Commands

mukul975/Threatswarm

Command Claude Code

Incident response workflow — triage, evidence collection, timeline, and IOC extraction.

adriannoes/awesome-agentic-ai

Command Claude Code

Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.

ChristopherKahler/base-v1

Command Claude Code

Command "orientation" from ChristopherKahler/base-v1, covering what, when to use, not for, role and style.

capitalparser/notebooklm-wiki-pipeline

Command Claude Code needs its repo

A workflow for sending a large PDF from Google Drive to NotebookLM, Google's document-analysis tool, and saving the resulting notes as Obsidian markdown files. It passes the file link rather than reading the PDF directly.

ForceInjection/forceinjection.github.io

Command Claude Code

Update a change - revise existing planning artifacts and keep them coherent (Experimental).

disler/agent-sandboxes

Command Claude Code

Complete plan and build workflow - creates plan then implements it.

arpitnath/claude-capsule-kit

Command Claude Code

Check and set up everything needed for /crew (agent teams, Go binaries).

FareedKhan-dev/claude-code-staff-engineer

Command Claude Code

Deprecated - use the senior-staff-engineer:brainstorming skill instead.

nota-america/forgecat-agent-profiles

Command Claude Code

You need to execute the following bash commands to clean up stale local branches that have been deleted from the remote repository.

LonelyHerbivore/Trellis-Herbivore

Command Claude Code

Initialize a Trellis-managed development session. If startup context was not injected automatically, manually load the equivalent compact context by following these steps.

EmilLindfors/a2a-rs

Command Claude Code

Review the current Rust diff (or specified files/PR) for idiomatic Rust patterns and hexagonal-architecture compliance, in one pass.

NetMindAI-Open/NarraNexus

Command Claude Code

Previous design had three half-aligned UX paths: Settings page showed text in the page, tray menu and startup auto-check both showed osascript dialogs. Symptoms in production.

Dubaoxu/distillation-skills

Command Claude Code

ARS full pipeline — research → write → review → revise → finalize.

vshvedov/elephant-goldfish

Command Claude Code

Independently review staged, unstaged and untracked changes, with explicit evidence and outcomes.

ruvnet/sublinear-time-solver

Command Claude Code

Automatically coordinate, format, and learn from Claude Code operations using hooks with MCP tool integration.

hamzafarooq/multi-agent-course

Command Claude Code

Produce docs/api-contract.md — the single source of truth the build agents build against. The stack and auth model come from the build configuration in docs/scope.md (resolved against .claude/stacks.md), not a fixed assumption.

mmiani/kotlin-kmp-claude-agent-skills

Command Claude Code

Execute a Kotlin Multiplatform ticket through isolated planning, implementation, validation, review, and PR delivery.

zhagqn/agentwork

Command Claude Code

A command named /brain that reads shared project rules before carrying out an operation.

Desko77/claude-code-skills-1c

Command Claude Code

A command for moving a project to another folder while keeping Claude Code's saved memory, sessions, and plans.

wei63w/pm-manager

Command Claude Code

Initialize local .pm governance; detect Spec Kit; if absent, analyze the repo and draft a PRD for user confirmation; after confirm/skip run a technical light scan.

coralogix/canopy

Command Claude Code

Run a pre-release checklist and report what's ready, what's not, and what needs attention.

Heuresis/Growth-Operator-Agency

Command Claude Code

Refresh PROJECT-STATE.md + memory index from current workspace state + tasks. Run at end of each working session OR whenever significant progress has been made so the next session boots without cold-read overhead.

MikeCodeur/killer-saas

Command Claude Code

Derive a story's screen from the design system. Autonomous path (the agent produces it) or brief path (an external tool produces it and the result comes back). Never freestyles outside the system.

ivangrynenko/cursorrules

Command Claude CodeCursor

Command "pr-assess" from ivangrynenko/cursorrules, covering custom command: pr assess, command usage, code review agent instructions, primary objectives and input data analysis.