Results for “task-review”

`analysis-agent`/`task-agent`/`review-agent`: use for database, broker, cache, HTTP, framework, process, or transaction seam proof; skip local, portfolio, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.

`analysis-agent`/`task-agent`/`review-agent`: use when form fields, validation, async checks, submit states, or recovery change; skip when form behavior is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when merges, rebases, conflicts, history rewrite, generated files, or recovery need evidence; skip when Git is irrelevant.

`analysis-agent`/`task-agent`/`review-agent`: use when authoring SKILL.md, triggers, decisions, references, registry, routing, or validation; skip when no Skill content changes.

`analysis-agent`/`task-agent`/`review-agent`: use when lifecycle states, transitions, guards, or terminal states need modeling; skip when no state-machine decision exists.

`analysis-agent`/`task-agent`/`review-agent`: use when uploads, object storage, streaming, MIME, scanning, access, retention, or cleanup changes; skip without file/storage impact.

`analysis-agent`/`task-agent`/`review-agent`: use when Rust changes cross ownership, unsafe/FFI, panic, cancellation, or Send/Sync boundaries; skip tool-only work.

Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.

`analysis-agent`/`task-agent`/`review-agent`: use to recommend a risk-to-test evidence portfolio and omissions; skip test implementation, fixed-command, and release-verdict work.

`task-agent`/`review-agent`: use when jobs, workers, queues, schedules, retries, cancellation, or status visibility need design; skip when no async-job decision is required.

`analysis-agent`/`task-agent`/`review-agent`: use when fixtures, factories, seeds, isolation, cleanup, or sensitive test-data rules change; skip when test data is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when migration, backfill, deployment order, rollback, or live-data safety needs design; skip when no data migration exists.

`analysis-agent`/`task-agent`/`review-agent`: use when Go context, goroutine, channel, error, interface, or resource semantics affect behavior; skip generic or non-Go work.

Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.

`analysis-agent`/`task-agent`/`review-agent`: use when C/C++ changes cross ownership, UB, ABI/FFI, exception, concurrency, or target-build boundaries; skip tool-only work.

`analysis-agent`/`task-agent`/`review-agent`: use when API/DTO, domain, persistence, event, generated, null/default, or mapper boundaries may leak; skip when models stay isolated.

`analysis-agent`/`task-agent`/`review-agent`: use when behavior needs deterministic seams for time, randomness, UUIDs, collaborators, or external I/O; skip when seams are adequate.

Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine). Does NOT apply to the legacy `packages/agent-core` or to any other package — for those, do not load this skill. Groups the review and testing lenses used for agent-core-v2 — `slop` (single-level-of-abstraction / layered error-handling review, invoked only on explicit request) and `test` (contract-driven per-test rules for both authoring and reviewing tests). Apply the sub-skill that matches the task; do not apply `slop` unprompted.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

`analysis-agent`/`task-agent`/`review-agent`: use when repeated failure needs a new hypothesis or proof path; skip an initial failure with verified cause and a different action.

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

Use `analysis-agent` for release decisions, `task-agent` for delivery artifacts, or `review-agent` for readiness on deployment, migration, rollback, or production risk. Skip local work with no release decision.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Use `task-agent` to update source-backed documentation or `review-agent` to assess documentation impact and accuracy when public behavior or operator workflows change. Skip work with no audience-facing behavior change.

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

Delegate a substantial diagnosis, implementation, or follow-up task to Claude Code through the tracked-job runtime. Args: --background, --wait, --resume, --resume-last, --fresh, --write, --model <model>, --effort <low|medium|high|xhigh|max>, --prompt-file <path>, [task text]. Defaults to opus + xhigh effort. Use when Claude should investigate or change things, not when the user only wants review findings.

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".

Never show the user a first draft. Run every writing task through a self-critique loop — draft, attack the draft as the harshest reviewer in the room, rewrite, and repeat until a full review pass finds zero flags — then return only the final plus a change log. Use for any writing the user actually cares about: emails, LinkedIn posts, newsletters, docs, announcements, client messages. Trigger whenever the user says 'run the loop', 'self-critique this', 'make it bulletproof', 'don't give me a first draft', 'be brutal', or hands over a task where quality matters more than speed. This is a single-agent loop; for the three-agent version use the-team.

Generate, review, and optimize natural language instructions for Business Central agents (Designer or SDK). Triggers on: agent instructions, InstructionsV1.txt, InstructionsV2.txt, MEMORIZE, qualification rules, agent behavior, instruction keywords, agent task instructions, iterate instructions, or improve agent accuracy. Follows the Responsibilities-Guidelines-Instructions framework with official BC agent runtime keywords.

Audit, plan, implement, or review Model Context Protocol version and SDK migrations. Use for MCP 2026-07-28, stateless Streamable HTTP, server/discover, removal of initialize or Mcp-Session-Id, MCP Tasks extension changes, full JSON Schema 2020-12 tool schemas, OAuth issuer hardening, deprecated roots/sampling/logging, or cross-version client/server compatibility.

Validate process decomposition and architecture design quality before execution begins. Load when the setup-evaluator agent fires (automatic for agent-chain tasks), or when user says "evaluate this setup", "check the decomposition", "validate the architecture", "is this plan sound", "review the agent design". Catches structural errors, missing knowledge, unrealistic step ordering, and topology mismatches. Does NOT modify — only evaluates.

Decentralized git for AI agents and humans. Use when the user wants to create repositories, push code, open pull requests, review and merge PRs, manage issues, create or claim bounties, delegate tasks to other agents, register human-readable names on Base L2, or interact with the gitlawb decentralized git network. Supports cryptographic DID identities, Ed25519-signed pushes, UCAN capability delegation, libp2p networking, and 31+ MCP tools for AI agent integration. Do NOT use for GitHub, GitLab, or other centralized git hosts.

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.