
--- name: coder-frontend-design description: Frontend design system practices: tokens, typography, color, layout, and component consistency. --- <when_to_use> <trigger>Creating or updating a design system for web UI</trigger> <trigger>Defining visual foundations before implementation</trigger> <trigger>Aligning design decisions between design and engineering</trigger> <trigger>Reviewing UI consistency and scalability risks</trigger> </when_to_use> <input_requirements> <required>Produ
Reliable and secure external API integration patterns for production-grade services.
Testability-first design rules for modular, deterministic, and verifiable systems.
Mermaid diagram generation for architecture, flows, and scenarios
Documentation of research results and their impact on project decisions
Use-case documents with traceability to PRD
--- name: planning-approach-selection description: Implementation approach selection: compare options and justify the decision --- <purpose> <item>Compare 1-3 realistic approaches and pick the best by explicit criteria</item> </purpose> <inputs> <required>Goal/requirements + constraints</required> <optional>Risks and process constraints (releases, windows, SLA)</optional> </inputs> <method> <step>Define 3-6 selection criteria (risk, speed, cost, maintainability, compatibility)</step>
Apply shared planning baseline (format, verifiability, assumptions) before creating any concrete change plan
Identify affected systems, contracts, and data plus regression hotspots; not file-level edit inventory
--- name: planning-monitoring-checks description: Observability: metrics, alerts, dashboards, post-change observation windows --- <purpose> <item>Define the signals that tell whether "everything is OK" or "we must stop/roll back"</item> </purpose> <inputs> <required>Change goal + critical user scenarios</required> <optional>SLA/SLO, existing metrics/alerts</optional> <optional>Risks (especially high-impact)</optional> </inputs> <method> <step>Define 3-7 key signals: errors, latency,
--- name: planning-requirements-extraction description: Extract requirements from a request: behavior, AC, constraints; for bugs - repro --- <purpose> <item>Convert the original request into verifiable requirements and acceptance signals</item> </purpose> <inputs> <required>Task description</required> <optional>For a bug: repro steps, environment, logs/stacktrace</optional> <optional>For a feature: user goal, constraints, desired UX</optional> </inputs> <method> <step>State the goal
--- name: planning-rollout-strategy description: Rollout strategy: stages, audiences, enablement mechanics, stop points --- <purpose> <item>Reduce rollout degradation risk and keep enablement controllable</item> </purpose> <inputs> <required>Change description + risks/criticality</required> <optional>Available mechanisms (feature flags, canary, blue-green)</optional> <optional>Release/window constraints</optional> </inputs> <method> <step>Select a rollout mechanism (flag/canary/blue
Choose fast or standard planning mode based on complexity, risk, and unknowns before any project artifacts
Create a compact fast-flow spec for one iteration (AC, architecture skeleton, and verification gate) before decomposition
Run a timeboxed research scan after fast-init to confirm critical constraints and escalation triggers
Decompose fast proto-spec into an ordered MVP task list with AC links, dependencies, and DoD
Use for external web research with primary sources and links; not for local repository analysis
Mobile testing (native/hybrid/web, gestures, offline, interruptions)
Project documentation map. Must be loaded before any work
Clean code execution rules for coding agents with verifiable quality gates.
Debugging requirements protocol from reproducible issue to verified fix and regression protection.
Requirement quality rules for coding tasks with traceable MUST/SHOULD and verifiable acceptance criteria.
Database schema design and migration safety rules for production systems.
System-level performance pattern selection with measurable tradeoffs and SLO alignment.
Security-by-design baseline for architecture decisions, controls, and verification.
Development plan document for implementation changes
Initial project brief and MVP boundaries
status.json as the single tracker of project stage and readiness
Implementation task description ready for delivery and validation
Bug report with reproducibility and impact assessment
Test report with functional and regression verification results
Enumerate concrete files/components and intended edits tied to AC; not broad cross-system impact analysis
Define task boundaries (in/out), assumptions, and non-goals
--- name: planning-migration-strategy description: Migration strategy for data/schemas/contracts: compatibility, phases, verification --- <purpose> <item>Design a migration that preserves data integrity and compatibility</item> </purpose> <inputs> <required>What we migrate (schema/data/API) and why</required> <optional>Data volume, time windows, downtime constraints</optional> <optional>Backward-compatibility requirements</optional> </inputs> <common_patterns> <pattern>expand/contra
--- name: planning-risk-assessment description: Risk assessment: likelihood/impact, mitigations, residual risk --- <purpose> <item>Identify risks, assess them, and define concrete mitigations</item> </purpose> <inputs> <required>Change description + impact areas (if available)</required> <optional>Critical business processes and SLA</optional> <optional>Release/window/process constraints</optional> </inputs> <risk_categories> <item>data</item> <item>security</item> <item>perform
--- name: planning-rollback-mechanism description: Rollback mechanics and scenario: criteria, steps, data impact, recovery --- <purpose> <item>Create a fast and safe path to revert in case of degradation</item> </purpose> <inputs> <required>Change description + rollout strategy</required> <optional>Data/compatibility constraints (especially for migrations)</optional> <optional>Available mechanisms: revert, feature flag, blue-green</optional> </inputs> <method> <step>Define rollback
--- name: planning-testing-strategy description: Testing strategy: what to verify, test types, data needs --- <purpose> <item>Define a sufficient verification set tied to AC and risks</item> </purpose> <inputs> <required>AC/Goal + change list</required> <optional>Critical scenarios, edge cases, risks</optional> <optional>Available environments and test data</optional> </inputs> <method> <step>Map each key AC/risk to a check (unit/integration/e2e/manual)</step> <step>Define a regre
Fast, evidence-based technology stack selection for one-iteration planning
Break standard-flow epics into implementation-ready tasks with AC, DoD, sequencing, and critical-path visibility
Review of architectural consistency of changes against principles and the current system landscape
Short quality gate for code review before merge
Idiomatic code review for the project's language and framework
--- name: review-code-maintain description: Maintainability and readability review: structure, clarity, and changeability --- <when_to_use> <trigger>Need to assess how easy the code is to maintain and evolve</trigger> <trigger>The PR has a lot of new logic or refactoring without functional changes</trigger> </when_to_use> <input_requirements> <required>PR/diff and a short change objective</required> <optional>Project naming rules and style guide</optional> <optional>List of known pai
Performance review for changes in critical paths and resource-intensive operations
Mandatory baseline rules for any agent. Must be loaded before any work
Use for read-only codebase investigation with file/symbol evidence; not for implementation planning or code edits
Use for domain rules and business-flow research with source evidence; not for low-level code tracing
Manually verify API behavior with reproducible requests and response checks; not contract version compatibility governance
Design and maintain automated UI/API tests (framework patterns, stability, CI artifacts); not one-off manual checks
Verify provider-consumer API contract compatibility and versioning; not ad-hoc endpoint behavior checks
Load testing (k6/JMeter scenarios, benchmarks)
Design detailed reproducible test cases (Given/When/Then, one check per case); not smoke/regression checklists
--- name: review-doc-quality description: Documentation quality checklist: accuracy, completeness, consistency, and freshness --- <when_to_use> <trigger>A short quality gate is needed before publishing a document</trigger> <trigger>An audit of existing documentation fitness is required</trigger> </when_to_use> <input_requirements> <required>Document text or diff</required> <required>Target audience and expected reading outcome</required> <optional>Relevant links to product/interfaces
API design rules for stable, observable, backward-compatible HTTP APIs.
Project architecture document and technical constraints
Manual browser UI verification via MCP snapshots with reproducible steps and observed behavior; not automation design
Use to draft decomposition for one feature/epic with dependencies and risks; final scope and priorities stay with main agent
End-to-end scenarios (user paths, integration chains)
Epic definitions as value slices with requirement traceability
--- name: review-arch-full-check description: Full architecture review: decisions, trade-offs, NFRs, risks, and rollback plan --- <when_to_use> <trigger>Major changes to architecture or public contracts</trigger> <trigger>High risk in reliability, security, or scalability</trigger> <trigger>Before launching an initiative with long-term consequences</trigger> </when_to_use> <input_requirements> <required>ADR or equivalent document with options and selected approach</required> <require
How-to, guide, and ops documents for users and developers
--- name: planning-estimation description: Time/effort estimation: method, range, assumptions, uncertainty --- <purpose> <item>Provide a transparent estimate tied to decomposition and risks</item> </purpose> <inputs> <required>Change inventory or work decomposition</required> <optional>Blockers/dependencies/quality/process constraints</optional> </inputs> <method> <step>Estimate by phases (analysis/implementation/tests/rollout) or by components</step> <step>Pick an estimation method
--- name: coder-frontend-ui-ux description: Frontend UI/UX practices: flows, interaction states, accessibility-first UX, forms, and perceived performance. --- <when_to_use> <trigger>Designing or refining user flows and screen behavior</trigger> <trigger>Improving usability, accessibility, and interaction quality</trigger> <trigger>Defining loading/error/empty states for key journeys</trigger> <trigger>Reviewing UX regressions in feature delivery</trigger> </when_to_use> <input_requirem
Designing use cases and user flows with PRD traceability
Visual regression (baseline diffs, UI stabilization)
Quick project planning kickoff in one iteration (scope, goal, artifacts)
Creating and validating project personas for requirement prioritization
Product Requirements Document with FR/NFR and testable acceptance criteria
Produce full standard-flow PRD with FR/NFR and testable AC after brief/research and before architecture
Run targeted evidence-based research in standard flow to close critical unknowns before architecture decisions
--- name: planning-scope-minimization description: Minimize changes for bugs/incidents: the smallest safe fix --- <purpose> <item>Narrow the plan to the minimal change that fixes the bug and reduces regression risk</item> </purpose> <inputs> <required>Bug description + observed vs expected</required> <optional>Repro steps, environment, logs/stacktrace</optional> <optional>Criticality (SLA, incident) and deadline</optional> </inputs> <method> <step>Define the minimal "fixed" criterio
--- name: review-code-strategy description: Code review strategy: PR review flow, risk prioritization, and merge blocking rules --- <when_to_use> <trigger>Need to review a pull request before merge</trigger> <trigger>There is disagreement on comment strictness and blocking criteria</trigger> <trigger>Need to align a unified review process across the team</trigger> </when_to_use> <input_requirements> <required>PR link or diff</required> <required>Task context and expected behavior</re
Accessibility testing (WCAG, keyboard, screen reader)
Changelog document for tasks and releases
User personas and scenarios for requirement prioritization
Classify a task (bug/feature/refactor/migration) and what the plan must emphasize