctor that validates health, evidence & drift.
StringKe/std-agent/.agents/skills/commands/release-patch Skill
8★ repo走 stdagent 标准化 patch 发版流程(CI 验证 -> tag -> goreleaser -> 验收) (Invoke when user types /release-patch or asks to run release-patch)
acquia/acquia-skills/skills/acli/codestudio Skill
8★ repoUse when setting up a new Code Studio (GitLab CI/CD) project, changing PHP version in Code Studio builds. NOT for checking pipeline job status — use pipelines-cli-pipeline-operations for that.
The same file is in 1 other repository
tyeongkim/spec-graph/skills/spec-graph Skill
no license8★ repoUse this skill whenever the project uses spec-graph for managing requirements, decisions, phases, changes, interfaces, states, tests, and other semantic entities in a typed graph. Trigger when the user mentions spec-graph, or when the task involves any of: tracking requirements or decisions, planning development phases, analyzing change impact, validating workflow gates, managing entity relationships in a specification graph, or coordinating agent work through structured impact analysis. Also trigger when you see a .spec-graph/ directory in the project, or when the user asks about impact analysis, gap detection, coverage checks, or phase exit criteria. This skill is essential for any phase-based development workflow that uses spec-graph as its semantic operator layer.
vunm-io/passdown/plugins/passdown/skills/passdown-handoff Skill
8★ repoUse when ending or pausing a work session — writes a session handoff log (the "passdown") so the next session or agent resumes cheaply from small files instead of replaying a large transcript
jscraik/Agent-Skills/Infrastructure/references/deferred-skill-context/agent-ops-codex-agent-creator Skill
8★ repoCreate, install, validate, and orchestrate Codex custom subagents as standalone TOMLs with canonical global defaults (`~/dev/configs/codex/agents/{name}/{name}.toml`, `~/dev/configs/codex/config.toml`) plus optional project scope (`${project_root}/.codex/agents/{name}/{name}.toml`), where project config writes occur only when runtime-limit flags are explicitly requested.