Skip to content

DavidCho1999/archaiflow-skills / bundles/construction-admin/skills/drawing-checklist

drawing-checklist

Verified

This skill should be used when the user needs a phase-specific drawing-set checklist for an architectural project — SD, DD, CD, or IFC. Trigger on 'make a checklist', 'drawing set review', 'CD checklist', 'DD set review', or pasted phase + project-type context. Generates a structured checklist markdown in `docs/checklists/` and updates the project checklist index.

---
name: drawing-checklist
description: "This skill should be used when the user needs a phase-specific drawing-set checklist for an architectural project — SD, DD, CD, or IFC. Trigger on 'make a checklist', 'drawing set review', 'CD checklist', 'DD set review', or pasted phase + project-type context. Generates a structured checklist markdown in `docs/checklists/` and updates the project checklist index."
license: MIT
metadata:
  title: "Drawing Checklist"
  summary: "Get a drawing-set checklist for the phase you are in"
  discipline: "construction-admin"
  tags: "Design"
---


# Drawing Checklist


## Overview


Generate a phase-specific drawing-set checklist (SD / DD / CD / IFC) for an architectural project, scoped to project type and primary discipline, with cross-discipline coordination flags. The checklist lives in `docs/checklists/` and serves as a working punch-list before issuing the set.


## Scope and limits — read first


**What this does.** Builds a checklist for one phase, one project type, and one
discipline: the sheet series that phase expects, the level of detail expected on
each, the items that commonly go missing, and the cross-discipline flags worth
raising now. It lands in `docs/checklists/` as a punch list to work through
before the set is issued.

**What this does not do.**

- **It does not open your drawings.** The checklist says what should be there.
  Confirming that it is there is the pass you make against your own set.
- It does not judge design quality. Completeness only; critique is
  `design-critic`.
- It does not check code compliance. A complete set can still fail code, and
  that is `code-compliance-review`.
- It does not produce structural or MEP checklists. Architecture is the primary
  discipline here and the others appear only as coordination flags.
- It does not know your contract's thresholds. The percent-complete figures are
  the industry convention, and where your agreement defines its own, yours
  govern.

**What you need before starting.** The phase, the project type, and the
discipline. If your office standards or your owner-architect agreement set their
own deliverable thresholds, have those in front of you.

## When to use


Trigger on:

- Phase + project-type context ("DD set for a 5-story commercial", "IFC review for civic project").
- Explicit asks: "make a checklist", "review the drawing set", "DD set review", "CD checklist", "drawing checklist for <phase>".
- Pre-issue review of a drawing set when the user wants a structured pass.

Do NOT trigger for design critique (use `design-critic`), RFI generation (use `rfi-writer`), or general drafting standards questions.


## Workflow


### Step 1 — Bootstrap if needed


Check `docs/checklists/index.md` exists. If not:


```bash
python scripts/init_checklist_workspace.py
```


### Step 2 — Gather context

- Read `docs/project.md` if present for site, program, scale, project type.
- Identify the **phase** (SD / DD / CD / IFC), **discipline** (architectural primary, with structural/MEP coordination notes), and **project type** (residential / commercial / civic / mixed-use / industrial).
- If the phase or project type is ambiguous, ask one clarifying question before continuing.

### Step 3 — Load references

- `references/phase_deliverables.md` — percent-complete and deliverable expectations per phase (AIA B101 / industry norm).
- `references/sheet_types.md` — required sheet content per phase by sheet series.
- `references/coordination_flags.md` — common architectural-to-structural and architectural-to-MEP coordination items.

### Step 4 — Compose the checklist


Build the checklist around:

- Required sheet types at this phase, by series (G / A / structural-coord / MEP-coord).
- Level of detail expected per sheet type at this phase.
- Common missing items: callouts, dimension strings, key plans, tags, north arrow consistency.
- Cross-discipline coordination flags: structural grid alignment, MEP chase locations, ceiling height conflicts, slab depressions, roof penetrations.
- Title block / sheet numbering / revision cloud hygiene.
- Phase-specific deliverable expectations (SD ~15-30%, DD ~35-50%, CD 100% biddable, IFC 100% issued).

### Step 5 — Write the checklist file


Read `assets/checklist-template.md`, fill placeholders. Filename:


`docs/checklists/<phase>-<discipline>-checklist.md`


Slug rule: lowercase, `[^a-z0-9-]` removed. Example: `dd-architectural-checklist.md`, `cd-architectural-checklist.md`. If a checklist with the same name exists, suffix `-<n>`.


### Step 6 — Update the checklist index


```bash
python scripts/append_to_index.py \
  --date 2026-05-06 \
  --phase DD \
  --discipline architectural \
  --project-type commercial \
  --slug dd-architectural-checklist
```


The script appends a row to `docs/checklists/index.md`. Do NOT edit the index manually.


### Step 7 — Report


Tell the user:

- Path to the checklist file.
- The 2-3 highest-risk items at this phase for this project type.
- Whether any cross-discipline coordination items need to be raised with consultants now.

## Rules

- Tie every item to either a sheet, a deliverable percent, or a coordination interface — no vague "make sure it's coordinated".
- Phase percent-complete is a guide, not a contract — note if the project's contract defines its own thresholds.
- Architectural is the primary discipline; structural and MEP appear only as coordination flags, not as full discipline checklists.
- For IFC, every "TBD" / "by others" / "VIF" callout is a defect. Flag explicitly.

## Anti-patterns

- Generic checklists that ignore project type (a residential CD set is not a civic CD set).
- Listing every conceivable sheet type regardless of project scope.
- Mixing critique with checklist — this skill checks completeness, not design quality.
- Editing `index.md` manually instead of using `append_to_index.py`.
- Restating CAD/BIM standards the office already enforces — focus on the per-phase delta.

## Resources

- `scripts/init_checklist_workspace.py` — bootstrap `docs/checklists/` and the checklist index
- `scripts/append_to_index.py` — append a row to `docs/checklists/index.md`
- `references/phase_deliverables.md` — SD / DD / CD / IFC deliverable expectations and percent-complete
- `references/sheet_types.md` — architectural sheet types with required content per phase
- `references/coordination_flags.md` — architectural-to-structural / architectural-to-MEP coordination items
- `assets/checklist-template.md` — checklist markdown template
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall