shark-task-manager

Query and manage project state and drive shark workflows — epics, features, tasks, bugs, change-cards, ideas. Use for ALL project state queries, task lifecycle, status transitions (status set / advance --outcome), claim/release/heartbeat leases, blocking/unblocking, notes/context/related-docs, status dashboards, analytics, creating/updating/deleting entities, and any command starting with "shark". Also the router for `/shark <verb>` and triggers the dispatch loop on `/run <key>`.

Multi-angle parallel code review. Six specialist subagents run in parallel (A: line-by-line bugs + production caller chains, B: removed behavior + SOLID, C: cross-file contracts + structural sibling check, D: reuse/complexity/idioms, E: tests design + counter-factual, F: standards crosswalk with citations), then a consolidator verifies and ranks findings into a PASS / PASS-with-triage / FAIL report with Blocker / Non-blocker / Nit triage. Triggered by /deep-review (aliases: /comprehensive-review, /pr-review). Flags: --fix (apply one-liner safe fixes), --comment (post as inline GitHub PR comments). Prompts live in references/angle-*.md and references/consolidator.md — readable on any platform even without the Workflow tool.

Authoritative source for all validation, code review, and quality assurance workflows. Provides consistent quality gates across all development phases.

Write the test first, watch it fail, write minimal code to pass (user) - when implementing any feature or bugfix, before writing implementation code

Orchestrate User Acceptance Testing for a feature — gather evidence, run Codex as the sole assessor, present a no-opinion report to the user, record results, route rejections, and triage non-blocking findings.

Quick-capture and classify a work item discovered during development, routing it to the correct entity type (task, feature, bug, tech-debt, change-card, idea, or note) under the right parent. Searches existing entities first to avoid duplication, proposes a classification, and confirms before creating. Use when you encounter work that needs to be recorded for later, the user says "/triage", or something should be tracked but its home is unclear. This is a capture-and-classify tool, NOT a create-and-elaborate tool.

Authoritative source for all specification document generation workflows (Epics, Feature PRDs, Tasks). Provides standardized templates, procedures, and naming conventions for consistent documentation across all projects.

Workflow decision-making assessments for project management. Use when evaluating feature complexity (SIMPLE/STANDARD/COMPLEX tier assignment), validating scope (feature vs task classification), checking phase readiness (gate validation), or estimating implementation effort. Invoked during feature triage, scope validation, phase transitions, or when complexity/effort estimates are needed for planning.

Systematic codebase analysis and project understanding workflows. Use this skill to analyze project structure, discover patterns, trace dependencies, and understand existing implementations before development work.

Authoritative source for all architecture design workflows (System, Backend, Frontend, Database, Security). Provides standardized patterns, templates, and design frameworks for consistent architecture documentation across all projects.

Feature-level UX design workflows producing wireframes and prototypes. Use during SDLC feature refinement after product-design evidence reaches its exit point. Consumes feature PRDs, D08 personas, D09 journey maps, and optionally D11 friction points.

Product-level design methodology covering D01–D14 — vision, discovery, UX/CX design, and concept validation. Produces the "what and why" before any feature work begins. Provides the methodology for each of the 14 product-design artifacts; any single artifact workflow can be applied independently. Triggers include "product vision", "discovery", "user personas", "journey mapping", "user testing", "friction points", and any "produce D0X" request.

Methodology for deep analysis and documentation of existing (brownfield) codebases. Covers how to analyze architecture, code structure, business logic, technical debt, security, code quality, and migration readiness, and how to produce enterprise-grade documentation from what you find. Use whenever the work involves analyzing a codebase, reverse-engineering a project, documenting an existing system, assessing technical debt, understanding a legacy codebase, or judging whether a system is ready to migrate — even when the word "brownfield" is not used.

Post-close sprint retrospective analysis skill that reads shark sprint summary --detailed and velocity data, synthesizes five-section markdown retro reports with data-driven recommendations, and gates the archive operation on explicit user confirmation.

Solo and team sprint pull-loop skills that drive an active sprint to completion by pulling entities from shark sprint next and delegating per-entity dispatch to the existing /run (or /run-agent-team) orchestration skill.

Mode-aware sprint scoping skill that walks an orchestrator or human through planning a sprint by reading shark sprint plan and readiness data, proposing entity assignments, and confirming changes. Never starts the sprint — starting is an explicit user action via /run-sprint.

Post-close sprint retrospective analysis skill that reads shark sprint summary --detailed and velocity data, synthesizes five-section markdown retro reports with data-driven recommendations, and gates the archive operation on explicit user confirmation.

Solo and team sprint pull-loop skills that drive an active sprint to completion by pulling entities from shark sprint next and delegating per-entity dispatch to the existing /run (or /run-agent-team) orchestration skill.

Mode-aware sprint scoping skill that walks an orchestrator or human through planning a sprint by reading shark sprint plan and readiness data, proposing entity assignments, and confirming changes. Never starts the sprint — starting is an explicit user action via /shark run-sprint.

Systematic approaches to writing high-quality code with contract-first discipline and validation gates

Decompose a requirement or specification section into testable acceptance criteria. Turns prose intent into an enumerated test matrix of conditions, expected outcomes, edge cases, and negative cases that any agent can hand to an implementer or test author.

Techniques for resolving ambiguous requirements. Detect ambiguity, surface hidden assumptions, and use question ladders to turn an unclear requirement into a precise, testable one. Use whenever a requirement, request, or spec is vague, underspecified, or open to multiple interpretations.

Validate written artifacts for completeness, internal consistency, evidence quality, clarity, and readiness before they are used downstream. Use for spec, plan, report, design, or review content that needs a rubric-based quality pass without becoming a workflow gate.

Checks consistency across layered specification artifacts (epic, feature, and task specs). Finds drift between specification layers — where a child spec contradicts, omits, or silently re-scopes what its parent established. Input is a set of related spec artifacts; output is a consistency report enumerating identified mismatches with severity and remediation.

Systematic debugging workflows for frontend, backend, tests, devops, and web issues. Provides structured approaches to isolate root causes and resolve problems efficiently.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Detect and reduce overconfident reasoning in analysis, plans, estimates, reviews, and recommendations. Use when conclusions may be based on weak evidence, hidden assumptions, premature certainty, or insufficient exploration of alternatives.