pngdeity
- 59 skills
- 0 followers
- 3 hours ago last updated
- ▌ Code Review Commons · pngdeityCommon guidelines, persona and critical constraints for performing high-quality code reviews. Use this skill when performing a /code-review or /pr-code-review command.
- ▌ Ssh Gpg Host · pngdeityHost-specific constraints for SSH authentication, GPG operations, and git commit signing on Arch Linux. Use when the user mentions SSH, GPG, signing, agent, keys, git commit signing, authentication, pinentry, or ssh-agent.
- ▌ Gh CLI Patterns · pngdeityPatterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback. Use when the agent needs to interact with GitHub via gh CLI or when gh command output needs parsing.
- ▌ Custom Skill Creator · pngdeity bundleMeta-skill for creating and packaging new AI agent skills. Use when requested to create a skill, document a multi-step process, or configure agent behavior as a procedural skill module. Not for single atomic functions or global architecture constraints — those go in AGENTS.md.
- ▌ Find Docs · pngdeityRetrieves up-to-date documentation via ctx7 for libraries, frameworks, SDKs, cloud APIs, and any tool where training data may be outdated. Prefer over websearch or webfetch for documentation lookups. For CLI tools installed on this system, try skill("local-first") first; if man pages and --help don't cover it, use ctx7.
- ▌ Local First · pngdeityDiscover and use man pages, --help, apropos, info pages, system logs, and kernel params before reaching for external documentation. Prefer over websearch or ctx7 for installed CLI tools, system utilities, and infrastructure commands. Local sources are version-matched and cost zero context tokens. When local sources are exhausted, fall back to skill("find-docs") → ctx7, then websearch last.
- ▌ Go Testing · pngdeity bundleUse when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff. Also use when a user asks to write a test for a Go function, even if they don't mention specific patterns like table-driven tests or subtests. Does not cover benchmark performance testing.
- ▌ Go Context · pngdeity bundleUse when working with context.Context in Go — placement in signatures, propagating cancellation and deadlines, and storing values in context vs parameters. Also use when cancelling long-running operations, setting timeouts, or passing request-scoped data, even if they don't mention context.Context directly. Does not cover goroutine lifecycle or sync primitives.
- ▌ Go Logging · pngdeity bundleUse when choosing a logging approach, configuring slog, writing structured log statements, or deciding log levels in Go. Also use when setting up production logging, adding request-scoped context to logs, or migrating from log to slog, even if the user doesn't explicitly mention logging. Does not cover error handling strategy.
- ▌ Go Defensive · pngdeity bundleUse when hardening Go code at API boundaries — copying slices/maps, verifying interface compliance, using defer for cleanup, time.Time/time.Duration, or avoiding mutable globals. Also use when reviewing for robustness concerns like missing cleanup or unsafe crypto usage, even if the user doesn't mention "defensive programming." Does not cover error handling strategy.
- ▌ Apm Migration · pngdeityMigrate consumer projects to APM. Use when asked to "migrate to APM", "add APM to project", "set up APM", or when detecting a repo lacking apm.yml. Covers greenfield and brownfield paths with tribal knowledge recovery from git history.
- ▌ Go Naming · pngdeity bundleUse when naming any Go identifier — packages, types, functions, methods, variables, constants, or receivers — to ensure idiomatic, clear names. Also use when a user is creating new types, packages, or exported APIs, even if they don't explicitly ask about naming conventions. Does not cover package organization.
- ▌ Go Interfaces · pngdeity bundleUse when defining or implementing Go interfaces, designing abstractions, creating mockable boundaries for testing, or composing types through embedding. Also use when deciding whether to accept an interface or return a concrete type, or using type assertions or type switches, even if the user doesn't explicitly mention interfaces. Does not cover generics-based polymorphism.
- ▌ Go Generics · pngdeity bundleUse when deciding whether to use Go generics, writing generic functions or types, choosing constraints, or picking between type aliases and type definitions. Also use when a user is writing a utility function that could work with multiple types, even if they don't mention generics explicitly. Does not cover interface design without generics.
- ▌ Use Modern Go · pngdeity bundleApply modern Go syntax guidelines based on the project's Go version. Use when writing Go code or when asked for modern Go code guidelines.
- ▌ Go Functions · pngdeity bundleUse when organizing functions within a Go file, formatting function signatures, designing return values, or following Printf-style naming conventions. Also use when a user is adding or refactoring any Go function, even if they don't mention function design or signature formatting. Does not cover functional options constructors.
- ▌ Design Systems · pngdeity bundleReference library of design systems for UI and branding work. Use when selecting color tokens, typography, or visual style for a project. Not for writing CSS or implementing designs.
- ▌ Go Packages · pngdeity bundleUse when creating Go packages, organizing imports, managing dependencies, or deciding how to structure Go code into packages. Also use when starting a new Go project or splitting a growing codebase into packages, even if the user doesn't explicitly ask about package organization. Does not cover naming individual identifiers.
- ▌ Go Concurrency · pngdeity bundleUse when writing concurrent Go code — goroutines, channels, mutexes, or thread-safety guarantees. Also use when parallelizing work, fixing data races, or protecting shared state, even if the user doesn't explicitly mention concurrency primitives. Does not cover context.Context patterns.
- ▌ Go Performance · pngdeity bundleUse when optimizing Go code, investigating slow performance, or writing performance-critical sections. Also use when a user mentions slow Go code, string concatenation in loops, or asks about benchmarking, even if the user doesn't explicitly mention performance patterns. Does not cover concurrent performance patterns.
- ▌ CI CD Pipeline · pngdeity bundleWorkflow for designing and maintaining high-performance, vendor-decoupled CI/CD pipelines. Use when setting up new build systems or optimizing existing automation. Not for configuring specific CI providers or writing pipeline YAML directly — use Justfile (preferred) or Makefile targets instead.
- ▌ Agent Architect · pngdeity bundleArchitect, write, structure, and maintain AI agent context files (AGENTS.md and SKILL.md). Use when creating new agent context configurations, scaffolding AGENTS.md files, designing SKILL.md modules, or determining where content belongs in the agent abstraction stack. Not for writing code or implementing features.
- ▌ Go Style Core · pngdeity bundleUse when working with Go formatting, line length, nesting, naked returns, semicolons, or core style principles. Also use when a style question isn't covered by a more specific skill, even if the user doesn't reference a specific style rule. Does not cover domain-specific patterns like error handling, naming, or testing (see specialized skills). Acts as fallback when no more specific style skill applies.
- ▌ Go Error Handling · pngdeity bundleUse when writing Go code that returns, wraps, or handles errors — choosing between sentinel errors, custom types, and fmt.Errorf (%w vs %v), structuring error flow, or deciding whether to log or return. Also use when propagating errors across package boundaries or using errors.Is/As, even if the user doesn't ask about error strategy. Does not cover panic/recover patterns.
- ▌ Go Control Flow · pngdeity bundleUse when writing conditionals, loops, or switch statements in Go — including if with initialization, early returns, for loop forms, range, switch, type switches, and blank identifier patterns. Also use when writing a simple if/else or for loop, even if the user doesn't mention guard clauses or variable scoping. Does not cover error flow patterns.
- ▌ Go Declarations · pngdeity bundleUse when declaring or initializing Go variables, constants, structs, or maps — including var vs :=, reducing scope with if-init, formatting composite literals, designing iota enums, and using any instead of interface{}. Also use when writing a new struct or const block, even if the user doesn't ask about declaration style. Does not cover naming conventions.
- ▌ Output Grader · pngdeityGrade skill evaluation outputs against assertions using LLM judgment. Use after quality evaluator completes to produce pass/fail grading with concrete evidence.
- ▌ Pkg Update · pngdeityUpdate an Arch Linux package to a new upstream version. Use when a package version has changed, nvchecker reports a delta, oldver.json is stale, the user asks to update/sync/upgrade a package, or a version bump is needed — even if the user doesn't explicitly mention "PKGBUILD" or "sync-package.sh."
- ▌ Ioc Github Actions · pngdeityInversion of Control CI/CD pipeline architecture. Use when designing or refactoring CI/CD pipelines to extract domain logic into testable shell scripts.
- ▌ Go Documentation · pngdeity bundleUse when writing or reviewing documentation for Go packages, types, functions, or methods. Also use proactively when creating new exported types, functions, or packages, even if the user doesn't explicitly ask about documentation. Does not cover code comments for non-exported symbols.
- ▌ Go Data Structures · pngdeity bundleUse when working with Go slices, maps, or arrays — choosing between new and make, using append, declaring empty slices (nil vs literal for JSON), implementing sets with maps, and copying data at boundaries. Also use when building or manipulating collections, even if the user doesn't ask about allocation idioms. Does not cover concurrent data structure safety.
- ▌ Struct Validator · pngdeityValidate SKILL.md files for structural compliance against the agentskills.io specification. Use when a new or modified SKILL.md needs frontmatter validation, directory schema verification, or format compliance checking.
- ▌ Apm Vendor Skills · pngdeityStep-by-step procedural skill for vendoring external SKILL.md files into an APM marketplace. Use when importing skills, prompts, instructions, or agents from a non-APM GitHub repository (skills.sh, Claude Code plugins, or raw SKILL.md collections) into this marketplace.
- ▌ Go Functional Options · pngdeity bundleUse when designing a Go constructor or factory function with optional configuration — especially with 3+ optional parameters or extensible APIs. Also use when building a New* function that takes many settings, even if they don't mention "functional options" by name. Does not cover general function design.
- ▌ Normalize Dataset · pngdeity bundleProcedural workflow for pre-processing raw documents (PDFs, transcripts, legacy text) into semantic, LLM-friendly Markdown datasets. Use when preparing data for RAG, ingestion, or knowledge graph construction. Not for live data processing, API design, or database schema design.
- ▌ Quality Evaluator · pngdeityEvaluate skill output quality by running test cases with and without the skill and comparing results. Use within the eval pipeline to measure a skill's value-add.
- ▌ Trigger Evaluator · pngdeityEvaluate whether a skill's description triggers correctly on test queries across agent CLIs. Use when testing skill activation accuracy against opencode and gemini CLI targets.
- ▌ Pkg Bootstrap · pngdeityInitialize a new Arch Linux package in the repository. Use when adding a new package, creating a PKGBUILD from scratch, bootstrapping from an upstream AUR or Arch GitLab source, or setting up a package for the first time — even if the user doesn't explicitly mention "bootstrap" or "PKGBUILD."
- ▌ Config Modernizer · pngdeityAudit, update, and modernize software configuration files (dotfiles) with a focus on technical accuracy and system compatibility. Use when reviewing terminal emulator configs, shell rc files, editor settings, or any program configuration.
- ▌ Candidate Selector · pngdeitySelect the best skill variant from multiple candidates based on composite evaluation scores. Use as the final stage of the skill eval pipeline to pick the measurably best SKILL.md.
- ▌ Trigger Aggregator · pngdeityAggregate trigger evaluation results across CLIs, compute trigger rates, and optimize skill descriptions using train/validation splits.
- ▌ Apm Package Author · pngdeity bundleMeta-skill for creating standalone APM packages. Use when asked to create an APM package, author a new skill, write instruction files, scaffold an .apm/ directory, or create agent context primitives. Covers package anatomy, primitive selection (instructions vs skill vs hybrid vs prompts), scaffolding, and authoring. For marketplace registration and publishing, use the apm-marketplace-publisher skill.
- ▌ Project Management · pngdeityIntegrate with project management software when completing tasks. Use when creating issues, updating task status, or interacting with project trackers like GitHub Projects or TODO.md.
- ▌ Revision Synthesizer · pngdeitySynthesize improved SKILL.md variants from eval signals. Use after grading to generate revised skill versions incorporating feedback from assertion failures, human review, and execution transcripts.
- ▌ Skill Eval Pipeline · pngdeity bundleOrchestrate end-to-end AI agent skill evaluation — structural validation, trigger testing across opencode and gemini CLI, output quality measurement with graded assertions, and automated revision synthesis. Use when a SKILL.md needs measurable quality verification or when implementing CI/CD quality gates for agent context files.
- ▌ Technical Integrity · pngdeityMaintain intellectual honesty and technical rigor during software engineering tasks. Use when performing code reviews, responding to peer agent feedback, or defending technical decisions.
- ▌ Implement Acp Client · pngdeity bundleProcedural guide for implementing the Agent Client Protocol (ACP) in host applications (IDEs, desktop apps) to enable AI agent integration. Use when adding support for ACP-compatible agents, implementing stdio or HTTP/WS transports, or exposing host-specific tools to an agent.
- ▌ Architectural Review · pngdeity bundleWorkflow for writing and auditing Architecture Decision Records (ADR) and Technical Design Documents (TDD). Use when creating new architectural decisions or reviewing functional designs for correctness and logic. Not for modifying existing skills, performing code reviews, or implementing code changes.
- ▌ Pkg Patch Recovery · pngdeityRecover from patch failures when an upstream Arch Linux package source changes. Use when .rej files appear, a patch fails to apply during sync-package.sh, updpkgsums reports checksum mismatches, or a build fails with patch-related errors — even if the user doesn't explicitly mention "patch" or ".rej."
- ▌ Context Quality Gate · pngdeityEnforce quality thresholds for AI agent context files in CI/CD. Use when validating SKILL.md files in pull requests, running automated quality checks on agent skills, or gating skill publication behind measurable quality criteria.
- ▌ Conventional Commits · pngdeityEnforce the Conventional Commits specification for git commit messages. Use when writing commit messages, setting up commit linting, or configuring automated versioning and changelog generation.
- ▌ Init Project Guidance · pngdeity bundleScaffolds AI-agent guidance files (GEMINI.md and AGENTS.md) for new or existing projects. Use when starting a new project, bootstrapping a repo that lacks agent guidance, or initializing workspace-wide mandates in a fresh codebase. Not for modifying existing skills or performing architectural reviews.
- ▌ Apm Marketplace Publisher · pngdeity bundleSkill for adding an APM package to a marketplace and publishing. Use when asked to register a package in apm.yml, add a package to the marketplace, publish an APM package, or integrate a package into the pngdeity-agent-context marketplace. Assumes the package already exists in packages/. For standalone package creation, use the apm-package-author skill.
- ▌ AI Agent Orchestration · pngdeityAI agent orchestration design patterns and production workflows. Use when designing multi-agent systems, choosing orchestration strategies (sequential, concurrent, group chat, handoff, magentic), refactoring monolithic agents into coordinated sub-agents, implementing production hardening (structured outputs, RAG pipelines, observability, circuit breakers), or planning multi-agent refactors with verification gates. Not for single-agent tool selection or prompt engineering within one agent.
- ▌ Technical Documentation · pngdeity bundleComprehensive guidance for writing architectural and technical documentation. Use when the user asks to create or update Architecture Decision Records (ADRs) or Technical Design Documents (Micro-Leaves).
- ▌ Microsoft Rust Guidelines · pngdeity bundleMicrosoft's Pragmatic Rust Guidelines for API design, crate architecture, library UX, resilience, FFI, performance optimization, documentation, and AI-oriented code. Invoke this skill when designing new Rust APIs, setting up crate structures, writing library code, implementing FFI, optimizing hot paths, authoring documentation, or making architectural decisions about Rust code organization.
- ▌ Configure Trim Safe Efcore · pngdeityConfigure Entity Framework Core for reflection-free compilation, Native AOT compatibility, and aggressive assembly trimming in Blazor WebAssembly apps. USE FOR: resolving trim warnings (IL2026/IL2111), configuring precompiled queries with dotnet ef dbcontext optimize, implementing source-generated JSON contexts, and minimizing WebAssembly build payloads. DO NOT USE FOR: standard runtime reflection-based queries or server-side DB seeding.
- ▌ Implement Offline First Sync · pngdeityDesign offline-first local data storage sync logs and implement optimistic concurrency models to handle conflicts when syncing local SQLite instances back to a central server. USE FOR: managing database synchronization states, authoring local sync queues, implementing version-concurrency keys (RowVersion/Timestamp), and designing conflict resolution strategies (Client Wins / Server Wins / Merge). DO NOT USE FOR: simple local storage caching or direct non-transactional database updates.
- ▌ Manage Sqlite Wasm Lifecycle · pngdeitySafely manage SQLite database file lifecycles and DbContext connection states in Blazor WebAssembly sandboxes during database resets, imports, exports, and restores. USE FOR: managing virtual sqlite.db files inside browser filesystems (OPFS/IndexedDB), draining DbContext connection pools before replacing database files on disk, executing direct binary database exports, and configuring connection strings for local browser sandboxes. DO NOT USE FOR: standard server-side database migrations or normal EF Core entity schema mapping.