openclaw-coding-skills

Execute implementation work in small, reviewable slices inside OpenClaw. Use when the request is to "implement this", "make the code change", "add this behavior", "wire this up", or "patch this without rewriting everything", especially when the change should stay narrow and be verified immediately.

Triage and resolve failures inside an OpenClaw workspace with a disciplined debugging loop. Use when the request sounds like "help me debug this", "this test is failing", "the build broke", "this works sometimes and I do not know why", or when logs suggest a problem but not the cause.

Prepare and execute deployment-oriented work in an OpenClaw workspace with explicit release safety, environment awareness, and rollback thinking. Use when the request sounds like "deploy this", "prepare this for production", "update config and ship it", "what is the rollback plan", "check release readiness", or when a change could affect production behavior or operator workflow.

Update technical documentation, operational notes, prompts, or decision records in an OpenClaw workspace with the same rigor used for code. Use when the request sounds like "update the docs", "write this down", "capture this decision", "document the setup", or when behavior changes and future agents need durable written context instead of tribal knowledge.

Build or modify user-facing interfaces inside an OpenClaw workspace with strong interaction, responsiveness, and verification discipline. Use when the request sounds like "build this UI", "fix this page", "this interaction is broken", "make this responsive", "update this component", or any browser-facing change users will directly see, click, type into, or depend on visually.

Enforce a production-grade development workflow for OpenClaw coding work. Use when the request is broad or end-to-end, such as "build this feature", "fix this properly", "handle this coding task", "implement this across the codebase", or "help me ship this safely", especially when work spans multiple files and needs planning, verification, and clean closeout.

Break coding work into ordered, verifiable tasks for OpenClaw execution. Use when the request sounds like "make a plan", "break this into steps", "split this into tasks", "figure out the implementation order", or when work spans enough files or uncertainty that explicit checkpointing and a maintained plan file will reduce risk.

Simplify or restructure code in an OpenClaw workspace while preserving behavior. Use when the request sounds like "clean this code up", "simplify this without changing behavior", "reduce duplication here", "this module is getting hard to maintain", or when readability, structure, or verification quality need improvement without changing intended outcomes.

Critically review a code or prompt change in an OpenClaw workspace before merge or handoff. Use when the request sounds like "review this", "audit this PR", "look for bugs", "sanity-check this implementation", or "tell me what is risky here", especially when regressions, weak assumptions, missing tests, or release risk are concerns.

Apply practical application-security discipline to coding work in an OpenClaw workspace. Use when the request sounds like "is this secure", "review auth", "we are touching tokens or secrets", "this code handles user input", "this calls an external API", or any task that expands trust boundaries.

Prepare an OpenClaw change for safe handoff or release. Use when the request sounds like "wrap this up", "close this out", "are we ready to ship", "prepare final handoff", or any task where work is complete enough to need a disciplined final pass over diffs, verification, documentation, and rollout risk.

Define implementation scope before coding inside an OpenClaw workspace. Use when the request sounds like "write a spec", "define this feature first", "clarify scope", "turn this idea into something buildable", or any task where outcome, constraints, interfaces, or acceptance criteria are still fuzzy.

Require evidence before declaring coding work done in OpenClaw. Use when the request sounds like "verify this works", "what tests should we add", "prove this is safe", "is this ready", or any implementation, fix, refactor, review, or deploy task where the right level of proof is ambiguous or easy to under-scope.