aiming-lab/metaclaw

1

avoid-hallucinating-specifics Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with f…

aiming-lab/metaclaw

29

2

structured-step-by-step-reasoning Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before a…

aiming-lab/metaclaw

17

3

codebase-navigation Use this skill when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system…

aiming-lab/metaclaw

15

4

data-validation-first Use this skill before any data analysis, transformation, or modeling. Always inspect and validate the data before dra…

aiming-lab/metaclaw

12

5

graceful-error-recovery Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retryin…

aiming-lab/metaclaw

12

6

secure-code-review Use this skill when reviewing or writing code that handles user input, authentication, file I/O, network requests, or…

aiming-lab/metaclaw

12

7

uncertainty-acknowledgment Use this skill when you are not sure about a fact, have outdated knowledge, or the question is contested. Explicitly …

aiming-lab/metaclaw

12

8

plan-before-multi-step-execution Use this skill before executing a sequence of 3 or more steps, especially when steps are irreversible or depend on ea…

aiming-lab/metaclaw

11

9

task-decomposition Use this skill when a user presents a large, vague goal. Break it into concrete, ordered sub-tasks before starting an…

aiming-lab/metaclaw

11

10

async-communication-etiquette Use this skill when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not…

aiming-lab/metaclaw

10

11

structured-progress-update Use this skill when summarizing progress on an ongoing project or multi-step task. Give a clear, scannable status rep…

aiming-lab/metaclaw

10

12

auth-and-authorization-patterns Use this skill when implementing authentication (login, token issuance) or authorization (access control, permissions…

aiming-lab/metaclaw

9

13

verify-before-irreversible-action Use this skill before taking any action that is hard to reverse — deleting files, overwriting data, sending messages,…

aiming-lab/metaclaw

9

14

agent-task-handoff Use this skill when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessi…

aiming-lab/metaclaw

8

15

visualization-selection Use this skill when creating charts, plots, or dashboards. Choose the visualization type that best communicates the d…

aiming-lab/metaclaw

8

16

sql-best-practices Use this skill when writing SQL queries — selects, joins, aggregations, window functions, or schema modifications. Ap…

aiming-lab/metaclaw

7

17

technical-writing-clarity Use this skill when writing documentation, READMEs, technical specs, runbooks, or any text that explains a system or …

aiming-lab/metaclaw

7

18

input-validation-and-sanitization Use this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input. Valid…

aiming-lab/metaclaw

6

19

prioritize-by-impact Use this skill when the user has a list of tasks and needs help deciding what to do first. Rank by impact and urgency…

aiming-lab/metaclaw

6

20

secrets-management Use this skill when handling API keys, passwords, tokens, private keys, or any sensitive credential. Never hardcode s…

aiming-lab/metaclaw

6

21

source-evaluation Use this skill when presenting information from external sources, citing research, or answering factual questions. As…

aiming-lab/metaclaw

6

22

structured-logging-and-observability Use this skill when building production services, pipelines, or automation that needs to be debugged, monitored, or a…

aiming-lab/metaclaw

6

23

audience-aware-communication Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match voca…

aiming-lab/metaclaw

5

24

avoid-acting-on-assumptions Common mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question fir…

aiming-lab/metaclaw

5

25

avoid-scope-creep Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked f…

aiming-lab/metaclaw

5

26

clarify-ambiguous-requests Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If pr…

aiming-lab/metaclaw

5

27

context-window-management Use this skill in long conversations or multi-turn agentic sessions where context may be lost or the conversation is …

aiming-lab/metaclaw

5

28

debug-systematically Use this skill when diagnosing a bug, unexpected behavior, test failure, or any situation where code does not behave …

aiming-lab/metaclaw

5

29

do-not-retry-without-diagnosis Common mistake — retrying the same failing command or API call without understanding why it failed. Always diagnose t…

aiming-lab/metaclaw

5

30

git-workflow Use this skill when working with git — making commits, creating branches, resolving merge conflicts, opening pull req…

aiming-lab/metaclaw

5

31

idempotent-script-design Use this skill when writing scripts, cron jobs, data pipelines, or any automated process that may be run multiple tim…

aiming-lab/metaclaw

5

32

professional-email-drafting Use this skill when drafting emails, Slack messages, announcements, or any external/internal communication. Apply pro…

aiming-lab/metaclaw

5

33

robust-error-handling-in-scripts Use this skill when writing shell scripts, Python automation, or any unattended batch job. Ensure failures are detect…

aiming-lab/metaclaw

5

34

structured-research-workflow Use this skill when conducting research on a topic from scratch — literature review, competitive analysis, technical …

aiming-lab/metaclaw

5

35

test-before-ship Use this skill when implementing a new feature or fixing a bug. Write or update tests before marking the task done. N…

aiming-lab/metaclaw

5

36

tool-selection-strategy Use this skill when deciding which tools to call in an agentic workflow. Always choose the minimal, most direct tool …

aiming-lab/metaclaw

5