Frontend guidance becomes outdated as browser APIs and support levels change. This skill finds focused implementation guides with compatibility and fallback advice.

Code changes can miss acceptance criteria, repository rules, or security boundaries. This skill performs a read-only review and returns structured, line-anchored findings.

Multi-agent issue delivery can lose state, mix roles, and skip safeguards. This skill coordinates implementation, review, QA, escalation, and pull request creation through agent-flow.

Issue implementation can drift beyond scope or produce incomplete handoffs. This skill applies focused changes, runs project checks, commits once, and reports structured evidence.

Deferred work becomes difficult to track when its limits and upgrade triggers remain scattered across code comments. This skill collects marked comments into a ledger and flags missing triggers.

Unnecessary abstractions and redundant dependencies make repositories harder to maintain. This skill reviews the whole codebase and ranks deletion, simplification, and replacement opportunities.

Unnecessary abstractions and dependencies make small coding tasks harder to maintain. Ponytail guides your assistant toward existing helpers, standard libraries, and minimal changes while preserving essential safeguards.

AI skills often fail because triggers, structure, and validation are unclear. This guide provides practical patterns for reliable SKILL.md design, testing, and maintenance.

Project conventions are difficult to reproduce consistently across related repositories. This skill searches local references, cites sources, synchronizes mirrors, and summarizes workflow triggers.

Unclear prompts and crowded sessions reduce coding quality. This skill provides practical workflows for planning, verification, context control, automation, and independent review.

Matching Camel, Spring Boot, and CXF versions requires checking several release sources. This skill collects current metadata and creates one Markdown matrix.

Mobile app bugs and usability problems can remain hidden during routine checks. This skill guides exploratory testing with agent-device and captures runtime evidence for issues.

App interaction tasks require reliable targeting and visible verification across device interfaces. This skill guides agent-device commands for navigation, inspection, verification, and session cleanup.

Movie and TV integrations often fail because generated clients hide authentication, response shapes, and unsupported operations. This skill gives Caffeine developers a tested implementation path for catalog reads, credential handling, and service limits.

Starting an Angular project requires many setup decisions and repeated CLI steps. This skill guides consistent scaffolding, generation, builds, AI configuration, and Tailwind setup.

Angular projects require version-aware patterns across components, state, forms, routing, testing, and tooling. This skill applies focused Angular guidance and verifies generated work.

Connecting external identity and payment providers to InsForge requires careful token, database, and protocol setup. This skill provides provider-specific implementation and verification guidance.

Convex applications need reliable coverage for data access, authentication, errors, and scheduled work. This skill guides you through focused Vitest tests against an in-memory backend.

Existing Convex applications can accumulate security, scaling, dependency, and observability gaps. This skill creates a prioritized plan and applies approved improvements.

Convex onboarding problems can remain hidden inside coding-session transcripts. This skill submits an approved transcript for analysis and summarizes actionable system improvements.