All Skills

Configure cli-progress with custom formatters, multi-bar support, and ETA calculations for CLI progress indication.

Call genes and annotate basic features for prokaryotes, viruses, and eukaryotes.

Resolving git merge conflicts. Use when rebasing, merging, or cherry-picking results in conflicts.

This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think", "second opinion on code", "consult the oracle", "ask the oracle", or mentions using an AI oracle for planning or code review. NOT for implementation tasks.

# Market Research Determine if a book is worth writing from a business perspective, specifically for Amazon KDP self-publishing. ## Core Philosophy **Commercial viability is separate from intellectual merit.** A brilliant idea can fail commercially. A mediocre idea can succeed. This skill assess

Build repeatable data-to-Docs pipelines from Sheets and Drive sources. Use for automated status reports, template-based document assembly, and scheduled publishing workflows.

This skill should be used when the user asks to "configure Biome", "extend biome config", "set up BiomeJS", "add biome overrides", "biome lint-staged", "fix biome errors", or mentions biome.jsonc, Biome linting, or Biome formatting configuration.

View execution logs, event history, and debugging information.

Audits deep link contracts and routing behavior. Use when validating

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

Query JGI Lakehouse (Dremio) for genomics metadata across GOLD/IMG/Mycocosm/Phytozome and download genome files via IMG taxon OIDs.

Uploads promo videos and content to Cloudflare R2 or AWS S3. Use when the user wants to host promo content for social media or distribution.

Type-safe CLI argument parsing with cleye. Use when writing CLI scripts, adding flags or parameters to Bun scripts, or parsing command-line arguments.

This skill should be used when the user asks to "create a bootstrap prompt", "handoff", "save session state", "continue in new session", "create handoff", "session summary for continuation", "bootstrap for fresh session", or wants to capture the current session state for resumption in a new Claude Code session.

Expert discovery call strategist for B2B sales. Use when preparing for discovery calls, qualifying prospects, asking effective questions, identifying pain points, mapping stakeholders, or documenting findings. Covers SPIN selling, active listening, budget/timeline qualification, competition discovery, and CRM documentation. Use for sales qualification, needs analysis, and discovery call execution.

Manually merge parallel development tracks. Debug/Expert command - track merging normally happens automatically via /devteam:implement.

Sets up or edits the plugin configuration file interactively. Use on first-time setup, when config is missing, or when the user wants to change settings.

Use when choosing the right modern Python tooling workflow for a project or script (uv setup, quality tools, CLI, logging, packaging) or when unsure which Python tooling skill applies.

Writes Google Ads copy including RSA headlines, descriptions, extensions, DKI, and CTAs mapped to search intent. Use when creating or optimizing Google Search campaigns, diagnosing Quality Score issues, or building complete ad groups from keyword research through final copy.

Skill for configuring Orchard Core deployment plans and steps. Covers deployment plan creation, content export/import, and deployment step configuration.

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

Generate visual representations of algorithm execution

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.