Browse Skills

Kiro Impl implements approved tasks using test-driven development and subagent dispatch. It runs all pending tasks autonomously or selected tasks manually, verifying tests pass before marking tasks complete.

Kiro Impl implements approved tasks using test-driven development and native subagent dispatch, running pending tasks autonomously or selected tasks manually.

Kiro Spec Batch generates complete specs (requirements, design, tasks) for all pending roadmap features by dispatching parallel subagents grouped by dependency waves, then runs a cross-spec consistency review. Use it when briefs exist for all features and you want spec-driven development specs created in dependency order.

Kiro Spec Design creates comprehensive technical designs for specifications, mapping requirements to components, interfaces, and file structures after discovery research and synthesis. Use it to produce design documents that guide implementation tasks in spec-driven development.

Kiro Spec Design generates comprehensive technical designs that translate requirements into architecture through a discovery process. Use it when creating architecture from requirements or extending an existing system.

Kiro Spec Quick generates specification files for a feature by running four phases—initialize spec, requirements, design, and tasks—with interactive or automatic modes. Use it to quickly scaffold a spec-driven development workflow and sanity-check the generated artifacts.

Kiro Steering Management maintains {{KIRO_DIR}}/steering/ as persistent project knowledge, bootstrapping core steering files from the codebase and syncing them as the project evolves. Use it to keep AI agents' shared context aligned with codebase patterns and principles.

Spec Batch creates complete specification files (spec.json, requirements.md, design.md, tasks.md) for all features in a roadmap by dispatching sub-agents in dependency-ordered waves. Use it when you need to generate specs for a whole project roadmap and verify cross-spec consistency.

Bug Bounty Local Toolkit provides the complete bug-bounty workflow (recon, learning, hunting, validation, reporting) and resolves local install paths for tools, wordlists, and clones. Use it when hunting from a local machine and you need to know where jhaddix, SecLists, trufflehog, ffuf, dalfox, or ghauri are installed, or as the full-workflow variant of the local toolkit.

Evidence Hygiene guides redaction of cookies, PII, and HAR files in bug-bounty evidence capture, ensuring sessions and user data are protected before screenshots or attachments are shared. Use it before any PoC capture to avoid leaking secrets.

Hunt Dispatch is a skill-set loader for the /hunt orchestrator. It fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set when /hunt receives a mode answer.

Lean Context compresses LLM context by up to 99% using 79 MCP tools, 10 read modes, 95+ shell patterns, and tree-sitter AST for 27 languages. Use it when reading files, running shell commands, searching code, or exploring directories.