do-movie-radio-play

Coordinate multiple agents for software development across any language. Use for parallel execution of independent tasks, sequential chains with dependencies, swarm analysis from multiple perspectives, or iterative refinement loops. Handles Python, JavaScript, Java, Go, Rust, C#, and other languages.

Multi-step GOAP planning for complex audio pipeline development. Orchestrates analysis, decomposition, strategy selection, and execution with state persistence in plans/.

Generates DORA metrics and agent delivery reports from structured events.

Records agent execution events for lead time, success rate, and human intervention tracking.

Generic TRIZ analysis for identifying technical and physical contradictions in software architecture and pipelines.

Generic TRIZ solver for resolving architectural and technical contradictions using inventive principles.

Three-persona code review and engineering analysis combining deep analysis (RYAN), pragmatic shipping focus (FLASH), and questioning synthesis (SOCRATES). Use for reviewing code, analyzing architecture, triaging bugs, evaluating technical proposals, assessing security risks, and making engineering trade-offs.

Execute iterative refinement workflows with validation loops until quality criteria are met. Use for test-fix cycles, code quality improvement, performance optimization, or any task requiring repeated action-validate-improve cycles.

Reusable skill for evaluating other skills with structure checks, eval coverage review, and real usage spot checks. Use when you need to check a skill, add evals, benchmark a skill, validate outputs against assertions, or compare current skill behavior against a baseline.

Use Codacy static analysis CLIs to query PR analysis, triage issues, suppress false positives, and run local analysis. Use when Codacy blocks a PR, when asked to fix Codacy issues, suppress false positives, query PR quality data, or integrate Codacy into CI/CD workflows. Relevant for Rust (clippy), Shell (shellcheck), and Markdown (markdownlint).

Voice Activity Detection on CPU using energy and spectral engines

Converting frame-level VAD output to non-voice segments with duration constraints

Profile-based threshold adjustment using correction feedback from manual reviews

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Create AGENTS.md files with production-ready best practices. Use when creating new AGENTS.md or implementing quality gates.

Apply this skill whenever the user wants to audit, fix, redesign, write, or review UI, UX, copy, or text to avoid the generic "AI slop" aesthetic of 2025–2026. Triggers include: "make this feel less AI", "this looks too generic", "avoid AI clichés", "audit my copy", "anti-pattern review", "humanize this", "this feels soulless", "too corporate", "fix the UX writing", "why does this feel like ChatGPT made it", "anti-design", "brutalist", "raw", "intentional", "authentic", "distinctive", "not like every other AI app", "responsive", "mobile", "tablet", "desktop". Also trigger when producing new UI, copy, or UX flows and the user cares about quality and distinctiveness. Always verify mobile, tablet, and desktop views for proper navigation and layout. This skill is your checklist, diagnostic tool, and creative brief for everything that makes design feel human, considered, and real in 2026.

Atomic git workflow - validates, commits, pushes, creates PR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure.

Lightweight git hook integration for updating agents-docs with minimal tokens. Triggered on commit/merge events to sync documentation.

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence.

Self-learning fix loop - commit, push, monitor CI, auto-fix failures using swarm agents with skills on demand, loop until all checks pass.

Lint and test shell scripts using ShellCheck and BATS. Use when checking bash/sh scripts for errors, writing shell script tests, fixing ShellCheck warnings, setting up CI/CD for shell scripts, or improving bash code quality.

TRIZ inventive principles applied to audio timeline segmentation problems

Automated code review with PR analysis, change summaries, and quality checks. Use for reviewing pull requests, generating review comments, checking against best practices, and identifying potential issues. Includes style guide compliance, security issue detection, and review automation.