Prove completeness for non-trivial implementation, migration, translation, content, integration, and audit work by inventorying the full affected surface, tracking coverage, auditing omissions, and refusing unsupported completion claims.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use this protocol for any non-trivial task whose result can be partially correct while still missing routes, records, states, content sources, integrations, or user journeys.
Before implementation, translate the requested outcome into a bounded inventory of affected surfaces. Derive the inventory from the actual system and the user's request, not only from examples in the prompt or the files first discovered.
The completion contract must identify:
For ambiguous scope that would materially change the result, ask before implementation. Do not use ambiguity to silently shrink the inventory.
Track every inventory item with exactly one status:
verified: implemented and supported by fresh evidence;excluded: outside scope with explicit user approval and a reason;blocked: incomplete, with the concrete blocker and required next action.An item is never complete merely because a file changed, a unit test passed, or one representative example worked. Evidence must match the claimed outcome.
After implementation, search for what was missed. Select checks that can falsify completeness, such as remaining source-language text, missing locale keys, stale fallbacks, unhandled routes, unstyled theme states, untested permissions, orphaned records, unchanged legacy APIs, placeholders, dead branches, or outputs that still use the old behavior.
For translation work, inventory and verify at minimum: navigation, routes, products, categories, database-owned content, field labels, placeholders, validation errors, empty/loading/error states, notifications, emails, metadata, search/filter values, mobile views, and fallback-language behavior. Approved brand names are exclusions, not silent exceptions.
Exercise complete user journeys across the affected boundaries. Then perform a separate completion audit against the original request and the coverage ledger. The audit's purpose is to disprove completion, not to summarize implementation.
The reviewer must inspect fresh outputs or runtime state. Self-authored claims, stale screenshots, changed-file lists, and successful build commands are not substitutes for outcome evidence.
Before reporting completion, produce the one-line JSON completion_manifest defined in references/manifest.md. A complete verdict is valid only when:
If any condition is unmet, use verdict incomplete and state exactly what remains. Never use done, finished, complete, polished, or verified as a softer substitute.
Classify rejected or repeated work by root cause, including omitted_surface, missing_state, missing_data_source, broken_continuity, stale_evidence, visual_mismatch, scope_drift, and unsupported_completion_claim.
Record each correction in the central learning system with its scope and evidence. When the same root cause occurs two or three times, propose a reusable inventory or verification rule. Do not promote a one-off preference automatically.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).
The English summary is being prepared. Showing the original description.
Whole site or product — a full web accessibility (a11y) audit against WCAG 2.2, following the WCAG-EM methodology. Defines scope, samples representative pages and flows, runs the automated tier (`accessibility-scan`) and the hands-on manual tier (`accessibility-inspect`), and produces one conformance report. Grades each finding by severity and evidence basis, and states per-criterion conformance as pass, fail, or undetermined (needs a human). Use it for 'audit my site for accessibility', 'is this product accessible', 'a11y audit', 'WCAG or Section 508 conformance report', or any multi-page assessment. Assesses; does not fix (use `accessibility-fix`) or diff (use `accessibility-diff`). For a single page use `accessibility-scan`; for hands-on keyboard and screen-reader checks use `accessibility-inspect`.
The English summary is being prepared. Showing the original description.
Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.
The English summary is being prepared. Showing the original description.
Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.
The English summary is being prepared. Showing the original description.
One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.
The English summary is being prepared. Showing the original description.
One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.
The English summary is being prepared. Showing the original description.