Bash

terminal-ops is an evidence-first repo execution skill for terminal work. Use it to run commands, inspect git state, debug CI or builds, and make narrow fixes with proof of what changed and what was verified. This terminal-ops guide helps reduce guesswork for Code Editing and repo operations.

gateguard is a fact-forcing pre-action gate for Claude workflows. It blocks the first Edit, Write, or Bash attempt, then requires concrete investigation of importers, schemas, user instructions, and related files before allowing changes. Use this gateguard guide to reduce guessing and improve first-pass edits.

continuous-learning-v2 turns Claude Code sessions into project-scoped learning with hooks, observer agents, confidence scoring, and promotion of repeated patterns into skills, commands, or agents.

continuous-learning automatically extracts reusable patterns from Claude Code sessions and saves them as learned skills. It uses a Stop-hook flow, supports configurable thresholds in config.json, and is best for skill authors, repo maintainers, and power users who want a practical continuous-learning guide for session-end capture.

gstack-upgrade is the skill for updating gstack safely. It detects global vs vendored installs, runs the upgrade path, and summarizes what changed so you can verify the result. Use this gstack-upgrade guide for install and usage details, migration-aware behavior, and workflow automation cases.

The unfreeze skill clears the freeze boundary set by /freeze, allowing edits across all directories again without ending the session. Use unfreeze when you need to unlock edits, restore full access, or continue a Workflow Automation session after temporary restrictions. It is a focused control skill with straightforward unfreeze usage.

The investigate skill guides systematic debugging and root-cause analysis for broken, flaky, or unexpected behavior. Use it for code review, incident triage, bug fixes, and "it worked yesterday" cases when you need evidence before changing code. It follows a four-phase workflow: investigate, analyze, hypothesize, implement.

git-guardrails-claude-code adds a PreToolUse hook to block dangerous git commands before Claude Code runs them. Install it to prevent destructive pushes, hard resets, forced cleans, and branch deletes, with scoped control for this project or all projects. Useful when you need git-guardrails-claude-code for Access Control boundaries in Claude Code.

shellcheck-configuration helps you install ShellCheck, tune .shellcheckrc, and apply lint policy for CI and Code Review across bash, sh, dash, and ksh projects.

bash-defensive-patterns helps agents write safer Bash for production automation, CI/CD, and system scripts with strict mode, traps, cleanup, quoting, and input validation.

bats-testing-patterns helps you design maintainable Bats tests for shell scripts, including fixtures, setup and teardown, exit codes, stderr checks, and CI-safe patterns for Bash, sh, and dash automation.

The configuring-aws-verified-access-for-ztna skill helps you design and configure AWS Verified Access for VPN-less zero trust network access with identity and device posture checks in Cedar. Use this configuring-aws-verified-access-for-ztna guide for access control planning, trust providers, group policies, and endpoint setup.

dwarf-expert helps you inspect DWARF v3-v5 debug info, read DIE trees and attributes, verify data integrity, and review code that parses or emits DWARF. Use the dwarf-expert skill when you need accurate, evidence-based answers for compiled binaries, debug sections, or backend development tooling.

burpsuite-project-parser searches and extracts data from Burp Suite project files (.burp) using Burp Suite Professional and the burpsuite-project-file-parser extension. Use it for security audit findings, proxy history, site map entries, and regex searches across captured HTTP traffic.

wordpress-router is a WordPress triage skill that classifies a repo fast and routes agents to the right workflow before edits. It helps with plugins, classic themes, block themes, Gutenberg, WordPress core checkouts, and full site repos, making wordpress-router useful for Agent Orchestration.

polyphony is a multi-agent orchestration skill for container-isolated workspaces. It runs each agent session in its own Docker container and git branch, making parallel work, verification, and clean landing safer for Multi-Agent Systems.

Learn terraform-search-import for discovering supported cloud resources with Terraform Search and bulk importing them into Terraform state. This terraform-search-import skill is useful for backend development, audits, and migration workflows when you want a practical guide to install, verify provider support, and start usage with less guesswork.

install-duckdb helps install or update DuckDB extensions from the CLI. Use plain extension names for core installs, or name@repo for repository-based extensions. The skill checks for DuckDB first, handles --update separately, and turns a simple request into valid DuckDB INSTALL commands with less guesswork.

read-memories is a Claude Code skill for searching prior session logs to recover decisions, patterns, unresolved TODOs, and user corrections. Use it when a task depends on earlier context, across ongoing projects, or for read-memories for Workflow Automation. The read-memories skill helps agents find evidence quickly instead of guessing from memory.

The using-tmux-for-interactive-commands skill helps you run interactive CLI tools in detached tmux sessions. Use it for editors, REPLs, git rebase -i, and other terminal apps that need real-time input/output. It is a practical guide for Workflow Automation when you need start, send, capture, and stop control.

Use the slack-messaging skill to send or read Slack messages, check channels, test Slack integrations, and interact with a Slack workspace from the command line with slackcli for workflow automation.

x-post is a command-line skill for posting to X (Twitter) with text, images, or video. Use the x-post guide to install and run it from the terminal, confirm the exact post text, and publish with local credentials and media files.

acquiring-disk-image-with-dd-and-dcfldd helps Security Audit and forensic users create a defensible bit-for-bit disk image with dd or dcfldd, using write protection, hash verification, and a clear acquisition workflow for incident response and evidence handling.

guard is a full safety mode for Workflow Automation that combines destructive-command warnings with directory-scoped edit restrictions. Use the guard skill to guard against mistakes, lock down edits, and block risky commands like rm -rf or force-pushes when working near production or live data.