personal-context

Use `al dispatch` for focused headless second-agent work — another model, tool set, skill, or review perspective. Trigger when the user asks to run al dispatch, use a subagent or second agent, get a fresh-context review, or invoke a target agent with a skill. Do not use for ordinary shell commands, local test runs, web search, browser automation, or multi-agent orchestration.

Audit and iteratively fix uncommitted working-tree changes until a confirming review finds no remaining actionable issues. Use to stabilize in-progress diffs and report each review/fix round with severity.

Audit the existing test suite for redundancy, quality gaps, and organization: duplicate or self-confirming tests, coverage gaps metrics miss, and safe cleanup fixes. Use `prune-new-tests` instead when the target is tests added in the current uncommitted diff.

Raise coverage: find the real coverage command, select under-covered files, add behavior-focused tests, iterate to target or blocker. Use `audit-tests` for full-suite cleanup; use `prune-new-tests` to prune speculative tests in the current uncommitted diff.

Use `npx ctx7` to fetch current documentation, API references, and code examples for libraries, frameworks, and APIs when the answer is version-dependent or post-cutoff, or local sources (README, docs/, CLI help) can't answer it. Trigger for API syntax, configuration, setup, migration, or "how do I use <technology>" questions. Do not use for generic web research, local file reading, browser automation, or package installation.

Execute an existing plan/task/context artifact set: make aligned code changes and verify code, tests, docs, and memory before closeout. Use `plan-work` when no plan exists.

Write a scoped implementation plan, task list, and context file for a requested change, roadmap slice, execution strategy, task breakdown, or pre-implementation design artifact.

Use playwright-cli for real-browser UI automation, screenshots, Playwright test debugging, and interactive test generation. Trigger when a task needs browser interaction, UI inspection, end-to-end verification, or Playwright test repair. Do not use for generic test running, web search, non-browser docs, or API-only work.

Burden-of-proof review of tests added in the current uncommitted diff: auto-delete any new test that can't justify itself with a production-code mutation that would flip its assertion. Use `audit-tests` for full-suite health; use `boost-coverage` to add tests.

Run completed local work through PR delivery: audit changes, verify locally, commit, push, open PR, monitor CI, handle review comments, finish green, then merge after approval and clean up the branch. Use `fix-ci` for failing PR checks.

Codebase-wide simplification removing real internal complexity — dead code, obsolete options, needless indirection, duplicate workflows, misplaced boundaries — across given paths or the whole repo. Use `simplify-new-code` instead for only the current uncommitted diff.

Scan the current uncommitted diff for agent-added scope creep — speculative flexibility, premature abstractions, dead branches, defensive scaffolding, half-finished work — and auto-apply simplifications, preserving user-requested behavior. Use `simplify-codebase` for full-codebase complexity sweeps.

Use the Tavily CLI for web search, URL extraction, site URL discovery, and cited research. Trigger when the user needs current web information, asks to search or read a webpage, provides URLs to inspect, or wants a sourced research report. Do not use for browser automation, local docs, or Tavily setup.

Handle reviewer feedback on an open PR: evaluate comments, implement agreed fixes, justify or track deferrals, reply to every comment, audit substantive changes when warranted, then commit and push. Use `fix-ci` for failing checks.

Audit Markdown docs for static accuracy and cross-document consistency against the repo, fixing what is safe. Excludes memory files by default; use `audit-memory` for those.

Audit agent memory files (ISSUES, BACKLOG, ROADMAP, DECISIONS, COMMANDS, CONTEXT) for structure, staleness, placement, consistency, and DECISIONS.md bloat; fix accepted findings.

Complete the current roadmap phase through planning, review, implementation, verification, audit, cleanup, and closeout. Use `plan-work` for planning only and `finish-task` for non-roadmap closeout.

Investigate a reported bug from symptom to root cause: reproduce, narrow, diagnose, write a failing test, fix, and verify. Use when the cause is unknown and investigation must precede planning.

Close out finished work by checking plan alignment, updating only necessary memory/docs, running credible verification, and summarizing outcome. Use `ship-pr` for PR work or `verify-against-plan` for read-only checks.

Diagnose and fix failing CI/checks on an open PR: inspect logs/artifacts, create a local reproducer when possible, patch, audit, commit, push, and re-check. Use `repair-checks` for local failures.

Fix open `ISSUES.md` items: plan a batch, implement, audit, verify, and keep the ledger current. Use `debug-issue` for one unexplained symptom or `resolve-findings` for review reports.

Run a deep autonomous quality sweep of the whole codebase or named subsystems: survey, split into reviewable chunks, run multi-lens reviews, fix findings iteratively, and delegate to cleanup/test skills as needed.

Run documented local checks, fix in-scope failures, and repeat until checks pass or a real blocker remains. Use for lint, typecheck, tests, format, or pre-PR check failures.

Triage a review findings report: verify each finding, implement accepted fixes, and record rejected, deferred, or already-resolved items. Use for report-driven follow-up work.

Review a plan/task/context artifact set before execution, reporting scope gaps, sequencing problems, weak verification, and missing docs/tests/memory updates.

Review explicit files, directories, diffs, uncommitted changes, or proactive hotspots for correctness, gaps, risks, architecture, tests, docs, performance, reliability, and maintainability. Use `review-plan` for plans.

Map BACKLOG.md items into roadmap phases, checking issue/decision impacts and pausing before roadmap edits. Use when scheduling backlog work or reshaping the roadmap; use `plan-work` for one implementation plan.

Read-only check of current implementation and working tree against a plan/task/context set, reporting completeness gaps, regressions, missing tests/docs, and scope drift. Use `review-plan` to critique the plan.