Loading...
Loading...
Found 159 Skills
Apply documentation standards: comment why not what, minimal comments (prefer clear code), maintain README with quick start, update docs with breaking changes. Use when writing comments, creating docs, reviewing documentation, or discussing what to document.
Unblock a PR: resolve conflicts, fix CI, address reviews. Composes: git-mastery conflict resolution, /fix-ci, /respond, /address-review. Use when: PR is blocked by conflicts, red CI, or unaddressed review feedback.
Generate high-quality voiceover audio with ElevenLabs. Includes word-level timestamps for video sync. Use when: creating demo narration, video voiceover, podcast intros, or any TTS need. Keywords: voiceover, TTS, text to speech, ElevenLabs, narration, audio, timestamps.
LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and reliability - Implementing cost-based or latency-based routing - A/B testing different models - Self-hosting an LLM proxy Keywords: openrouter, litellm, llm gateway, model routing, fallback, A/B testing
Apply Convex database best practices for cost optimization, performance, security, and architecture. Use when: building Convex backends, optimizing queries, handling embeddings/vector search, reviewing Convex code, designing schemas, planning migrations, or discussing Convex architecture. Keywords: Convex, real-time database, queries, mutations, actions, indexes, pagination, vector search, embeddings, schema, migrations, ctx.auth, convex-helpers, bandwidth.
Fix issues found by stripe-audit. Reconciles configuration drift, fixes code patterns, and resolves discrepancies.
Session retrospective and codification. Run at the end of any significant session to extract learnings, update documentation, and create artifacts that make future sessions smoother. Invoke when: - Finishing a multi-step implementation - After debugging a hard problem - End of any session with 3+ tool calls - "what did we learn?" / "wrap up" / "done" Subsumes /codify-learning (codification is one output, not the only one).
Orchestrate comprehensive code review across ~12 AI reviewers. 5 persona reviewers (Grug, Carmack, Ousterhout, Beck, Fowler) via Moonbridge, 4 domain specialists (security-sentinel MANDATORY, performance, data integrity, architecture) via Task, plus hindsight-reviewer and synthesis. Use when: code review, PR review, pre-merge quality check.
Investigates and analyzes an idea or codebase area before committing to changes. Pure research, no writes. Trigger: /sdd-explore <topic>, explore, investigate codebase, research feature, analyze before changing.
Run /check-posthog, then create GitHub issues for all findings. Each finding becomes a separate, actionable issue with clear acceptance criteria. Invoke for: PostHog audit to issues, analytics backlog creation.
Programmatic visual asset pipeline for proposal-context logos and images. Uses Recraft, OpenAI Image, and Nano Banana Pro together with phase-aware breadth vs convergence.
Generate custom lint rules from architectural patterns. ESLint local plugins (JS/TS) or ast-grep YAML rules (Python/Go/Rust/any). Invoke when: codifying an import boundary, enforcing API conventions, blocking deprecated patterns, or any "always/never" constraint.