From lisa
Verification lifecycle: classify types, discover tools, fail fast, plan, execute, loop. Includes verification surfaces, proof artifacts, self-correction loop, escalation protocol, and definition of done.
npx claudepluginhub codyswanngt/lisa --plugin lisaThis skill uses the workspace's default tool permissions.
This skill defines the complete verification lifecycle that agents must follow for every change: classify, check tooling, fail fast, plan, execute, and loop.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
This skill defines the complete verification lifecycle that agents must follow for every change: classify, check tooling, fail fast, plan, execute, and loop.
Agents must follow this mandatory sequence for every change:
Determine which verification types apply based on the change. Start with the three always-required types (Test, Type Safety, Lint/Format), then check each conditional type against the change scope.
For each required verification type, discover what tools are available in the project. Use the Tool Discovery Process below.
Report what is available for each required type. If a required type has no available tool, proceed to step 3.
If a required verification type has no available tool and no reasonable alternative, escalate immediately using the Escalation Protocol. Do not begin implementation without a verification plan for every required type.
For each verification type, state:
After implementation, run the verification plan. Execute each verification type in order.
If any verification fails, fix the issue and re-verify. Do not declare done until all required types pass. If a verification is stuck after 3 attempts, escalate.
Agents must discover available tools at runtime rather than assuming what exists. Check these locations in order:
scripts/, bin/, project root)If a tool is expected but not found, report the gap rather than assuming it doesn't exist — it may need to be installed or configured.
Agents may only self-verify when the required verification surfaces are available.
Verification surfaces include:
If a required surface is unavailable, agents must follow the Escalation Protocol.
Many verification steps require tools that may not be available by default.
Tooling surfaces include:
If required tooling is missing, misconfigured, blocked, undocumented, or inaccessible, agents must treat this as a verification blocker and escalate before proceeding.
Every completed task must include proof artifacts stored in the PR description or linked output location.
Proof artifacts must be specific and re-checkable. A proof artifact should contain enough detail that another agent or human can reproduce the verification independently.
Acceptable proof includes:
Statements like "works" or "should work" are not acceptable.
Verification is not a one-shot activity. Agents operate within a three-layer self-correction architecture that catches errors at increasing scope. Each layer is enforced automatically — agents do not need to invoke them manually.
Trigger: Every file write or edit.
Hooks run formatting, structural analysis, and linting on the single file just written. Errors are reported immediately so the agent can fix them before writing more files. This prevents error accumulation across multiple files.
Agent responsibility: When a hook blocks, fix the reported errors in the same file before proceeding to other files. Do not accumulate errors.
Trigger: Every commit.
Checks run on staged files: linting, formatting, secret detection, commit message validation, and branch protection. This layer catches errors that span multiple files or involve staged-but-not-yet-checked changes.
Commit-time checks cannot be bypassed. Agents must discover what specific checks are enforced by reading the project's hook configuration.
Trigger: Every push.
The full project quality gate runs: test suites with coverage thresholds, type checking, security audits, unused export detection, and integration tests. This is the last automated checkpoint before code reaches the remote.
Handling failures: When a push fails, read the error output to determine which check failed. Fix the root cause rather than working around it. Agents must discover what specific checks are enforced by reading the project's hook configuration.
When the root cause of errors is architectural (wrong abstraction, incorrect data flow, fundamentally broken approach), delete and regenerate rather than incrementally patching. Incremental patches on a broken foundation accumulate tech debt faster than the self-correction loop can catch it.
Signs that regeneration is needed:
Agents must follow this sequence unless explicitly instructed otherwise:
Agents must escalate when verification is blocked, ambiguous, or requires tools that are missing or inaccessible.
Common blockers:
When blocked, agents must do the following:
Agents must never proceed past an unverified boundary without surfacing it to the human overseer.
Agents must provide:
Example:
db.host and internal logs viewer.db.host, provide credentials or endpoint.Agents must pause until explicit human confirmation.
Agents must never bypass security controls to proceed.
If an operation is irreversible or risky, escalate first.
Every PR must include:
Preferred artifact locations:
scripts/verification/A task is done only when:
If any of these are missing, the work is not complete.