Skillz Forge
Skillz Forge is a catalog and review platform for the Skillz ecosystem. It verifies that skill catalog data, accessibility affordances, and release gates stay trustworthy as the root distribution families and the wider Skillz project evolve.
Artifacts in this monorepo
| Artifact | Directory | Purpose |
|---|---|---|
| Skillz Forge | artifacts/forge |
Public-facing catalog browser and review surface for skills. |
| Skillz Forge Review Desk | artifacts/forge-review-desk |
Standalone review workspace for auditing skill submissions. |
| API Server | artifacts/api-server |
Shared backend API used by the Forge artifacts. |
| Canvas / Mockup Sandbox | artifacts/mockup-sandbox |
Component preview sandbox for design iteration. |
Validation & release gates
Reusable validators live under .agents/skills/ and are wired into
.github/workflows/release-validation.yml on pushes and pull requests:
catalog-integrity— rebuilds and checks catalog truth/provenance without credentials.production-build-verification— builds the standalone Forge artifact and confirms its static output exists.publishing-trigger-check— verifies GitHub Pages publishing stays family-agnostic and fails closed.static-route-validation— checks Forge route declarations and hash-anchor targets.validation-smoke— exercises validator failure boundaries with dependency-free fixtures, including CI report-contract checks.publish-health-check— confirms the live GitHub Pages site matches the last successful deploy, on a schedule and after every deploy.
See .agents/skills/README.md for the project-local support catalog and
.agents/skills/VALIDATION.md for how to run each validator locally.
Publishing status
.github/workflows/deploy-pages.yml builds and publishes Skillz Forge to
GitHub Pages on pushes to main that touch its watched paths.
.github/workflows/publish-health-check.yml independently re-checks, every
30 minutes and right after each deploy run, that the live site is actually
reachable and matches the commit the last successful deploy run built -- a
failure opens a tracking issue labeled publish-health (auto-closed once
healthy again) so a silent publish failure doesn't go unnoticed between
pushes. If the PUBLISH_HEALTH_WEBHOOK_URL repository secret is configured,
the workflow also sends one Slack/Discord-compatible notification when an
incident opens and one when it recovers; repeated checks do not spam the
webhook. Scheduled failures must persist across three consecutive checks
before opening an incident, while a failed deploy run alerts immediately.
Without the secret, issue tracking continues normally.
Development
This is a pnpm workspace. Each artifact runs as its own workflow/service; see
.replit/artifact.toml for the managed dev commands, or run an artifact
directly, e.g.:
pnpm --filter @workspace/forge run dev
Known gaps
- The Review Desk artifact does not yet have automated tests or CI coverage.
Distribution families
24 families · 20 active · updated: September 5, 2026 at 02:49 UTC
| Family | Skills | What it covers |
|---|---|---|
abrahamic/ |
4 | A family of 4 skills. Find thematically parallel passages across Judaism, Christianity,... |
agent-foundry/ |
3 | The agent-foundry family covers the creation, readiness assessment, and portability pla... |
artifacts/ |
— placeholder | A family of 0 skills. No skills cataloged yet. |
askjamie/ |
10 | One of the three OKHP3 sub-brands. AskJamie is the calm, architected AI helpdesk and in... |
brand-styles/ |
— placeholder | A family of 0 skills. No skills cataloged yet. |
community/ |
107 | A family of 107 community-originated skills spanning codebase discovery, architecture, ... |
context-extraction/ |
10 | The context-extraction family is the mining, extraction, and refinement layer for sourc... |
copilot/ |
40 | Host-oriented Agent Skills for GitHub Copilot, Copilot Cowork, SharePoint Copilot, Copi... |
glee-fully/ |
12 | Conversion target for the Glee-fully custom GPT catalog (~42 GPTs from the `Glee-fullyT... |
knowledge-operations/ |
7 | Portable lifecycle skills for capturing, classifying, researching, validating, and prom... |
language-mediation/ |
5 | Language Mediation governs controlled transformations across human languages, |
| regional ... | ||
lib/ |
— placeholder | A family of 0 skills. No skills cataloged yet. |
lifetrkr/ |
2 | A family of 2 skills. Calculate moon phase, astrological season, and Mercury retrograde... |
mermaid/ |
9 | Nine skills. One foundation, four domain skills, one publish layer, one update skill, o... |
notion/ |
11 | This family covers Notion-centered knowledge operations for OKHP3. |
outcome-modeling/ |
5 | A family of 5 skills. OverKill Hill P³ NFL fantasy picks. Use when selecting NFL fantas... |
process-capture/ |
16 | The family includes okhp3-recurring-task-capture as its meta-layer. |
red-teaming/ |
24 | A family of 24 skills. Forecast adoption of emerging agentic attack patterns from dated... |
refolddec/ |
1 | Agent Skills for ReFolDec operations — recursive folding, unfolding, and refolding acro... |
replit/ |
8 | Agent Skills for building, presenting, deploying, and maintaining projects on the Repli... |
scripts/ |
— placeholder | A family of 0 skills. No skills cataloged yet. |
social-posting/ |
31 | Platform-specific drafts for LinkedIn, Facebook, X/Twitter, Discord, YouTube, |
| Ko-fi, In... | ||
software-reclamation/ |
15 | Family crest: The Reclamation Crest, Remastered |
universal/ |
21 | Cross-project skills for repository maintenance, evidence-led review, integrations, and... |
Catalog last updated: September 5, 2026 at 02:49 UTC · 341 skills across 20 categories
abrahamic (4 skills)
| Skill | Description | Version |
|---|---|---|
| okhp3-cross-tradition-compare | Compare shared themes across Judaism, Christianity, and Islam using 20 seeded passage sets, neutr... | 1.2.0 |
| okhp3-tradition-observance-calendar | Fetch, compute, and format religious observance calendars for the three in-scope Abrahamic tradit... | 1.2.0 |
| okhp3-tradition-reference | Reference ARE scope, canon, denominations, translations, Pew US shares, and free API providers fo... | 1.2.0 |
| okhp3-verse-lookup | Fetch or integrate scripture passages from Judaism, Christianity, or Islam through the ARE free a... | 1.2.0 |
agent-foundry (3 skills)
| Skill | Description | Version |
|---|---|---|
| okhp3-custom-gpt-builder | >- | 1.3.0 |
| okhp3-custom-gpt-readiness | >- | 1.2.0 |
| okhp3-gpt-skill-conversion-plan | >- | 1.2.0 |
askjamie (10 skills)
| Skill | Description | Version |
|---|---|---|
| okhp3-askjamie-brand | OverKill Hill P³ AskJamie SPA styling. Use when a user wants an AskJamie application, documentati... | 1.1.0 |
| okhp3-askjamie-chatgpt-migrate | OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventory... | 1.0.0 |
| okhp3-askjamie-extract-chatgpt | Extract manually supplied ChatGPT conversations into standalone, actionable Markdown. Use when th... | 2.0.0 |
| okhp3-askjamie-extract-claude | Extract manually supplied Claude conversations into standalone, actionable Markdown. Use when the... | 2.0.0 |
| okhp3-askjamie-gpt-builder | >- | 1.0.0 |
| okhp3-askjamie-gpt-readiness | >- | 1.0.0 |
| okhp3-askjamie-repo-creator | Create governed FoundRy child repositories from Custom GPTs, Gemini Gems, Copilot agents, prompt ... | 1.1.0 |
| okhp3-askjamie-repo-organizer | OverKill Hill P³ repository organizer for content-first Git repositories. Use when a local Git re... | 1.1.1 |
| okhp3-askjamie-style-registry | OverKill Hill P³ visual style registry and application workflow. Use when a user wants to extract... | 1.1.0 |
| okhp3-askjamie-thread-context | Extract pasted or uploaded AI chat threads into standalone, actionable Markdown. Use when the use... | 2.0.0 |
community (107 skills)
| Skill | Description | Version |
|---|---|---|
| acquire-codebase-knowledge | Use this skill when the user explicitly asks to map, document, or onboard into an existing codeba... | 1.3 |
| agent-governance | Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Us... | — |
| agent-owasp-compliance | Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use... | — |
| agent-supply-chain | Verify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when:... | — |
| ai-social-media-content | Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: image... | — |
| api-design | Designs an interface other people will depend on — REST endpoints, RPC methods, library functions... | — |
| api-documentation | Documents an interface others will call — endpoints, SDK methods, CLI commands, and their paramet... | — |
| appinsights-instrumentation | Instrument a webapp to send useful telemetry data to Azure App Insights | — |
| architecture-blueprint-generator | Comprehensive project architecture blueprint generator that analyzes codebases to create detailed... | — |
| architecture-decision-records | Write and maintain Architecture Decision Records (ADRs) following best practices for technical de... | — |
| audit-integrity | Shared audit integrity framework for all AppSec agents — enforces output quality, intellectual ho... | 1.0 |
| auth-design | Designs how a system knows who someone is and what they may do — login, sessions, tokens, roles, ... | — |
| brand-guidelines | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit... | — |
| breakdown-test | Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task bre... | — |
| browser-testing | Writes and debugs end-to-end browser tests — Playwright, Cypress, Selenium — covering selector st... | — |
| build-evidence-map | Build an auditable evidence map for a contested technical choice, research synthesis, proposal re... | — |
| c4-codebase-architecture | Helps an agent inspect a repository and produce C4 architecture documentation. Use this when reve... | — |
| code-analysis | Builds an understanding of a whole codebase or subsystem — what it does, how it is structured, wh... | — |
| code-exemplars-blueprint-generator | Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases ... | — |
| code-linting | Sets up, fixes, or tunes linting and formatting for a project in any language — Python, JavaScrip... | — |
| code-review | Reviews a change — a diff, a PR, a branch, or uncommitted work — for correctness, risk, and maint... | — |
| code-tour | Use this skill to create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that ... | — |
| codebase-architecture | >- | — |
| codebase-discovery | Extract domain, architecture, business rules, workflows and a business glossary from an existing ... | — |
| codebase-memory-mcp | Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, traci... | — |
| containerize-aspnet-framework | Containerize an ASP.NET .NET Framework project by creating Dockerfile and .dockerfile files custo... | — |
| containerize-aspnetcore | Containerize an ASP.NET Core project by creating Dockerfile and .dockerfile files customized for ... | — |
| context-map | Generate a map of all files relevant to a task before making changes | — |
| copilot-instructions-blueprint | Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files ... | — |
| create-readme | Create a README.md file for the project | — |
| create-specification | Create a new specification file for the solution, optimized for Generative AI consumption. | — |
| create-tldr-page | Create a tldr page from documentation URLs and command examples, requiring both URL and command n... | — |
| csharp-docs | Ensure that C# types are documented with XML comments and follow best practices for documentation. | — |
| csharp-mstest | Get best practices for MSTest 3.x/4.x unit testing, including modern assertion APIs and data-driv... | — |
| csharp-nunit | Get best practices for NUnit unit testing, including data-driven tests | — |
| csharp-xunit | Get best practices for XUnit unit testing, including data-driven tests | — |
| custom-instructions-from-codebase | Migration and code evolution instructions generator for GitHub Copilot. Analyzes differences betw... | — |
| data-breach-blast-radius | Pre-breach impact analysis: inventories sensitive data (PII, PHI, PCI-DSS, credentials), traces d... | — |
| data-migration | Changes a schema or moves data in production without downtime or loss — column changes, backfills... | — |
| data-migration-best-practices | Operational data migration guidance. Use when moving or transforming persisted data between schem... | — |
| ddd-best-practices | Domain-Driven Design guidance for modeling complex domains. Use when designing Bounded Contexts o... | 1.0.0 |
| dependency-audit | Assesses what a project depends on — known vulnerabilities, licence obligations, abandoned packag... | — |
| deployment-strategies | Gets a change into production safely — blue-green, canary, rolling, feature flags, and the rollba... | — |
| devops-rollout-plan | Generate comprehensive rollout plans with preflight checks, step-by-step deployment, verification... | — |
| diagramming | Draws architecture and flow diagrams as code — Mermaid, C4, sequence, ER, and state diagrams that... | — |
| doc-and-modernize | >- | — |
| documentation-writer | Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality s... | — |
| dotnet-best-practices | Ensure .NET/C# code meets best practices for the solution/project. | — |
| dotnet-design-pattern-review | Review the C#/.NET code for design pattern implementation and suggest improvements. | — |
| dotnet-upgrade | Ready-to-use prompts for comprehensive .NET framework upgrade analysis and execution | — |
| ef-core | Get best practices for Entity Framework Core | — |
| efcore-d2-db-diagram | Generate D2 database diagrams from Entity Framework Core models. USE FOR: EF Core database diagra... | — |
| find-skills | Helps agents discover, evaluate, and recommend installable agent skills when a task may be better... | — |
| folder-structure-blueprint-generator | Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures.... | — |
| frontend-design | Create distinctive, production-grade frontend interfaces with high design quality. Use this skill... | — |
| incident-postmortem | Use when an outage, production incident, or significant service degradation has occurred and the ... | — |
| integration-testing | Tests that components work together — service against real database, API against real dependencie... | — |
| load-testing | Measures how a system behaves under load and finds where it breaks — throughput ceilings, latency... | — |
| log-analysis | Extracts an answer from logs, traces, or metrics — finding the relevant lines in volume, correlat... | — |
| lsp-architecture | Generate a structural architecture overview of a codebase: languages, package map, entry points, ... | — |
| lsp-dead-code | Enumerate exported symbols in a file and surface those with zero references across the workspace.... | — |
| lsp-docs | Three-tier documentation lookup for any symbol — hover → offline toolchain doc → source definitio... | — |
| lsp-refactor | End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, ve... | — |
| lsp-test-correlation | Find and run the tests that cover a source file. Use after editing a file to discover exactly whi... | — |
| markdown-docs | Writes or restructures project documentation in Markdown — READMEs, guides, references, runbooks,... | — |
| mcp-builder | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact... | — |
| mermaid-diagrams | Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to c... | — |
| multi-stage-dockerfile | Create optimized multi-stage Dockerfiles for any language or framework | — |
| nuget-manager | Manage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updati... | — |
| oo-component-documentation | Create or update standardized object-oriented component documentation using a shared template plu... | — |
| openapi-to-application-code | Generate a complete, production-ready application from an OpenAPI specification | — |
| playwright-automation-fill-in-form | Automate filling in a form using Playwright MCP | — |
| playwright-explore-website | Website exploration for testing using Playwright MCP | — |
| playwright-generate-test | Generate a Playwright test based on a scenario using Playwright MCP | — |
| premium-frontend-ui | A comprehensive guide for GitHub Copilot to craft immersive, high-performance web experiences wit... | — |
| readme-blueprint-generator | Intelligent README.md generation prompt that analyzes project documentation structure and creates... | — |
| refactor | Surgical code refactoring to improve maintainability without changing behavior. Covers extracting... | — |
| refactor-plan | Create a concrete plan before starting a multi-file refactor. Use when the user asks to plan, seq... | — |
| refactoring-best-practices | Safe refactoring guidance for legacy and existing codebases. Use when improving design without ch... | 1.0.0 |
| rest-api-best-practices | REST API design guidance. Use when designing or reviewing REST endpoints, choosing HTTP methods a... | 1.0.0 |
| review-and-refactor | Review and refactor code in your project according to defined instructions | — |
| scoutqa-test | This skill should be used when the user asks to "test this website", "run exploratory testing", "... | — |
| secret-scanning | Guide for configuring and managing GitHub secret scanning, push protection, custom patterns, and ... | — |
| secrets-management | Handles credentials safely through their whole life — where they live, how code gets them, how th... | — |
| security-analysis | Reviews code or a change for exploitable vulnerabilities — injection, auth and access-control gap... | — |
| security-review | AI-powered codebase security scanner that reasons about code like a security researcher — tracing... | — |
| skill-creator | Create new skills, modify and improve existing skills, and measure skill performance. Use when us... | — |
| software-architecture-analysis | Use this skill to reverse-engineer an existing software system, map its | — |
| sql-code-review | Universal SQL code review assistant that performs comprehensive security, maintainability, and co... | — |
| sql-optimization | Universal SQL performance optimization assistant for comprehensive query tuning, indexing strateg... | — |
| sql-server-table-reconciliation | Use when: comparing SQL Server tables across instances, data migration validation, ETL verificati... | — |
| tdd-best-practices | Test-Driven Development guidance. Use when writing tests before implementation, applying Red-Gree... | 1.0.0 |
| technology-stack-blueprint-generator | Comprehensive technology stack blueprint generator that analyzes codebases to create detailed arc... | — |
| theme-factory | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML... | — |
| threat-model-analyst | Full STRIDE-A threat model analysis and incremental update skill for repositories and systems. Su... | — |
| threat-modeling | Works out what could go wrong in a system's design before it is built — who would attack it, how,... | — |
| tm7-threat-model | Creates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Mo... | — |
| unit-testing | Writes unit tests for code that already exists — choosing what deserves a test, what the cases ar... | — |
| update-specification | Update an existing specification file for the solution, optimized for Generative AI consumption b... | — |
| vercel-react-best-practices | React and Next.js performance optimization guidelines from Vercel Engineering. This skill should ... | 1.0.0 |
| vercel-react-native-skills | React Native and Expo best practices for building performant mobile apps. Use when building React... | 1.0.0 |
| web-artifacts-builder | Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern fron... | — |
| web-design-guidelines | Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check ... | 1.0.0 |
| web-design-reviewer | This skill enables visual inspection of websites running locally or remotely to identify and fix ... | — |
| webapp-testing | Toolkit for interacting with and testing local web applications using Playwright. Supports verify... | — |
| workflow-analysis-blueprint | Comprehensive technology-agnostic prompt generator for documenting end-to-end application workflo... | — |
| write-coding-standards-from-file | Write a coding standards document for a project using the coding styles from the file(s) and/or f... | — |
context-extraction (10 skills)
| Skill | Description | Version |
|---|---|---|
| okhp3-chatgpt-project-migration | OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventory... | 1.0.0 |
| okhp3-session-handoff | Create a durable continuation record when work pauses, becomes blocked, crosses a machine, or cro... | 0.1.0 |
| okhp3-thread-context-extraction | Extract pasted or uploaded AI chat threads into standalone, actionable Markdown. Use when the use... | 2.0.0 |
| okhp3-thread-context-extraction-grok | Extract manually supplied xAI Grok conversations into standalone, actionable Markdown. Use when t... | 2.0.0 |
| okhp3-thread-extract-chatgpt | Extract manually supplied ChatGPT conversations into standalone, actionable Markdown. Use when th... | 2.0.0 |
| okhp3-thread-extract-claude | Extract manually supplied Claude conversations into standalone, actionable Markdown. Use when the... | 2.0.0 |
| okhp3-thread-extract-copilot-m365 | Extract manually supplied Microsoft Copilot and Microsoft 365 Copilot chats into standalone, acti... | 2.0.0 |
| okhp3-thread-extract-gemini | Extract manually supplied Google Gemini conversations into standalone, actionable Markdown. Use w... | 2.0.0 |
| okhp3-thread-extract-mistral-vibe | Extract manually supplied Mistral Vibe or former Le Chat conversations into standalone, actionabl... | 2.0.0 |
| okhp3-thread-extract-perplexity | Extract manually supplied Perplexity conversations into standalone, actionable Markdown. Use when... | 2.0.0 |
copilot (40 skills)
| Skill | Description | Version |
|---|---|---|
| okhp3-copilot-studio-skill-foundry | Design, author, evaluate, and package a reusable Microsoft Copilot Studio agent skill. Use when a... | 1.1.0 |
| okhp3-cowork-commitment-tracker | Find and reconcile the user's commitments across an agreed set of email and meeting sources. Use ... | 1.1.0 |
| okhp3-cowork-daily-execution-brief | Build a realistic personal execution brief from an agreed day's priorities, calendar, and commitm... | 1.1.0 |
| okhp3-cowork-decision-record | Draft a durable decision record from an agreed discussion or source set. Use when capturing a dec... | 1.1.0 |
| okhp3-cowork-document-critique | Critique a draft against an explicit audience, purpose, quality bar, and risk checklist. Use when... | 1.1.0 |
| okhp3-cowork-file-triage-planner | Propose a safe folder, naming, and retention cleanup plan for selected files. Use when reviewing ... | 1.1.0 |
| okhp3-cowork-inbox-triage | Triage a Microsoft 365 inbox into a prioritized, reviewable work queue. Use when organizing email... | 1.1.0 |
| okhp3-cowork-meeting-closeout | Turn an agreed meeting record into a reviewable decision and action closeout. Use when capturing ... | 1.1.0 |
| okhp3-cowork-meeting-prep | Prepare a concise meeting brief from an agreed calendar event and relevant Microsoft 365 context.... | 1.1.0 |
| okhp3-cowork-project-context-pack | Create a current, source-linked project context pack from selected Microsoft 365 material. Use wh... | 1.1.0 |
| okhp3-cowork-research-evidence-log | Build a source-linked research evidence log with confirmed, inferred, and unknown claims. Use whe... | 1.1.0 |
| okhp3-cowork-skill-foundry | Design, author, evaluate, and package a task-focused Microsoft Copilot Cowork skill. Use when con... | 1.1.0 |
| okhp3-cowork-stakeholder-update | Draft a source-grounded stakeholder up |
No comments yet
Be the first to share your take.