Claude Skills by athola

Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.

Manually evaluate a recent skill execution to record qualitative feedback.

Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.

Models a business in its own language. Use when the domain has real business rules to capture.

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.

Delegates tasks to the OpenAI Codex CLI (codex exec) via delegation-core. Use when delegation-core selects Codex or OpenAI credentials are already configured.

Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.

Delegates tasks to Z.ai GLM-5.x via the stock claude binary and an endpoint swap. Use when delegation-core selects GLM or a 1M-token context is needed.

Delegates tasks to the MiniMax CLI (mmx) via delegation-core. Use when delegation-core selects MiniMax or large-context batch work is needed.

Delegates tasks to Meta's Muse Code CLI (muse) via delegation-core. Use when delegation-core selects Muse or repository-scale work needs a 1M-token context.

Delegates tasks to OpenCode (opencode run) via delegation-core. Use when delegation-core selects OpenCode or a provider-agnostic harness is wanted.

Reports which delegation CLIs are installed and authenticated, installs missing ones, and stores the result. Use before delegating or when a provider errors.

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.

Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.

Verifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.

Ramps implementation ambition a notch only after the prior increment is understood. Use when building a feature you must understand, not just ship.

Contract for the project decision journal (tradeoffs and lessons-learned logs). Use when recording a decision, tradeoff, or lesson, or building a consumer hook.

Decides hand-vs-compiler for loop transforms (unrolling, SIMD, fusion, branchless). Use when reviewing/authoring a hot loop or tempted to hand-optimize one.

Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.

Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.

Decompose a session into typed handoff units and recall them later. Use when ending a session or resuming work whose prior state must be recovered.

Generates and self-executes a diff-derived test plan for a PR.

Applies an ASD-STE100-derived register to operator and procedural text. Use when writing runbooks or steps. Do not use for docstrings, ADRs, or rationale.

Export a research session into knowledge-intake compatible markdown. Use after a research session to hand findings to memory-palace.

Generate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.

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