aiming-lab/metaclaw
36 skills · 291 total installs
$npx skills add aiming-lab/metaclawSkillInstalls
avoid-hallucinating-specificsCommon mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain.structured-step-by-step-reasoningUse this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic.codebase-navigationUse this skill when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system works.graceful-error-recoveryUse this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach.secure-code-reviewUse this skill when reviewing or writing code that handles user input, authentication, file I/O, network requests, or database queries.uncertainty-acknowledgmentUse this skill when you are not sure about a fact, have outdated knowledge, or the question is contested.data-validation-firstUse this skill before any data analysis, transformation, or modeling.task-decompositionUse this skill when a user presents a large, vague goal. Break it into concrete, ordered sub-tasks before starting any work.async-communication-etiquetteUse this skill when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up…plan-before-multi-step-executionUse this skill before executing a sequence of 3 or more steps, especially when steps are irreversible or depend on each other.structured-progress-updateUse this skill when summarizing progress on an ongoing project or multi-step task.auth-and-authorization-patternsUse this skill when implementing authentication (login, token issuance) or authorization (access control, permissions).verify-before-irreversible-actionUse this skill before taking any action that is hard to reverse — deleting files, overwriting data, sending messages, pushing to remote, modifying production…agent-task-handoffUse this skill when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions.visualization-selectionUse this skill when creating charts, plots, or dashboards. Choose the visualization type that best communicates the data relationship before writing any…sql-best-practicesUse this skill when writing SQL queries — selects, joins, aggregations, window functions, or schema modifications.input-validation-and-sanitizationUse this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input.prioritize-by-impactUse this skill when the user has a list of tasks and needs help deciding what to do first.secrets-managementUse this skill when handling API keys, passwords, tokens, private keys, or any sensitive credential.source-evaluationUse this skill when presenting information from external sources, citing research, or answering factual questions.structured-logging-and-observabilityUse this skill when building production services, pipelines, or automation that needs to be debugged, monitored, or audited.technical-writing-clarityUse this skill when writing documentation, READMEs, technical specs, runbooks, or any text that explains a system or process to other engineers.audience-aware-communicationUse this skill when writing any explanation, documentation, or response that will be read by someone else.avoid-acting-on-assumptionsCommon mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question first.avoid-scope-creepCommon mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change.clarify-ambiguous-requestsUse this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways.context-window-managementUse this skill in long conversations or multi-turn agentic sessions where context may be lost or the conversation is approaching token limits.debug-systematicallyUse this skill when diagnosing a bug, unexpected behavior, test failure, or any situation where code does not behave as expected.do-not-retry-without-diagnosisCommon mistake — retrying the same failing command or API call without understanding why it failed. Always diagnose the root cause before retrying anything.git-workflowUse this skill when working with git — making commits, creating branches, resolving merge conflicts, opening pull requests, or reviewing diffs.idempotent-script-designUse this skill when writing scripts, cron jobs, data pipelines, or any automated process that may be run multiple times.professional-email-draftingUse this skill when drafting emails, Slack messages, announcements, or any external/internal communication.robust-error-handling-in-scriptsUse this skill when writing shell scripts, Python automation, or any unattended batch job.structured-research-workflowUse this skill when conducting research on a topic from scratch — literature review, competitive analysis, technical due diligence, or fact-finding.test-before-shipUse this skill when implementing a new feature or fixing a bug. Write or update tests before marking the task done.tool-selection-strategyUse this skill when deciding which tools to call in an agentic workflow.