Always invoke this skill for any git-related request (commit messages, staging review, history, PR descriptions, etc.) so git workflows are handled consistently.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.5 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Prepare a lading release. Updates CHANGELOG.md, bumps version in Cargo.toml, updates Cargo.lock, commits, and creates a PR.

This skill should be used when the user asks to "autofix pr", "fix pr locally", "fix ci failures", "fix review comments", "iterate on pr", "fix failing checks", "fix pr comments", "make ci green", "fix the build", "address reviewer feedback", or wants to iteratively fix CI failures and review comments on a GitHub PR from the local CLI.

Apply modern Go syntax guidelines based on project's Go version. Use when user ask for modern Go code guidelines.

This skill should be used when the user says "prototype lock", "lock prototype", "arn prototype lock", "freeze prototype", "preserve prototype", "snapshot prototype", "protect prototype", "archive prototype", "save the prototype", "don't overwrite the prototype", "lock the design", "freeze the design", or wants to create a frozen snapshot of the validated prototype before development begins, preventing production code from overwriting the validated reference artifact.

Optional customization tool for greenfield projects. This skill should be used when the user says "greenfield init", "arn spark init", "initialize greenfield", "setup greenfield", "greenfield setup", "start greenfield", "configure greenfield", "set up greenfield", "init greenfield", "greenfield configuration", "review greenfield config", "customize greenfield config", "greenfield settings", "Figma setup", "Canva setup", "add Figma", "add Canva", "design tool setup", or wants to customize Arness Spark configuration, add design tool integrations (Figma, Canva), or review current greenfield settings. Arness Spark auto-configures with sensible defaults on first skill invocation — this init is optional. Design tool integration (Figma/Canva) remains available only through this skill.

This skill should be used when the user says "pick issue", "work on issue", "arness code pick", "arness code pick issue", "arn-code-pick-issue", "grab issue", "pick from backlog", "what should I work on", "show issues", "find issue", "browse issues", "next issue", "select issue", "choose issue", "what's unblocked", "work on next feature", "pick from feature tracker", or wants to browse issues filtered by Arness labels, select one, and route it to the appropriate Arness pipeline skill for implementation. Supports local-first dependency resolution from a greenfield feature backlog when available. Requires an issue tracker (GitHub or Jira) to be configured for remote issue browsing. Do NOT use this for creating new issues — use /arn-code-create-issue for that.

This skill should be used when the user says "bug spec", "arness code bug spec", "investigate this bug", "help me debug", "trace this bug", "diagnose this issue", "I found a bug", "something is broken", "why is X not working", "fix this bug", "debug this", "why is this not working", or wants to iteratively investigate a bug through guided conversation with diagnostic analysis. Bridges the gap between a bug report and either a direct fix or a structured bug specification for the Arness pipeline.

This skill should be used when the user says "simplify", "arness code simplify", "simplify code", "code simplification", "clean up code", "reduce complexity", "remove duplication", "check for reuse", "find duplicates", "optimize code", "efficiency review", "simplify implementation", "arn-code-simplify", or wants to review recently implemented code for reuse opportunities, quality issues, and efficiency problems after execution completes. Do NOT use this for full implementation correctness review (use arn-code-review-implementation) or PR review (use arn-code-review-pr).

This skill should be used when the user says "deploy", "deploy to staging", "deploy to production", "promote to production", "infra deploy", "arn infra deploy", "deploy infrastructure", "apply infrastructure", "push to prod", "go live", "tofu apply", "terraform apply", "pulumi up", "cdk deploy", "fly deploy", "deploy to railway", "release to prod", "promote environment", or wants to execute a deployment of their infrastructure to a target environment. This skill handles environment promotion, CI/CD enforcement, cost gates, safety layers, and resource tracking.

This skill should be used when the user says "document infra change", "infrastructure documentation", "generate runbook", "infra docs", "arn infra document", "create infra changelog", "document infrastructure", "generate infrastructure docs", "infra documentation", "create runbook", "generate changelog", "arn-infra-document-change", or wants to generate operational documentation (runbooks, architecture updates, changelogs, environment docs) from completed infrastructure changes.

This skill should be used when the user says "infra help", "arn infra help", "where am I in the pipeline", "what's next for infra", "infra status", "pipeline status", "infra pipeline", "arn-infra-help", "show infra pipeline", "what step am I on for infra", "infra workflow", "infrastructure status", "show infrastructure pipeline", or wants to see their current position in the Arness Infra workflow and get guidance on the next step. This skill detects whether the user is in Quick (interactive) mode or Full Pipeline mode and renders an ASCII diagram with the active stage marked.

This skill should be used when the user says "discover tools", "infra discover", "arn infra discover", "arn-infra-discover", "audit tools", "check installed tools", "what tools do I have", "scan for MCPs", "check provider tools", "tool discovery", "discover infrastructure tools", "check my setup", "infra tooling", or wants to audit their installed infrastructure tools (MCPs, CLIs, Claude Code plugins), check authentication state, search for new official tools online, and produce a tooling manifest for the infrastructure workflow.

Use this skill when the user asks to "set up parsing", "create parsing rule", "extract fields from logs", "regex extraction", "log parsing", "enrich logs", "add context to logs", "custom enrichment table", "lookup table", "geo enrichment", "create metric from logs", "events to metrics", "convert logs to metrics", "generate metrics from events", "recording rule", "precomputed metrics", "PromQL recording", "configure data pipeline", "transform log data", "data processing rules", "rule group", "enrichment settings", "E2M definition", "labels cardinality", "bulk delete rules", "enrichment limits", "search enrichment table", or wants to configure how Coralogix processes, enriches, or transforms ingested data.

Set up a new Django 6.0 project with modern tooling (uv, direnv, HTMX, OAuth, DRF, testing). Use when the user wants to create a Django project from scratch with production-ready configuration.

Generate agent-ready prompts from existing task specification files. Use when regenerating prompts after editing tasks, updating prompt templates, or preparing tasks for cpo execution.

Use when debugging JavaScript errors, checking console warnings, analyzing browser logs, finding runtime errors, investigating console output, or troubleshooting browser issues. Provides console message analysis.

Create a new Claude Code slash command with proper YAML frontmatter structure. Use when the user wants to add a custom slash command to a plugin. Handles command file creation with description, argument hints, allowed tools, and all advanced features.