kdy1/kdy1-scripts

write-blog-post

Collect the user's blog material, suggest topics to develop, and rephrase and reorder supplied content into a draft only on request.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/kdy1/kdy1-scripts --skill write-blog-post

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Write Blog Post

Help the user develop a blog post from their own material. By default, collect their notes and suggest what they could write about. Write or revise a draft only when the user explicitly asks for drafting, rephrasing, or arranging the supplied material. Invoking the skill alone is not a request for a draft.

Preserve the source

  • Use only content the user supplies for this post. Do not infer or invent facts, experiences, intentions, causal relationships, or conclusions. Do not fill gaps with outside research or model knowledge.
  • Keep user-supplied material separate from your suggestions and unanswered questions. Selecting a suggested topic does not supply the details needed to write it.
  • Preserve meaning, point of view, names, links, numbers, and the user's degree of certainty. A possibility must not become a fact, and a sequence of events must not become a causal claim.
  • Ask focused questions when an ambiguity or contradiction affects meaning. Leave unresolved material out of prose that would require choosing an interpretation, and identify the gap separately.

Collect material and suggest topics

  • Accumulate the user's material across messages in the current conversation, incorporating their explicit corrections and additions.
  • When given only a topic, suggest useful angles or questions the user could develop; do not generate an article from the topic.
  • Ground suggestions in the supplied topic or notes. Phrase them as optional topics or questions without assuming the user had a particular experience, motivation, or result.
  • Keep collection replies brief: acknowledge the new material and offer relevant suggestions or necessary questions. Do not repeat all collected notes or produce draft prose unless requested.
  • Continue collecting when more notes arrive, even after an earlier draft. An earlier drafting request does not authorize automatic draft updates on later turns.

Rephrase and arrange on request

  • Use the accumulated user material when asked to draft or organize the post. Respect a request to edit only a particular passage.
  • Rephrase for clarity and natural blog prose, group related ideas, reorder them for a readable progression, and remove redundancy without losing distinct points or qualifications.
  • Preserve the input language unless the user requests another language. Make the tone natural without forcing the original wording, a fixed level of formality, or a fixed blog structure. Follow explicit style preferences.
  • Use titles, headings, introductions, transitions, and endings only when supported by the supplied material. Do not add a new takeaway, explanation, or causal link to make the post feel complete.
  • If there is enough material for only part of a post, draft that part and list the missing material separately. If only a topic is available, ask for content or suggest what to add instead of fabricating a draft.

Output

  • During collection, return concise suggestions or questions rather than a draft.
  • When drafting is requested, present the requested text in readable Markdown. Put any remaining questions or optional content suggestions outside the draft under a separate, clearly labeled section.
  • Before returning prose, check that every substantive claim comes from user-supplied material and that no suggestion or uncertain statement has become an established fact.
같은 저장소의 Skills

더 많은 Skills

모든 Skills
kdy1
커뮤니티

add-issue

Investigate explicitly requested work in the local environment by default, inspect relevant logs, repair confirmed regenerable local state, and create evidence-backed GitHub issues for confirmed Bugs or decision-complete Features and Tasks without implementing product changes. Start only on explicit human $add-issue invocation or an authorized candidate handoff from human-invoked MainQA, Static Analysis, or Collect Review; ordinary reports, ideas, and skill editing do not start this workflow.

설치 수
1
GitHub Stars
34
업데이트
10월 23일
kdy1
커뮤니티

fork-gungraun-optimize

Update or configure Gungraun measurement infrastructure on a personal fork's default branch on top of the latest upstream code, then validate optimization PR candidates with profiles and benchmarks from fork CI. Use for ForkGungraunOptimize requests or performance optimization based on a personal fork. Create each upstream PR only after human approval of that candidate.

설치 수
1
GitHub Stars
34
업데이트
10월 23일
kdy1
커뮤니티

manage-stacked-prs

Modify existing GitHub stacked PRs and restack and verify affected upper layers with gh stack. Apply when editing a PR in an existing stack or repairing its alignment. Preserve unrelated lower PRs; fix a lower layer only when its confirmed defect blocks the requested work. Stack creation and merging remain separate workflows.

설치 수
1
GitHub Stars
34
업데이트
10월 23일
kdy1
커뮤니티

static-analysis

Analyze all code in a user-specified scope, or the whole repository when scope is omitted, and hand each confirmed bug to $add-issue immediately. Use for requested comprehensive static bug analysis; issue recording requires a direct human invocation of $static-analysis or an explicit request to run Static Analysis.

설치 수
1
GitHub Stars
34
업데이트
10월 23일