본문으로 건너뛰기
cccskills
무료GitHub에 공개

schedule-quantity-reconcile

Compare scoped quantity snapshots and explain matches, missing rows and conflicts. Use to reconcile drawing, report or schedule counts; not to extract source documents or update adopted records.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(3)

  • SKILL.md4.1 KB
  • host-contract.json1.1 KB
  • README.md311 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

/as:schedule-quantity-reconcile — Reconcile sourced quantities

Before acting, read the host contract and declaration (skill:schedule-quantity-reconcile), using its profiles from the catalog. No source or write access is implied.

<!-- architecture-studio:harness-compatibility -->

Use the host adapter and available native tools or ordinary task-specific code. Operation names identify semantic procedures, not installed functions. No Arch Studio runner, package installation or executable reconstruction is required. Existing exact authorization persists; ask only for material missing information or permission.

Input: two source-identified quantity snapshots and explicit building/floor/phase/revision scope. Output: a read-only comparison, not an authoritative merged schedule. Project instructions apply when bound to a project; one-off comparison does not initialize or adopt records.

  1. Read both actual inputs and preserve hashes/locators. Drawing extraction belongs to /as:drawing-quantity-extract. Do not compare a whole-campus inventory against one floor as though their denominators match. Missing scope or unit evidence remains unresolved.
  2. Read native evidence procedures. Prepare exact tag/scope/unit keys and preserve every contributing source row. Explicitly resolve aliases or unit conversions using source evidence before comparison; no fuzzy match or automatic phase/room synonym.
  3. Apply schedule_reconcile.compare with native computation under its evidence procedure. Duplicate keys require explicit aggregation or conflict resolution first. Unknown is null, not zero; absent rows are not zero. Matching supplied values proves agreement, not correctness or completeness. Lighting reports first use /as:lighting-report-extract to distinguish inventory from calculation surfaces. Never sum repeated room inventory to remove duplicate keys. Before projecting normalized groups to tag/scope/unit, explicitly select matching source revisions, rooms, scenes and variants on both sides, or preserve those distinctions in the agreed comparison scope. Keep every contributing locator; do not flatten unresolved/conflicting identity into an authoritative quantity. The comparison rejects duplicate comparison keys; it does not choose or merge lighting inventories.
  4. Explain each discrepancy with locators on both sides and source coverage. A revision note can explain a split but does not authorize changing labels or records. Preserve competing values; distinguish a proposed correction from an approved one. Product identity/spec discrepancies route to /as:product-audit; do not enlarge this skill into a general product audit.
  5. Return matched, conflicting, missing and unknown groups. Save only an authorized derived report and read it back; do not change original files. Adopted changes go to /as:master-schedule with explicit selected changes and expected revisions. Missing host capability yields a bounded handoff, not a fabricated match or silent fallback. On retry, reread input hashes before reusing results.

Current document placement

Save only authorized derived outputs and verify their actual content, source hashes and complete requested scope. Inline answers and one-off files need no project setup or adoption. For a requested registered project report, resolve confirmed coordinates using the receive-owned native documents.resolve/register semantics in the workspace model, including its complete document/register mutation sequence. Find existing records with documents.query; never guess a folder. This conditional handoff does not authorize schedule or library changes.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

agreement

무료

Maintain sourced agreement context and scope in PROJECT.md, cite registered contracts/proposals, and record amendments without imposing a commercial workflow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

Explain US architecture professional-practice terms, phases, deliverables, roles, delivery methods, AIA contract families, CSI documentation systems, or NCS at a high level. Use for questions such as “what is a CD set?” or “what does 50% CDs mean?”; do not use for code/jurisdiction, outline-spec, agreement-scope, or work-plan work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks. Use for color schemes or brand colors.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

Research population, income, age, housing, and employment around a site. Use for census, demographic, or local-market questions tied to a location.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

Extract countable FF&E or luminaire instances from supplied drawings with position-level evidence. Use for plan quantities or symbol counts; not area takeoffs, product specs or cross-source reconciliation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AlpacaLabsLLC/skills-for-architects3852026년 10월 21일 업데이트

AlpacaLabsLLC의 스킬 모두 보기

이 스킬의 문제 신고