review-remediation-gate
Review Remediation Gate
Use this skill when work has already been reviewed and the next step is to close findings, not re-litigate the whole task.
This is a closure skill. It exists to prevent weak "fixed" claims, review steering, and partial remediation from being treated as completion.
When to use
Use this skill for prompts like:
- "Fix the review findings"
- "Close the blocking comments"
- "Run a review-remediation pass"
- "Address the reviewer feedback and prove it is resolved"
- "Finish only after the review issues are closed"
Use it when the work already has findings, comments, or a review artifact and the goal is deterministic closure.
Required workflow
- Read the original intent, the review findings, and the current implementation state.
- Classify every finding as blocking, adjacent, validation-related, documentation-related, or intentionally accepted by the user.
- Convert each finding into a concrete remediation action with exact file scope and a verification step.
- Make the smallest complete fix that actually resolves the finding.
- Re-run the relevant validation or proof step after the fix.
- Record whether each finding is resolved, still open, or no longer applicable, with evidence.
- Stop only when every blocking finding is actually closed or the user has explicitly accepted the residual risk.
Non-negotiable rules
- Do not mark a finding resolved without evidence.
- Do not rewrite findings into softer language to make them look closed.
- Do not claim "done" while any blocking finding still lacks verification.
- Do not broaden scope unless the finding genuinely requires a coupled fix.
- Do not hide an unresolved issue behind a summary that only describes the intended fix.
- Do not convert a remediation pass into a redesign unless the review evidence proves the redesign is necessary.
Remediation discipline
- Preserve the original review context.
- Keep the fix traceable from finding to code change to validation output.
- Prefer the smallest safe patch that closes the issue.
- If a finding is invalid, explain why with evidence instead of silently dropping it.
- If the issue cannot be fixed, state the blocker precisely and name the missing condition.
Definition of done
This skill is complete only when all of the following are true:
- every blocking finding has a concrete fix or an explicit user-accepted exception
- each claimed fix has a verification step
- the final state is truthful about any remaining risk
- the closure report distinguishes resolved, deferred, invalid, and accepted findings
Final output contract
Report all of the following:
- original finding text
- remediation taken
- verification performed
- outcome for each finding
- any residual risk or accepted exception
If the work is still blocked, say exactly what remains open and what would unblock it.
More from mwillbanks/agent-skills
code-discipline
Prevent trivial helpers, wrapper layers, rename-only utilities, duplicate constants, and local reinvention. Enforce reuse of platform primitives, framework capabilities, shared utilities, and proven libraries. Use when adding or reviewing logic, constants, composition, or UI structure so the agent keeps code disciplined and avoids technical debt.
32agent-execution-mode
Enforces complete execution, repository-aware spec-driven delivery, mode-aware delivery, compact sub-agent communication, independent agent-review gating, validation, and reporting for implementation, bugfix, hardening, documentation, specification, architecture, design, review, and post-mortem tasks. Use whenever work must be completed, reviewed, validated, or documented through an explicit execution mode instead of handled ad hoc.
28repo-standards-enforcement
Use this skill to enforce repository-wide standards for toolchain compliance, package-manager purity, type safety, testing, maintainability, and architecture. When a more specific skill exists for a concern such as final linting or formatting remediation, that more specific skill takes precedence over this skill's generalized guidance.
26biome-enforcement
Use this skill when a task touches code, tests, Biome config, or generated artifacts and Biome must remain the final remediation and enforcement pass using the required JSON changed-files command.
24execution-alignment-gate
Detects materially ambiguous or under-specified requests, selects the right clarification target, and enforces bounded alignment before execution, including spec-governed continuations and approval-gated manager handoffs. Use when ambiguity could cause wrong deliverables, wrong scope, wrong implementation path, avoidable rework, or token waste from repeated follow-up.
19speckit-feature-orchestrator
Orchestrates a full Speckit feature workflow from constitution amendment through specification, clarification, plan, tasks, and analysis as a chief-architect governor using subagents. Use when the repository already uses Speckit or the user explicitly asks for Speckit and wants to discuss, refine, or directly drive a new feature into implementation-ready Speckit artifacts in one controlled pass.
12