Development

Auto-detect project linter and run it. Internal utility skill used by feature-flow commands for the lint phase.

Detect repository hosting service (GitHub/GitLab) from git remote and extract owner/repo/project_path. Internal utility skill used by commands that need platform-aware routing.

Push current branch, create MR/PR, wait for CI pipeline, merge, and clean up branch using auto-mr CLI

Manage Go tool dependencies using the tool directive (Go 1.24+). Use when a Go project needs code generation tools like sqlc, moq, templ, swag, or stringer managed as reproducible Go tool dependencies.

Recommend and scaffold Go project layouts based on project type (CLI, API, library, monorepo). Internal skill used by golang-pro agent when initializing projects or reviewing structure.

Detect white box Go tests and propose conversion to black box tests (package foo_test). Internal skill used by golang-pro agent to enforce black box testing conventions.

Integrate Charmbracelet gum for beautiful, TTY-safe terminal output in bash scripts. Internal skill used by bash-pro agent for interactive prompts, styled output, and structured logging.

estimate CC active time for a task using the time rule, with dynamic effort resolution

measure your real CC throughput against the time rule's matrix, using lore.db

Comprehensive optimization audit with two modes and a single tier. Planning mode designs performance strategy, capacity planning, and scaling architecture. Audit mode scans code and infrastructure for performance anti-patterns, inefficient algorithms, N+1 queries, missing caching, concurrency issues, and resource waste. Single tier — optimization tools are overwhelmingly free/open-source. Use when asked to "optimization audit", "performance review", "find bottlenecks", "optimize this", "check...

walk the user through a low/medium/high effort A/B/C throughput benchmark on their current model

capture decisions, lessons, reminders, and todos into the lore knowledge graph

query the lore knowledge graph for sessions, costs, tools, projects, search, and patterns

all /lore intents, examples, and setup

explore relationships in the lore knowledge graph - cooccurring files, project sessions, sibling sessions, tagged notes

export the lore knowledge graph or its slices to json, csv, or markdown

See active Claude Code sessions on this machine and coordinate across them via direct messages, status announcements, and file-overlap awareness. Triggers when the user asks "who else is running?", "any other claude open?", "what other sessions are active?", "tell <name> to ...", "ping <peer>", "let peers know I'm doing X", "broadcast <status>", "check the cc digest", or any cross-session / multi-agent coordination on this machine.

Comprehensive documentation audit with two modes and a single tier. Planning mode designs documentation strategy, content type maps, learning paths, and scaffolding architecture. Audit mode evaluates linguistic precision (Strunk & White, Google/Microsoft style guides), structural taxonomy (Diataxis quadrant classification, Good Docs Project), pedagogical scaffolding (Carroll's Minimalism, Cognitive Load Theory, Merrill's First Principles, Lemov techniques), cross-document consistency, reposit...

Comprehensive cognitive interface audit with two modes and a single tier. Planning mode designs task models, user expertise mapping, and error tolerance strategy. Audit mode evaluates mental model alignment (Norman's Gulfs), consistency (Gestalt), error tolerance (Wood 7-layer defense), cognitive load (NASA-TLX, Dual-Process), visual grounding (Gergle), trust calibration (Lee & See), data visualization integrity (Kirk, Cleveland & McGill, Brewer ColorBrewer palette enforcement), ecological co...

Creates interactive C4 model architecture diagrams using Structurizr DSL — the official C4 notation by Simon Brown. Produces self-contained single-file HTML visualizations with embedded SVGs rendered locally via Java 21+ and the Structurizr export pipeline (structurizr.war + plantuml.jar). Generates System Context, Container, Component, Dynamic, and Deployment diagrams with tabbed navigation, DSL panel, and copyable Structurizr DSL source. Requires Java 21+. Use when the user asks for archite...

Comprehensive architecture audit with two modes and a single tier (beta). Planning mode evaluates architectural patterns, bounded context decomposition, dependency direction, and SOLID compliance for new systems. Audit mode scans existing codebases for architectural drift, coupling violations, domain model quality, dependency direction violations, and structural anti-patterns. Grounded in Hexagonal Architecture (Cockburn), Domain-Driven Design (Evans/Vernon), Clean Architecture (Martin), SOLI...

Use when writing or modifying any function, method, class, or source file in a repo using repo-hygiene — public API, internal helpers, and new files all require docstrings; only one-line lambdas and trivial accessors are excluded

Use when drafting any commit message — sets format (imperative subject under 72 chars, explanatory body when the why isn't obvious from the diff) and prevents the "Fix X" one-liner reflex for non-trivial fixes

Use when starting any conversation in a repo — establishes the repo-hygiene skill set and the moments each sub-skill applies