TashanGKD/tashan-cursor-skills
Agent
A separate reviewer for AI features, including language-model calls, prompts, and agent output. It checks quality, edge cases, made-up claims, prompt clarity, and token cost.
TashanGKD/tashan-cursor-skills
Agent
A hostile review agent for checking a technical architecture draft. It looks for security weaknesses, performance limits, failures in outside services, data-consistency risks, and hard-to-change decisions.
TashanGKD/tashan-cursor-skills
Agent
A background logging agent for recording important decisions and discoveries while people and AI build a new skill, mechanism, or architecture together.
TashanGKD/tashan-cursor-skills
Agent
A background agent that watches for newly confirmed principles or major updates to a foundational document. It analyzes which work areas may need review and adds follow-up tasks to a master checklist.
TashanGKD/tashan-cursor-skills
Agent
A tool that combines five or more separate notes or fragments into an existing higher-level document. It reads the document and fragments together, then proposes where each fragment belongs and drafts matching text.
TashanGKD/tashan-cursor-skills
Agent
An agent that extracts reusable lessons from completed work involving a structured knowledge system. It turns task details into candidate knowledge fragments or deeper guiding principles.
TashanGKD/tashan-cursor-skills
Agent
A consistency checker for a knowledge system’s documents and guiding principles. It independently compares an updated document with the system’s map, principles, and related documents.
TashanGKD/tashan-cursor-skills
Agent
A coding agent that fixes reported bugs using test-driven development, or TDD: reproduce the problem, write a failing test, change the code, and confirm the tests pass. It first checks what the affected feature is meant to do.
TashanGKD/tashan-cursor-skills
Agent
A read-only reviewer for technical architecture documents and product definitions. It checks whether the planned system matches the product and whether important technical decisions are recorded.
TashanGKD/tashan-cursor-skills
Agent
A read-only reviewer that checks whether a development plan, issue lists, and recorded changes match the work actually done.
TashanGKD/tashan-cursor-skills
Agent
A document reviewer that checks a product definition from the viewpoint of a professional product manager taking over the project. It reads the product document, issue tracker, and recorded user decisions without changing them.
TashanGKD/tashan-cursor-skills
Agent
A review agent that acts like an AI reading a Skill, agent, or rule for the first time. It looks for unclear instructions, overlapping triggers, hidden assumptions, and missing failure paths.
TashanGKD/tashan-cursor-skills
Agent
A destructive review agent that looks for conflicts and failure paths among coding-agent skills, agents, and rules.
TashanGKD/tashan-cursor-skills
Agent
An agent that turns one project lesson into a new or updated reusable Skill. A Skill is a set of instructions an AI agent can follow for a recurring type of work.
TashanGKD/tashan-cursor-skills
Agent
A review agent that pretends to be different kinds of real users and tries a product’s main journeys. It checks the product without relying on the designer’s intentions.
TashanGKD/tashan-cursor-skills
Agent
A read-only reviewer that examines an interface from the viewpoint of someone seeing the product for the first time. It checks visual order, wording and icons, task flow, empty or error states, mobile use, and accessibility.
TashanGKD/tashan-cursor-skills
Agent
A guide for an independent testing agent that checks whether completed code works, integrates correctly, handles errors, and matches the stated requirements.
TashanGKD/tashan-cursor-skills
Agent
A helper agent for downloading batches of articles from WeChat public accounts. WeChat is a Chinese messaging and publishing platform, and a public account is a publisher's channel there.
TashanGKD/tashan-cursor-skills
Cursor rule
A deprecated rule written in Chinese for automatically recording lessons after a task finishes, while directing current behavior to another session-startup rule.
TashanGKD/tashan-cursor-skills
Cursor rule
A rule for fixing software bugs with test-driven development, or TDD: first reproduce the bug, then write a test that fails, then make the smallest code change that passes it, and finally run the full checks.
TashanGKD/tashan-cursor-skills
Cursor rule
A process log for collaborative creative work, such as building a new skill, redesigning an architecture, or creating a new mechanism. It records important decisions, changes of direction, discoveries, and the final outcome.
TashanGKD/tashan-cursor-skills
Cursor rule
A rule for reusing existing code when the user explicitly asks for reuse or copying. It requires the agent to find and verify the original implementation before calling or copying it.
TashanGKD/tashan-cursor-skills
Cursor rule
An automatic logging rule for important changes to a cognitive-structure system. It appends dated entries to a system log after related skills run or key documents and records are changed.
TashanGKD/tashan-cursor-skills
Cursor rule
A consistency check for adding new material to L1 cognitive-structure documents. It compares the new text with confirmed L1.5 principles, which are the system’s underlying rules.