athola

Python testing with pytest, fixtures, mocking, and TDD workflows.Triggers: pytest, unit tests, test fixtures, mocking, TDD, test suite, coverage,test-...

Audit Makefiles for duplication, portability, and idiomatic GNU Make usage.Triggers: Makefile review, build system, GNU Make, portability, deduplicati...

Master Python asyncio, concurrent programming, and async/await patternsfor high-performance applications.Triggers: asyncio, async/await, coroutines, c...

Standardized pytest configuration patterns for plugin development. Reducesduplication across parseltongue, pensive, sanctum, and other plugins.Trigger...

Evaluate public API surfaces against internal guidelines and external exemplars.Triggers: API review, API design, consistency audit, API documentation...

Model system responsibilities across clients, servers, and optional peer-to-peernodes for traditional distributed applications.Triggers: client-server...

Apply CQRS (Command Query Responsibility Segregation) and Event Sourcing fordomains requiring strong auditability and independent scaling of reads and...

Structure systems around asynchronous, event-based communication to decoupleproducers and consumers for improved scalability and resilience.Triggers: ...

Employ the "Functional Core, Imperative Shell" pattern to isolate deterministicbusiness logic from side-effecting code for superior testability.Trigge...

Employ the Hexagonal (Ports & Adapters) pattern to decouple domain logic frominfrastructure, maximizing flexibility and testability.Triggers: hexagona...

Use a Layered (N-Tier) architecture to separate presentation, domain logic, anddata access responsibilities within a system.Triggers: layered architec...

Build a minimal, stable core system that loads plug-ins to provide featurevariability and extensibility for platform development.Triggers: microkernel...

Decompose systems into a suite of small, independently deployable services alignedto specific business capabilities.Triggers: microservices, service d...

Maintain a single deployable artifact while enforcing strong internal boundariesbetween modules for team autonomy without distributed complexity.Trigg...

Compose processing stages using a pipes-and-filters model for ETL, mediaprocessing, or compiler-like workloads.Triggers: pipeline architecture, pipes ...

Build serverless, Function-as-a-Service (FaaS) systems for event-driven oroperations-light workloads with minimal infrastructure management.Triggers: ...

Employ a coarse-grained, service-based architecture (lighter SOA) whenmicroservices aren't necessary but modular deployment is required.Triggers: serv...

Employ space-based or data-grid architectures to scale high-traffic, statefulworkloads across multiple nodes with linear scalability.Triggers: space-b...

Interactive selector and implementation planner for architecture paradigms.Triggers: architecture selection, pattern comparison, system design, ADR cr...

Evaluate codebase architecture against ADRs, coupling rules, and team guardrails.Triggers: architecture review, ADR audit, coupling analysis, design r...

Common authentication patterns for external service integration. Covers API keys,OAuth flows, token management, and verification strategies.Triggers: ...

Systematically uncover and fix bugs using language-specific expertise andreproducible evidence.Triggers: bug hunting, defect detection, debugging, fix...

Methodology for summarizing changes, extracting insights, and identifying follow-up actions.Triggers: catchup, what changed, summarize changes, contex...

Generate conventional commit messages from staged changes by inspecting diffs,picking the correct type/scope, and writing the final text.Triggers: com...

Reduce context usage with MECW principles (keep under 50% of total window).Triggers: context pressure, token usage, MECW, context window, optimization...

Monitor and optimize CPU/GPU usage with load measurement and cost-effectivevalidation strategies.Triggers: CPU usage, GPU usage, performance, load mon...

Framework for delegating tasks to external LLM services (Gemini, Qwen).Uses leyline infrastructure for quota, logging, and error handling.Triggers: de...

Comprehensive development workflow with modular patterns for git, code review, testing, documentation, and deployment

Methodology for categorizing changes, assessing risks, and creating summariesfrom any changeset.Triggers: diff analysis, changeset review, risk assess...

Design, manage, and evolve digital gardens as living knowledge bases withinmemory palaces.Triggers: digital garden, knowledge base, linking, note cura...

Consolidates ephemeral LLM-generated markdown files into permanent documentation.Triggers: consolidate docs, untracked reports, ephemeral files, git c...

Update documentation files based on recent changes while enforcing projectwriting guidelines.Triggers: documentation update, docs update, ADR, docstri...

Standardized error handling patterns for robust plugin development. Provideserror classification, recovery strategies, and logging patterns.Triggers: ...

Guide to deciding whether to escalate from a lower model (haiku/sonnet) toa higher model (sonnet/opus).Triggers: model escalation, haiku to sonnet, so...

Generic weighted scoring and threshold-based decision framework for evaluatingartifacts against configurable criteria.Triggers: evaluation, scoring, q...

Workflow for capturing evidence and citations to create reproducible analysesand audit trails.Triggers: evidence capture, citations, reproducible anal...

Review implemented features and suggest new features using configurableprioritization heuristics. Supports GitHub issue creation for accepted suggesti...

Structured file enumeration and content analysis for understanding codebasestructure before reviews or refactoring.Triggers: file analysis, codebase s...

Fix GitHub issues using subagent-driven-development with parallel executionwhere appropriate.Triggers: fix issue, github issue, issue resolution, suba...

Gemini CLI delegation workflow implementing delegation-core for Google's Gemini models.Triggers: gemini cli, gemini delegation, google gemini, 1M cont...

Lightweight preflight checklist for verifying repo path, staged changes, anddiffs before other workflows.Triggers: git status, preflight, workspace ch...

Generate program dashboards, GitHub-ready comment digests, and CSV summariessourced from Minister's tracker data.Triggers: initiative pulse, status re...

Complete guide for writing Claude Code and SDK hooks with security-first design.Triggers: hook creation, hook writing, PreToolUse, PostToolUse, UserPr...

Comprehensive hook evaluation framework for Claude Code and Agent SDK hooks.Triggers: hook audit, hook security, hook performance, hook compliance,SDK...

Process external resources (articles, blog posts, papers) into actionableknowledge with systematic evaluation, storage, and application decisions.Trig...

Spatial indexing and retrieval system for finding information within memorypalaces using multi-modal search.Triggers: knowledge search, find informati...

Analyze and enhance Makefiles for complete user functionality coverage.Triggers: Makefile analysis, Makefile gaps, missing targets, plugin release,Mak...

Intensive mathematical analysis for numerical stability, algorithm correctness,and alignment with authoritative standards.Triggers: math review, numer...

Transform tool-heavy workflows into MCP code execution patterns using MECWprinciples for optimized token savings and hallucination prevention.Triggers...

Maximum Effective Context Window (MECW) theory and practical patterns forpreventing hallucinations through context management. Implements the 50% rule...

Design and construct virtual memory palaces for spatial knowledge organizationusing mnemonic techniques.Triggers: memory palace, spatial organization,...

Design skills as modular building blocks for predictable token usageand maintainable architecture.Triggers: skill design, skill architecture, modulari...

Systematic methodology to reduce skill file size through externalization,consolidation, and progressive loading patterns.Triggers: large skill, skill ...

Shared infrastructure and reusable modules for all pensive review skills.Triggers: pensive patterns, review workflow, output templates, quality checkl...

Prepare a pull request by validating the workspace, running quality gates,summarizing changes, and drafting the PR template.Triggers: PR preparation, ...

Scope-focused PR code review that validates against original requirements androutes out-of-scope findings to GitHub issues.Triggers: PR review, pull r...

Standardized patterns for context-aware, progressive module loading thatoptimizes token usage. Implements hub-and-spoke with dynamic module selection....

Create distributable Python packages with proper structure and publishing.Triggers: Python packaging, pyproject.toml, uv, pip, PyPI, distribution, CLI...

Profile and optimize Python code using cProfile, memory profilers, andperformance best practices.Triggers: profiling, optimization, cProfile, memory p...

Universal quota tracking and enforcement patterns for rate-limited services.Provides threshold monitoring, estimation, and graceful degradation strate...

Qwen CLI delegation workflow implementing delegation-core for Alibaba's Qwen models.Triggers: qwen cli, qwen delegation, alibaba qwen, qwen batch, mul...

Declarative release readiness checklist that mirrors GitHub checks,deployment issues, and documentation requirements.Triggers: release gates, release ...

Foundational workflow for preparing and structuring detailed reviews(architecture, API, code quality).Triggers: review workflow, structured review, re...

Expert-level Rust audits covering ownership, concurrency, unsafe blocks,traits, and Cargo dependencies.Triggers: Rust review, ownership analysis, borr...

Prevents overengineering through worthiness scoring, opportunity cost comparison,and branch threshold monitoring.Triggers: scope creep, overengineerin...

Registry pattern for managing external service connections, configurations,and health checks.Triggers: service registry, service discovery, health che...

Construct temporary, session-specific memory palaces for complex projectsand conversations.Triggers: session context, project memory, conversation sta...

Shared infrastructure and patterns for sanctum git/workspace skills.Triggers: sanctum patterns, todowrite patterns, git commands, output templates,san...

Reusable patterns and templates for Claude Code skill and hook development.Triggers: validation patterns, error handling, testing templates, workflow ...

Guide to effective Claude Code skill authoring using TDD methodology andpersuasion principles.Triggers: skill authoring, skill writing, new skill, TDD...

Evaluate and improve Claude skill quality through comprehensive auditing.Triggers: skill audit, quality review, compliance check, improvement suggesti...

Create clear, testable specifications from natural language descriptions.Focus on what users need and why, not implementation details.Triggers: spec w...

Workflow orchestrator for Spec Driven Development. Coordinates skill loading,tracks progress, and ensures consistency across the speckit workflow.Trig...

Generic template patterns and lifecycle stages for knowledge storage,configuration management, and structured documentation.Triggers: storage template...

Guide to formatting review deliverables for consistency, ensuring findingsare comparable across different types of analysis.Triggers: report formattin...

Generate dependency-ordered implementation tasks from specifications and plans.Create actionable, phased task breakdowns for systematic implementation...

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking,and quality assessment.Triggers: test audit, test coverage, test quality, TDD, ...

Update and maintain tests following TDD/BDD principles with comprehensivequality assurance.Triggers: test updates, test maintenance, test generation, ...

Shared testing quality metrics and standards for cross-plugin use. Referencedby pensive:test-review and parseltongue:python-testing.Triggers: testing ...

Minimize token usage through conservative prompting, work delegation,and quota tracking.Triggers: token usage, quota, token limits, prompt size, token...

Orchestrate and run appropriate pensive review skills based on codebaseanalysis and context.Triggers: code review, unified review, comprehensive revie...

Consolidate README content using language-aware exemplars, internal doc linkage,and reproducible evidence.Triggers: README update, documentation refre...

Session-aware usage logging infrastructure for audit trails, cost tracking,and analytics. Provides structured logging with JSONL format and session ma...

Bump project versions across configs, docs, and changelog usinggit-workspace-review context.Triggers: version bump, semver, release version, changelog...

Retrospective workflow to evaluate the most recent command/session sliceand drive improvements to workflow assets (skills, agents, commands, hooks).Tr...

Design skills as modular building blocks for predictable token usage and maintainable architecture

Evaluates and improves Claude Skills across all ~/.claude/ locations

Model system responsibilities across clients, servers, and optional peer-to-peer nodes.

Apply Command Query Responsibility Segregation (CQRS) and Event Sourcing (ES) for collaboration-heavy domains that require strong auditability and ind...

Structure systems around asynchronous, event-based communication to decouple producers and consumers for improved scalability and resilience.

Employ the "Functional Core, Imperative Shell" pattern to isolate deterministic business logic from side-effecting code for superior testability.

Employ the Hexagonal (Ports & Adapters) pattern to decouple domain logic from infrastructure, maximizing flexibility and testability.

Use a Layered (or N-Tier) architecture to separate presentation, domain logic, and data access responsibilities within a system.

Build a minimal, stable core system that loads plug-ins to provide feature variability and extensibility.

Decompose systems into a suite of small, independently deployable services that are aligned to specific business capabilities.

Maintain a single deployable artifact while enforcing strong internal boundaries between modules.

Compose processing stages using a pipes-and-filters model for ETL, media processing, or compiler-like workloads.

Build serverless, Function-as-a-Service (FaaS) systems for event-driven or operations-light workloads.

Employ a coarse-grained, service-based architecture (a lighter form of SOA) when microservices are not yet necessary but modular deployment is require...

Employ space-based or data-grid architectures to scale high-traffic, stateful workloads across multiple nodes.

Interactive selector and implementation planner for architecture paradigms.

Evaluate public/API surfaces against internal guidelines and external exemplars in any language.

Model system responsibilities across clients, servers, and optional peer nodes.

Apply CQRS + Event Sourcing for collaboration-heavy domains needing auditability and independent scaling.

Structure systems around asynchronous events to decouple producers and consumers.

Use Functional Core, Imperative Shell pattern to isolate deterministic business logic from side-effect orchestration for improved testability.

Use Hexagonal (Ports & Adapters) boundaries to decouple domain logic from infrastructure concerns for maximum flexibility.

Use Layered / N-tier architecture to separate presentation, domain logic, and data access responsibilities.

Build a minimal, stable core that loads plug-ins for feature variability.

Decompose systems into independently deployable services aligned to business capabilities.

Keep a single deployable artifact while enforcing strong internal module boundaries.

Compose processing stages via pipes-and-filters for ETL, media, or compiler-like workloads.

Build serverless/function-as-a-service systems for bursty or ops-light workloads.

Use coarse-grained service-based architecture (SOA-lite) when microservices are unnecessary but modular deployment is needed.

Use space-based/data-grid architectures to scale high-traffic, stateful workloads across nodes.

Interactive selector and implementation planner for architecture paradigms with orchestration access to specialized paradigm skills.

Evaluate how the codebase architecture lines up with existing ADRs, coupling rules, and team guardrails before approving major work.

Systematically uncover and fix bugs across diffs/snippets with language-aware expertise and reproducible evidence.

Repo-diff catchup ritual that gathers git status/diffs, reviews each material file, and produces a concise summary while keeping token usage low.

Generate conventional commit messages from staged changes by inspecting diffs, picking the correct type/scope, and writing the final text to the promp...

Guardrail workflow that keeps CPU/GPU usage lean by measuring load, narrowing scope, and choosing the lowest-cost validation strategy before running h...

Update documentation files based on recent changes while enforcing project writing guidelines.

Decide when and how to hand routine coding work to the Gemini CLI while Claude focuses on higher-level reasoning.

Lightweight preflight checklist for verifying repo path, staged changes, and diffs before other workflows.

Audit Makefiles for duplication, portability, and idiomatic GNU Make usage using research-driven heuristics.

Perform intensive mathematical analysis on code changes, ensuring derivations, numerical stability, and validation evidence align with authoritative s...

Design superpowers skills as modular building blocks for predictable token usage and maintainable architecture

Prepare a pull request by validating the workspace, running quality gates, summarizing changes, and drafting the PR template.

Comprehensive Python testing guidance with orchestration access to specialized testing skills for unit testing, integration testing, mocking, and adva...

Master unit testing fundamentals with pytest for reliable, isolated testing of individual Python components.

Decide whether to delegate lower-level execution to Qwen MCP while Claude handles planning/review.

Shared preflight + reporting workflow for all deep-dive reviews (architecture, math, makefile, api, etc.).

Perform in-depth Rust audits (ownership, concurrency, unsafe, traits, Cargo dependencies) with reproducible evidence.

Comprehensive evaluation and improvement system for Claude Skills across all ~/.claude/ locations

Gemini-marketplace–only orchestrator that forces every /speckit:* workflow to load the correct superpowers skills, capture dual-governance variances, ...

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking, and reproducible evidence.

Enforce ultra-conservative token usage by minimizing prompt exposure, delegating bulk work, and tracking quotas.

Consolidate README content using language-aware exemplars, internal doc linkage, and reproducible evidence.

Bump project versions across configs, docs, and changelog using git-workspace-review context.

Framework for delegating tasks to external LLM services, with a focus on strategic oversight and quality control.

Gemini CLI delegation workflow with quota tracking, authentication, and usage logging.

Qwen CLI delegation workflow with quota tracking, authentication, and usage logging. Utilizes shared shell execution infrastructure for consistent del...

Guardrail workflow that keeps CPU/GPU usage lean by measuring load, narrowing scope, and choosing the lowest-cost validation strategy before running h...

A workflow for conservative token usage by minimizing prompt exposure, delegating bulk work, and tracking quotas.

A methodology for summarizing changes, extracting insights, and identifying follow-up actions.

A methodology for categorizing changes, assessing risks, and creating summaries from any changeset.

A workflow for capturing evidence and citations to create reproducible analyses and audit trails.

A foundational workflow for preparing and structuring detailed reviews (e.g., architecture, API).

A guide to formatting review deliverables for consistency, ensuring findings are comparable across different types of analysis.

Design, manage, and evolve digital gardens as living knowledge bases within memory palaces.

A spatial indexing and retrieval system for finding information within memory palaces.

Design and construct virtual memory palaces for spatial knowledge organization.

Construct temporary, session-specific memory palaces for complex projects and conversations.

Map and navigate relationships between Claude skills.

Evaluate and improve Claude skills for clarity, completeness, testability, and architectural coherence.

Evaluate API surfaces against internal guidelines and external examples in any language.

Evaluate codebase architecture against ADRs, coupling rules, and team guardrails before approving major work.

Uncover and fix bugs in code snippets using language-specific expertise and reproducible evidence.

Audit Makefiles for duplication, portability, and idiomatic GNU Make usage.

Perform intensive mathematical analysis on code changes to ensure numerical stability and alignment with authoritative standards.

Perform in-depth audits of Rust code, covering ownership, concurrency, unsafe blocks, traits, and Cargo dependencies.

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking, and reproducible evidence.

Orchestrate and run appropriate pensive review skills based on codebase analysis and context.

Generate conventional commit messages from staged changes by inspecting diffs, picking the correct type/scope, and writing the final text to the promp...

Update documentation files based on recent changes while enforcing project writing guidelines.

Structured file enumeration and content analysis for understanding codebase structure before reviews or refactoring.

Lightweight preflight checklist for verifying repo path, staged changes, and diffs before other workflows.

Prepare a pull request by validating the workspace, running quality gates, summarizing changes, and drafting the PR template.

Consolidate README content using language-aware exemplars, internal doc linkage, and reproducible evidence.

Bump project versions across configs, docs, and changelog using git-workspace-review context.