All authors
Claude Skills by This-HW
github.com/This-HW39 skills0 installs37 views
- Agent CreatorCreate Claude Code sub-agents with optimal configuration. Use when users ask to create a new agent, custom agent, specialized assistant, or want to configure task-specific AI workflows.Votes: 0GitHub stars: 4
- Agent TeamsSUPERSEDED by control-loop (kept through claude-code-kit 2.x; removed in the successor hiway-kit) — large-scale parallel work guidance. Routes 10+ parallel independent tasks to native dynamic workflows, with legacy experimental Agent Teams as fallback. See control-loop for the current multi-session delegation discipline.Votes: 0GitHub stars: 4
- Auto DevAutomated development pipeline. Runs a completed Planning Work through Development and Validation phases end-to-end.Votes: 0GitHub stars: 4
- BrainstormingDesign and spec before any planning or code. MUST USE before new features, creative work, or any implementation. Explores requirements, proposes approaches, gets design approval, then chains to plan-task.Votes: 0GitHub stars: 4
- DebugAnalyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.Votes: 0GitHub stars: 4
- Doc CoauthoringAI-assisted documentation authoring. Use when writing, reviewing, or updating technical documents and READMEs.Votes: 0GitHub stars: 4
- Eval ForgeTurn an observed agent defect into a machine-checkable eval scenario, generated and self-validated in one step. Use after a defect lands in the feedback ledger, or before changing an agent definition that has no eval coverage. Trigger with /eval-forge.Votes: 0GitHub stars: 4
- Harness ExportExport the kit's host-neutral rules to AGENTS.md so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /harness-export.Votes: 0GitHub stars: 4
- Mcp BuilderBuild and configure MCP servers. Use when scaffolding a new Model Context Protocol server or adding tools to an existing one.Votes: 0GitHub stars: 4
- Multi Perspective ReviewMulti-perspective collaborative review of plans or documents. Ten expert viewpoints deliberate in 3 rounds to reach consensus.Votes: 0GitHub stars: 4
- Native WatchAudit Claude Code native feature absorption. Use to compare the kit's components against the latest Claude Code releases and propose absorption-ledger updates. Trigger with /native-watch or on a schedule.Votes: 0GitHub stars: 4
- Plan TaskStructured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.Votes: 0GitHub stars: 4
- ReviewRun a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.Votes: 0GitHub stars: 4
- Self ImprovePropose improvements to agent/skill/rule definitions from accumulated feedback-ledger defects and eval reports. Proposal-only - applies changes exclusively after evals show no regression AND the user approves. Trigger with /self-improve.Votes: 0GitHub stars: 4
- Skill CreatorCreate new Claude Code skills. Applies standard templates and best practices to scaffold a skill file automatically.Votes: 0GitHub stars: 4
- Skill ForgeDistill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge.Votes: 0GitHub stars: 4
- TestRun tests and auto-fix failures. Detects the test framework, executes tests, and iterates on fixes until all pass.Votes: 0GitHub stars: 4
- Using Claude Code KitSession-start meta-skill. claude-code-kit-specific workflow chain, agent map, and Work system rules (generic skill-invocation discipline is shared with superpowers when present).Votes: 0GitHub stars: 4
- Web ResearchResearch external information using MCP servers. Use when users need to find documentation, compare technologies, or research best practices.Votes: 0GitHub stars: 4
- Child SessionDiscipline a worker session loads at dispatch time — verify the brief's premises before implementing, work only on its own branch, and report in the fixed completion format. Use when a session has been dispatched as a worker (child) with a brief from a parent control session.Votes: 0GitHub stars: 4
- Control LoopMulti-session control discipline for delegating work to worker sessions — investigate, decide, dispatch, verify, and merge. Use when a session is coordinating separate worker sessions or worktrees and needs to know when to delegate versus decide, and how to verify before merging.Votes: 0GitHub stars: 4
- Eval ForgeTurn an observed agent defect into a machine-checkable eval scenario, generated and self-validated in one step. Use after a defect lands in the feedback ledger, or before changing an agent definition that has no eval coverage. Trigger with /eval-forge.Votes: 0GitHub stars: 3
- Native WatchAudit Claude Code native feature absorption. Use to compare the kit's components against the latest Claude Code releases and propose absorption-ledger updates. Trigger with /native-watch or on a schedule.Votes: 0GitHub stars: 3
- Self ImprovePropose improvements to agent/skill/rule definitions from accumulated feedback-ledger defects and eval reports. Proposal-only - applies changes exclusively after evals show no regression AND the user approves. Trigger with /self-improve.Votes: 0GitHub stars: 3
- Agent CreatorCreate a Claude Code sub-agent definition for this project or user. Use when the user asks to create a new custom agent or a specialized sub-agent for a recurring task.Votes: 0GitHub stars: 3
- Auto DevAutomated development pipeline. Runs a completed plan file through Development and Validation phases end-to-end.Votes: 0GitHub stars: 3
- BrainstormingDesign and spec a Large new feature or system change before planning - explores requirements, proposes approaches, gets design approval, then chains to plan-task. Skip for bug fixes and Small/Medium work; go straight to plan-task or just do it.Votes: 0GitHub stars: 3
- Child SessionDiscipline a worker session loads at dispatch time — verify the brief's premises before implementing, work only on its own branch, and report in the fixed completion format. Use when a session has been dispatched as a worker (child) with a brief from a parent control session.Votes: 0GitHub stars: 3
- Control LoopMulti-session control discipline for delegating work to worker sessions — investigate, decide, dispatch, verify, and merge. Use when a session is coordinating separate worker sessions or worktrees and needs to know when to delegate versus decide, and how to verify before merging.Votes: 0GitHub stars: 3
- Cross Engine ReviewReach an evidence-backed decision between sessions running on different agent engines. Use when a call is high-stakes enough that one engine's blind spots are a real risk, and a second session with different tool access can bring evidence the first cannot.Votes: 0GitHub stars: 3
- DebugInvestigate a failure whose cause is not evident from the error itself - flaky or intermittent failures, failures that only happen in CI or one environment, or errors with several plausible causes across files - by reproducing, isolating, fixing and verifying. Skip it when the message already shows the fix (a missing variable, a typo, a wrong import); just fix that directly.Votes: 0GitHub stars: 3
- Harness ExportExport the kit's host-neutral rules to every harness entrypoint file (AGENTS.md, GEMINI.md) so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Gemini CLI, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /harness-export.Votes: 0GitHub stars: 3
- Multi Perspective ReviewMulti-perspective review of a plan or design document. Up to ten viewpoints deliberate in 3 rounds; the main session orchestrates, with a sequential path for harnesses without subagents.Votes: 0GitHub stars: 3
- Plan TaskStructured task planning into a plan file. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.Votes: 0GitHub stars: 3
- ReviewReview current changes or specified files - ruff lint for Python files, an adversarial review-code pass, and a security scan only when security-sensitive files changed.Votes: 0GitHub stars: 3
- Skill ForgeDistill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge.Votes: 0GitHub stars: 3
- TestRun tests and auto-fix failures. Detects the test framework, executes tests, and iterates on fixes until all pass.Votes: 0GitHub stars: 3
- Using Hiway KitSession-start meta-skill (hook-injected). Kit workflow chain and plan file rules.Votes: 0GitHub stars: 3
- Web ResearchMulti-source external research with cited sources, using search/docs MCP servers when installed and built-in web tools otherwise. Use when a question needs several external sources compared or synthesized, or a web task needs the user's logged-in browser. Not for a single quick lookup.Votes: 0GitHub stars: 3