Claude Skills by athola

Converts a Claude Code session JSONL file into an animated GIF terminal replay. Use when creating demos or visual evidence from past sessions.

Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

Audit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.

Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process a backlog automatically.

Pre-implementation gate covering think-first, simplicity, surgical edits, and verifiable goals. Use when starting implementation to verify the approach.

Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers. Use when designing or auditing enforcement mechanisms for project rules.

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

Defines the contract for deferred-item capture across plugins. Use when building or validating a plugin's deferred-capture wrapper or adding source labels.

'Surfaces expert frameworks and proven methodologies before creating

TDD-style testing methodology for skills using fresh subagent instances

Architecture-aware project initialization combining online research with archetype selection. project initialization, new project, architecture decision, project setup, which architecture, choose architecture, project architecture Use when: initializing a new project and need to select an appropriate architecture based on project type, team size, domain complexity, and current best practices DO NOT use when: architecture is already decided - use project-init instead. DO NOT use when: explo...

Generate language-specific Makefiles with common development targets for testing, linting, and automation. Use when: initializing projects, setting up development workflow, standardizing commands. Do not use when: Makefile already exists and is current.

Configure three-layer pre-commit quality system with linting, type checking, and testing hooks. Use when: setting up quality gates, configuring pre-commit, establishing code quality standards. Do not use when: pre-commit already configured optimally.

Guide project ideation through Socratic questioning and constraint analysis to create actionable project briefs. Use when: starting projects, exploring problem spaces, comparing approaches, validating feasibility. Do not use when: requirements already clear and specification exists.

Execute implementation plans systematically with checkpoint validation, progress tracking, and continuous quality gates. Use when: implementing tasks, executing plans, tracking progress, validating checkpoints. Do not use when: no implementation plan exists or still in planning phase.

Interactive project initialization with git setup, workflows, hooks, and build configuration. project setup, initialization, scaffold, bootstrap, new project Use when: starting new projects or initializing repositories

Transform specifications into structured implementation plans with architecture design and dependency-ordered task breakdown. Use when: converting specs to plans, designing architecture, breaking down tasks, estimating effort. Do not use when: no specification exists yet or still brainstorming approaches.

Transform project briefs into detailed, testable specifications using spec-driven development methodology. Use when: translating requirements, defining acceptance criteria, creating technical specs, before implementation. Do not use when: already have detailed specification or still exploring problem space.

Inline reversibility assessment for embedded War Room escalation from other commands. Use when: called from commands at decision points, determining if escalation needed. Do not use when: standalone strategic decisions, simple questions.

Multi-LLM deliberation framework for strategic decisions through expert pressure-testing and consensus building. Use when: critical decisions, irreversible changes, architecture choices, conflicting approaches, high stakes. Do not use when: decision is trivial, easily reversible, or already made.

Configure GitHub Actions CI/CD workflows for automated testing, linting, and deployment. Use when: setting up CI/CD, configuring GitHub Actions, automating quality checks. Do not use when: CI/CD already configured or using different platform.

'Detect codebase bloat through progressive analysis: dead code, duplication,

'Automatic context management with graceful handoff to continuation subagent.

'Provides guidance on fundamental software design principles to reduce

'Guidance on when to ask clarifying questions vs proceed with standard

'hype, and unnecessary framing. Includes termination and directness guidelines.

'balancing accuracy with token efficiency. Use when: source, cite, reference,

This skill provides the catalog and guides installation. Use when looking

Create hookify rules - markdown-based behavioral rules preventing unwanted actions. create hookify rule, behavioral rule, prevent behavior, block command Use when: preventing dangerous commands, blocking debug commits, enforcing conventions DO NOT use when: hook scope (abstract:hook-scope-guide), SDK hooks (abstract:hook-authoring), evaluating hooks (abstract:hooks-eval)

Feature review and prioritization with RICE/WSJF/Kano scoring. Creates GitHub issues for suggestions. feature review, prioritization, RICE, WSJF, roadmap, backlog Use when: reviewing features or suggesting new features DO NOT use when: evaluating single feature scope - use scope-guard.

'Enforces "prove before claim" discipline - validation, testing, and

'Prevents sycophantic reasoning through checklist-based analysis, categorical

automatically create GitHub issues for workflow improvements via /fix-workflow.

'Capture and retrieve PR review knowledge in project memory palaces.

'Analyze and improve living code quality: duplication, algorithmic efficiency,

Architecture review using FPF (Functional Programming Framework) methodology.

'Guidelines from the NASA Power of 10 rules for writing robust, verifiable

Audit shell scripts for correctness, portability, and common pitfalls.

'Uses subagents for parallel execution with code review gates between

Manage Claude Code sessions with naming, checkpointing, and resume strategies.

Orchestrate tutorial generation from VHS tapes and Playwright specs to dual-tone markdown with GIF recording. tutorial update, gif generation, tape recording, update tutorial, regenerate gifs, tutorial manifest Use when: regenerating tutorial GIFs, updating documentation demos, creating tutorials from tape files DO NOT use when: only updating text - use doc-updates. DO NOT use when: only capturing browser - use scry:browser-recording directly.

'Generate or remediate documentation with human-quality writing and style

'Detect and flag AI-generated content markers in documentation and prose.

Learn and extract writing style patterns from exemplar text for consistent

Record browser sessions using Playwright for web UI tutorials, converts video to GIF. Triggers: tutorial, web, video, browser, playwright, browser recording, web demo Use when: creating browser-based tutorials

Post-process video files and generate optimized GIFs. Converts webm/mp4 to GIF with configurable quality settings. Triggers: gif, ffmpeg, video, optimization, gif conversion, video to gif Use when: converting browser recordings to GIF format, optimizing GIF file size

Combine media assets (GIFs, videos) into composite tutorials with vertical/horizontal layouts. Triggers: tutorial, composition, stitch, ffmpeg, media, combine, merge recordings Use when: combining terminal and browser recordings

Generate terminal recordings using VHS tape files, produces GIF outputs. Triggers: tutorial, vhs, gif, terminal, recording, terminal demo Use when: creating terminal recordings for tutorials

Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.

Provides coding assistance with best practices and code review