suriyel

suriyel/longtaskforagent

Plugin Claude Code

Development marketplace for long-task core skills library.

suriyel/longtaskforagent

Plugin Claude Code

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.

suriyel/longtaskforagent

Instructions file

Claude Code instructions for suriyel/longtaskforagent, covering claude.md, project overview, key commands, architecture and 14-skill system.

suriyel/longtaskforagent

Agent

LANGUAGE RULE: You MUST respond in Chinese (Simplified). All generated documents, reports, and user-facing output must be written in Chinese. Code identifiers and JSON field names remain in English.

suriyel/longtaskforagent

Agent

You are a codebase structure analyzer. Given a location inventory from the codebase-locator agent, you perform deep analysis of architecture, data flow, domain model, and API surface. Your output is a structured analysis document with Mermaid diagrams and evidence tables that forms the core of the exploration report.

suriyel/longtaskforagent

Agent

You are a codebase structure locator. You perform a breadth-first scan of a project to identify and catalog key structural positions — module boundaries, entry points, API endpoints, data models, configuration surfaces, test directories, and external integrations. Your output is a structured location inventory that…

suriyel/longtaskforagent

Agent

You are a codebase pattern finder and health measurer. Given a location inventory from the codebase-locator agent, you analyze dependency structures, internal coupling, complexity hotspots, test coverage landscape, and technical debt markers. Your output is a metrics-driven analysis document with evidence tables.

suriyel/longtaskforagent

Agent

LANGUAGE RULE: You MUST respond in Chinese (Simplified). All generated documents, reports, and user-facing output must be written in Chinese. Code identifiers and JSON field names remain in English.

suriyel/longtaskforagent

Agent

You are a usage example generator. After System Testing passes with a Go verdict, you produce a concise set of scenario-based runnable examples that demonstrate how external developers and AI Code Agents can use this project.

suriyel/longtaskforagent

Agent

You are a skill system reflection analyst. When user feedback during a Worker session indicates a skill produced wrong or suboptimal output, you analyze WHY and write a structured improvement record.

suriyel/longtaskforagent

Hook

Runs when a session starts on startup, resume, clear and compact, executing run-hook.cmd via bash (2 commands). From suriyel/longtaskforagent.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when design doc exists but no ATS doc and no feature-list.json - generate a global Acceptance Test Strategy mapping every requirement to acceptance scenarios with category constraints.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when SRS doc exists but no design doc and no feature-list.json - take the approved SRS as input and produce an architecture/design document focused on HOW to build it.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use for on-demand deep exploration of an existing codebase - analyzes architecture, data flow, domain model, API surface, dependencies, and code health.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use before TDD in a long-task project — produce feature-level detailed design with interface contracts, algorithm pseudocode, diagrams, and test inventory.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use after quality gates pass in a long-task project — independently manages test environment lifecycle (start/cleanup), executes black-box acceptance testing per feature, generates ISO/IEC/IEEE 29119 compliant test case documents.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use after ST Go verdict — generate usage examples and finalize release documentation via SubAgent.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when bugfix-request.json exists - validate, reproduce, root-cause, and enqueue a user-reported bug as a category=bugfix feature, then chain to Worker for TDD fix.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when increment-request.json exists - collect incremental requirements, perform impact analysis, update design, and decompose new features.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when ATS doc exists (or auto-skipped) but feature-list.json not yet created - scaffold project artifacts and populate features from Design §10.2.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use after TDD cycle in a long-task project - enforces coverage gate, mutation gate, and fresh verification evidence before marking features as passing.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when no SRS doc and no design doc and no feature-list.json exist - elicit requirements through structured questioning and produce a high-quality SRS document aligned with ISO/IEC/IEEE 29148.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use after ST Go verdict when retrospective records exist and user authorized feedback — consolidate records and POST to REST API.

suriyel/longtaskforagent

Skill Claude CodeCodex

Use when all features in feature-list.json are passing - run comprehensive system testing before release, aligned with IEEE 829 and ISTQB best practices.