blackprince001/skills

core-foundations-code-style

Always-on coding style and organization rules for naming, file shape, comments, types, module boundaries, pattern use, errors, and avoiding unnecessary abstraction across languages and tracks.

core-setup-ci-skeleton

Use when setting up or modifying CI pipelines — the quality-gate sequence every change passes, shift-left ordering, feeding failures back to agents, and keeping the pipeline under 10 minutes.

core-build-apis-and-contracts

Use when designing any public interface — REST/GraphQL endpoints, module contracts, component props — Hyrum's Law, contract-first, consistent error semantics, validate at boundaries, extend rather than break.

core-build-architecture-in-practice

Use when designing or restructuring module interfaces while coding — deep modules, seams and adapters, designing for testability, exploring alternative interfaces (design it twice), and the implementation working loop.

core-verify-code-review

Use when reviewing changes since a fixed point, or when a non-trivial in-flight decision needs adversarial scrutiny — keep Standards and Spec separate, measure relevant complexity, and use the bounded doubt cycle (claim → extract → fresh-context adversarial…

core-verify-test-authoring

Use when writing or revising tests in any language or framework — express one observable behavior at a public seam, keep cause and effect close, use independent expected values, prefer real boundaries over internal mocks, and make tests readable,…

core-verify-testing-strategy

Use before writing or revising tests to choose the smallest useful evidence for each behavior — balance risk, cost, speed, maintainability, utilization, reliability, and fidelity; avoid pyramid cargo cults, coverage gaming, and flaky signals; record gates,…

core-ship-launch-checklist

Use as the final gate before anything goes live — the pre-launch checklist across code/security/performance/a11y/infrastructure/docs, and the first-hour post-launch verification.

core-operate-feedback-and-iteration

Use when closing the loop from shipped software back into scoping, or when operating a growing user community — activity analysis feeding revised scenarios, and human-scaling mechanisms (accountability, partitioning, friction, filters, spam-proofing).

core-operate-observability

Use when adding logging, metrics, tracing, or alerts — define the on-call questions first, structured events with correlation IDs, RED/USE metrics with bounded cardinality, symptom-based alerting, then verify the telemetry itself.

core-setup-checklist-design

Use when turning a settled goal, plan, procedure, runbook, migration, launch, investigation, or recurring operation into an atomic, dependency-ordered, evidence-backed checklist. Apply failure-aware checklist design when success depends on identifying how…

ponytail-gain

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save",…

ponytail-help

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

ponytail-audit

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for…

ponytail-review

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says…

ponytail-debt

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did…

human-writing

Write and edit prose that reads as human rather than AI-generated. Use when drafting or revising articles, essays, documentation, emails, blog posts, or any natural-language text where an obviously "AI" tone would undermine the work. Catches and fixes tells…

ai-ml-setup-model-selection

Use when choosing, comparing, benchmarking, routing, or replacing generative, embedding, vision, speech, or classical ML models; extends core architecture selection with quality, latency, cost, privacy, deployment, and model-lifecycle trade-offs.

ai-ml-build-agents-and-tools

Use when implementing agent loops, tool definitions, handoffs, manager-worker or multi-agent orchestration, context transfer, memory, MCP integrations, stopping conditions, and human checkpoints after agentic complexity has been justified.

ai-ml-build-ai-security

Use when building, reviewing, or operating ML, LLM, agent, retrieval, or tool-using systems and when installing agent skills; applies responsible-AI impact review, prompt-injection and output controls, least agency, data protection, human oversight, and…

ai-ml-build-llm-app-architecture

Use when designing an LLM application, deciding whether it needs a direct call, deterministic workflow, agent, multi-agent system, or framework, and defining model boundaries, state, structured output, streaming, failure handling, and human control.

ai-ml-build-ml-data-pipelines

Use when building datasets, labels, features, embeddings, fine-tuning data, training or inference pipelines, experiment tracking, model artifacts, data validation, or reproducible ML workflows; applies the Microsoft ML lifecycle checklist on top of core data…

ai-ml-build-prompting-and-context

Use when writing or changing system instructions, prompt templates, few-shot examples, retrieval, RAG, citations, conversation context, compaction, memory, or token budgets for an LLM application or agent.

ai-ml-verify-evals

Use when defining, implementing, or reviewing evaluations for nondeterministic model behavior, prompts, retrieval, tools, agents, safety, model changes, or ML pipelines; extends core testing with representative datasets, graders, repeated trials, error…

ai-ml-operate-model-monitoring

Use when operating a deployed model, prompt, retrieval system, or agent and monitoring quality, drift, safety, tools, latency, cost, provider changes, feedback, rollout, rollback, retraining, or retirement.

backend-setup-service-architecture

Use when choosing backend service boundaries, deployment units, runtime topology, state placement, capacity assumptions, or failure domains; extends the core architecture decision with server-specific constraints.

backend-build-api-surface

Use when implementing or evolving backend HTTP, GraphQL, RPC, webhook, or event interfaces; extends core contract rules with transport semantics, authentication, idempotency, pagination, rate limits, and delivery guarantees.

backend-build-backend-security

Use when implementing internet-facing services, server authorization, sensitive-data handling, tenant isolation, audit trails, or service identities; extends core secure coding with backend trust boundaries and infrastructure controls.

backend-build-data-and-storage

Use when implementing backend schemas, queries, transactions, migrations, caches, queues, jobs, backups, or recovery; extends core state-and-data rules with durable server-side persistence mechanics.

blogs-design-post-design

Shaping a blog post — angle, structure, and framing for learn-and-showcase writing.

blogs-build-showcase-and-media

Code snippets, demos, screenshots, and figures in blog posts — showing the work well.

blogs-build-voice-and-participation

Use when drafting blog posts with the user — their words carry the post; the agent supports through the fragments → beats/shape → edit pipeline (mine raw fragments by interview, assemble beat-by-beat with grounding, tighten prose), never ghostwriting.

blogs-ship-publishing-and-sharing

Publishing blog posts — platform, formatting, metadata, distribution and sharing.

cli-design-cli-design

Use when designing or changing a command-line interface, including commands, arguments, output, prompts, errors, exit status, help, and automation behavior; extends core UX and contract rules for terminal interfaces.

cli-ship-distribution

Use when packaging, signing, publishing, installing, updating, or supporting a CLI across operating systems and package managers; extends core release and versioning rules with command-line distribution mechanics.

core-foundations-accessibility-baseline

Always-on accessibility baseline for every user-facing artifact and interface. Use to enforce perceivable, operable, understandable, and robust access before design, build, platform overlays, or verification add specifics.

core-foundations-design-principles

Always-on interface design principles for clarity, hierarchy, feedback, accessibility, restraint, predictability, and trade-off decisions before visual, typography, motion, or platform design skills add specifics.

core-foundations-engineering-principles

Always-on engineering values for every technical decision, all tracks — including source-driven development: ground framework-specific code in current official docs, detect versions first, cite sources, flag the unverified.

godfile-navigator

Mandatory first routing gate for every substantive request, response, recommendation, plan, explanation, diagnosis, review, research task, implementation, verification, release, or operational action. Always load before answering or using tools unless the…

core-foundations-performance-values

Performance as an always-on value, all tracks — performance engineering is proactive, not testing: objectives grounded in business goals, checkable criteria, and integration into every phase from design onward.