All authors
Claude Skills by lawzava
github.com/lawzava16 skills0 installs39 views
- Autonomous RunUse when an approved goal must continue unattended across many steps, milestones, context resets, or sessions, including keeping a pull request moving until it is merge-ready.Votes: 0GitHub stars: 7
- Design And PlanUse to specify non-trivial behavior or interfaces, resolve requirements or tradeoffs, or produce a multi-step implementation plan. Do not use for a mechanical edit, routine status update, or execution of a settled plan.Votes: 0GitHub stars: 7
- Evidence ResearchUse to research a decision that needs evidence beyond the repository, such as current upstream behavior, historical rationale, cross-system incidents, or contested claims. Do not use for repository-only code tracing or a summary of provided material.Votes: 0GitHub stars: 7
- Grill MeUse when the user asks to be grilled, or wants a plan, decision, idea, or draft stress-tested through a structured interview before any action.Votes: 0GitHub stars: 7
- Humanizing ProseUse when the task itself is to draft, rewrite, edit, or preserve human-facing prose for clarity, attribution, or proportion; do not select merely because other work ends with a response.Votes: 0GitHub stars: 7
- Independent ReviewUse when security, auth, billing, concurrency, data integrity, or another high-stakes artifact needs adversarial review by a provider other than its author.Votes: 0GitHub stars: 7
- Mcp SetupUse when installing, configuring, debugging, or verifying an MCP server for a harness, or when a configured server's tools are missing or failing.Votes: 0GitHub stars: 7
- Memory HygieneUse when auditing, pruning, correcting, refreshing, or automatically applying approved evidence-based cleanup to native harness memory.Votes: 0GitHub stars: 7
- OrchestratingUse when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination.Votes: 0GitHub stars: 7
- Safe EffectsUse when preparing a deploy, message, charge, migration, destructive query, DNS change, external API write, or any action with a real-world side effect.Votes: 0GitHub stars: 7
- Systematic DebuggingUse when a bug, failing or flaky test, production incident, unexpected output, or performance regression has an unknown cause.Votes: 0GitHub stars: 7
- Test First ImplementationUse when adding or changing behavior, fixing a confirmed bug, refactoring executable code, or implementing a feature with tests.Votes: 0GitHub stars: 7
- Upgrading MegapowersUse when asked to update, upgrade, refresh, reinstall, or migrate Megapowers, check for a newer release, or repair stale installed plugin state.Votes: 0GitHub stars: 7
- Verify And FinishUse to verify a completed outcome before claiming success, handing off, committing, merging, publishing, deploying, or closing a task. Do not use for an intermediate update, an isolated test run, or merely naming an oracle command.Votes: 0GitHub stars: 7
- Writing Agent InstructionsUse when creating, revising, or auditing an agent skill, AGENTS.md, CLAUDE.md, or nested project instructions, including trigger design, progressive disclosure, harness-aware scope, behavioral validation, and session retrospectives that turn agent mistakes into instruction or tooling changes.Votes: 0GitHub stars: 7
- Megapowers DoctorUse when Megapowers seems inactive or broken: a skill did not fire, the output style is missing, a hook errors or times out, or the user asks to check the Megapowers setup.Votes: 0GitHub stars: 7