Skip to main content
Glama
seonmikii

gdc-claude-plugin

by seonmikii

task_from_doc

Create tasks from work request documents, extracting title and structured description, then record task_id and task_url in the document's frontmatter.

Instructions

작업 요청 문서로 태스크를 생성하고, 문서 frontmatter에 task_id/task_url을 기록한다.

  • 제목: 문서의 첫 '# ' 헤딩에서 추출.

  • description(필수): 호출하는 에이전트가 아래 라벨 섹션 템플릿(평문)으로 작성해 전달한다. 도구가 GDC 리치텍스트(HTML)로 변환해 저장한다(라벨→문단, 블렛→목록, 섹션 사이 빈 문단). [요약] 문서 "요청 내용" 한두 줄 요약

    [AS-IS] ← 선택(TO-BE와 짝): '요청 내용'·'배경'에서 구현 전 상황이 실제로 드러날 때만 구현 전 상황

    [TO-BE] ← 선택(AS-IS와 짝) 구현 후 상황

    [작업 내용]

    • 작업 결과 단계를 블렛(-)으로 간단히 요약 (각 단계 한 줄) ※ [요약]·[작업 내용]=필수, [AS-IS]/[TO-BE]=선택(짝). 전/후 상황이 불명확하면 생략(추측·빈말 금지) — 신규 기능·문서 작업엔 보통 빠진다. ※ 체크박스 표시([ ]/[x])는 넣지 않는다. 진행 상태는 태스크 progress 필드가 담당한다. ※ 빌드·타입체크·검증·테스트·lint·커밋·배포/동작 확인·'INDEX.md 이력 추가' 같은 프로세스 메타 단계는 넣지 않는다(실제 산출물 단계만). 넣더라도 도구가 자동 제거한다.

  • status: 생략 시 문서 메타데이터 표의 상태를 보고 매핑한다 — done → '완료'(완료/closed 계열), partial → '진행'(in_progress). 그 외 값은 자동 매핑하지 않고 기본 상태로 둔다. status 인자를 주면 그 값이 우선한다.

  • 완료 보정: 최종 status가 완료 계열(category=='done')이면 progress=100·실제 종료일=오늘을 자동 주입한다.

  • task_type: 호출하는 에이전트가 문서 유형/본문을 근거로 프로젝트 enum에 맞춰 매칭해 전달한다(get_project_enums 참고).

  • project: 생략 시 현재 레포에서 gdc_login으로 저장한 프로젝트(레포별 컨텍스트)를 사용.

  • 담당자(assignee): 항상 로그인 사용자로 자동 등록(create_task와 동일).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNo
projectNo
doc_pathYes
priorityNo
task_typeNo
descriptionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses behavioral traits: auto-extraction of title from '# ' heading, conversion of description to GDC rich text, status mapping from document metadata, automatic injection of progress=100 and actual end date for done status, and auto-assignment of assignee. It also discloses automatic removal of checklist markers and process meta steps, giving complete transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Though detailed, the description is well-structured with bullet points and clear section headers. Every sentence adds necessary operational detail, and the length is justified by the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers input parameters, transformations, default behaviors, and side effects (frontmatter update). An output schema exists, so lack of return-value explanation is acceptable. This is a complete specification for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description compensates substantially for description, status, project, task_type, and assignee behavior. It does not clarify the 'priority' parameter, leaving that one gap, which prevents a perfect 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource: 'create a task from a work request document' and record task_id/task_url in document frontmatter. This distinguishes it from sibling create_task, which lacks the document-writing aspect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool—when a task must be created from a document with metadata write-back—and references related tools (create_task, get_project_enums) for behavior. However, it stops short of explicit 'use this instead of X' exclusions, so it earns a 4 rather than a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/seonmikii/gdc-claude-plugin'

If you have feedback or need assistance with the MCP directory API, please join our Discord server