Community研究與資料分析github.com

precedent-dossier

Research architectural precedents into a cited dossier with a source ledger, so no claim (architect, year, client, program, dimension, intent) reaches a crit without a source id. Sets up the folder, assigns stable S### ids at time of access, ranks sources by class (architect, permit/public record, publication, builder, listing/marketing, social), separates architect-stated intent from inference, records contradictions instead of resolving them silently, tracks drawings and saved images with provenance, and validates the ledger with scripts/check_ledger.py. Use for "precedent research", "find precedents", "case studies", "research this building", "sources for", "who designed", "dossier", or any request to find drawings, intent, or facts about an existing building.

precedent-dossier 是什麼?

precedent-dossier is a Claude Code agent skill that research architectural precedents into a cited dossier with a source ledger, so no claim (architect, year, client, program, dimension, intent) reaches a crit without a source id. Sets up the folder, assigns stable S### ids at time of access, ranks sources by class (architect, permit/public record, publication, builder, listing/marketing, social), separates architect-stated intent from inference, records contradictions instead of resolving them silently, tracks drawings and saved images with provenance, and validates the ledger with scripts/check_ledger.py. Use for "precedent research", "find precedents", "case studies", "research this building", "sources for", "who designed", "dossier", or any request to find drawings, intent, or facts about an existing building.

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/zohartito/arch-skills/tree/HEAD/skills/precedent-dossier

Installed? Explore more 研究與資料分析 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Precedent dossier

Modeled on a real studio research dossier (four houses, three parallel lanes, 69-source ledger) and that project's facts sheet. Rule zero: cite or don't claim.

1. Folder layout

<project>/research/YYYY-MM-DD-<topic>/
  README.md            start here: identity table (spoken target -> resolved project ->
                       architect -> confidence + source ids), read order, known gaps
  RESEARCH-BRIEF.md    the ask as given, targets verbatim, lanes + id blocks, permissions
  SOURCES.csv          the ledger. One row per URL. Primary agent owns it.
  agents/NN-slug.md    one note per precedent (or tight pair), from templates/precedent-note.md
  DRAWINGS.md          D## index: type, local file, source id + page, scale, limits
  ASSET-INVENTORY.json every saved file: path, kind, source_id, url, bytes, sha256
  SYNTHESIS.md         transferable moves -> proposed tests for our project (inference, labelled)
  VERIFICATION.json    checks run, results, limits, file hashes
  NEXT-AGENT.md        ten-line primer for whoever resumes
  assets/  evidence/   saved PDFs/images (assets) and page captures/records (evidence),
                       prefixed by lane: 00- primary, 01-, 02-, ...

Optional: ACCESS.md when records took real work to get (portal, API, request form, what failed). The original dossier called this PUBLIC-RECORDS-AND-DRAWING-ACCESS.md.

2. Source classes and weight

Use these source_class values (the first six come from the original ledger):

source_classAuthoritative forNot evidence for
architect project sourcecredit, project name, published drawings, architect's stated intentas-built state, exact areas (often rounded)
official civic / planning recordlegal address/parcel, permitted program, architect/engineer of record, permit dates, written dims on scanned plansdesign intent; current condition
architect firm sourcefirm-general philosophythis project's intent (applying it = inference)
project builder sourcecredit, completion year, program as builtarchitect's intent
publication / corroborationarchitect quotes inside interviews; second source for creditseditorial attributions on their own (the original dossier: a broker editorial misattributed one house)
listing / property corroborationaddress, photos, marketing areasauthorship, intent, scale (listing plans lacked title blocks)
developer / marketingclient/developer identity, unit mix as soldarchitect intent, verified areas
book / academicanalysis, historical context, published drawings with scalecurrent state
social / user-posteda lead to followanything, until a stronger source confirms it

When sources disagree, the higher class usually wins for its own column only: a permit beats a listing on legal program; the architect beats the permit on intent.

3. Citation rules

  • Ledger first. Add the row to SOURCES.csv when you open the source, not afterwards. Ids are S###, assigned once, never renumbered. Do not generate ids by sorting URLs; that renumbers everything when a source is added.
  • Every factual claim carries an id on the same line: [S012], [S012 p.73], [S012 fig.4; S020 p.3]. Pinpoints (page, sheet, figure, timestamp) go in the citation, never in the ledger label, because one URL is one row however many pages you cite.
  • A claim with no source is marked [unsourced] or deleted. Never in a crit deck.
  • Attributions (architect, year, client, architect of record) need a architect project source or official civic / planning record, or two independent sources from other classes. Republished press repeating one release counts once.
  • Dimensions come only from a drawing or record that writes the number or states a scale: [S021 p.3, written] or [S021 p.3, scaled 1/8"=1'-0"]. Never from a photo, render, or image proportions. Published areas are "published figures", not measurements. Our own derived numbers say [derived: method] and cite their inputs (facts-sheet pattern).
  • Intent layers stay separate: architect-stated / team- or client-stated / firm-general / observed in photos / our inference. Label which layer each move belongs to.
  • Status words from the project's evidence vocabulary: verified-file, verified-live, reported, inference, rejected. Search snippets and blocked pages are reported, never verified.
  • qualification is specific to that source ("permit names architect of record, not designer"; "plans cropped, no title block"). Never boilerplate like "see report".
  • access_date_local is the day that source was actually opened.

4. Parallel research (what the original dossier did)

It ran three fresh-context agents, one lane each, while the primary integrated:

  • Each lane owns agents/NN-slug.md and assets/evidence prefixed NN-. Lanes never edit README, SYNTHESIS, SOURCES.csv, or project handoff files.
  • Give each lane an id block so parallel ids never collide: primary S001-S099, lane 01 S100-S199, lane 02 S200-S299. Lanes put their rows in a ## Sources table at the bottom of their note with the ledger's columns.
  • The primary merges those rows into SOURCES.csv. If two lanes ledgered the same URL, keep the lower id and replace the other in the notes. Then it checks the key evidence itself (opens the permit, looks at the plan) and writes README, SYNTHESIS, DRAWINGS.
  • One precedent? Skip the lanes and write agents/01-slug.md yourself.

5. Copyright and assets

  • Store links, short attributed quotes (a sentence at most) and your own paraphrase. Never paste long passages or whole articles.
  • Save images/PDFs locally only as private study references: record path, source id, URL, access date, sha256 in ASSET-INVENTORY.json. Claim no publication licence.
  • No login or paywall bypass, no buying documents, no contacting architects or owners unless the user says so. A blocked page is recorded as blocked.
  • Never substitute AI-generated or redrawn drawings for source drawings. Redraws are ours, labelled as such, and cite the sheet they trace.

6. Contradictions

Every note has a ## Contradictions section. Record both sides with ids, which one you prefer and why (class, date, specificity), or "unresolved". Rejected claims go in ## Do not reintroduce so the next agent doesn't revive them (the original dossier: a wrong firm credit and a predecessor address). Area/program figures that drift across permit, approval and listing stay listed side by side; never average them into one "verified" number.

7. Validate

python3 scripts/check_ledger.py <dossier>   # from this skill's folder

Exit 1 = hard errors (bad/missing columns, duplicate or malformed ids, bad URLs, empty required fields, notes citing ids that aren't in the ledger). Warnings: ledger rows never cited, inline URLs not in the ledger, lines with a number + unit and no source on the same line, boilerplate qualifications, duplicate URLs. Markdown links to ledger URLs count as citations, so older URL-cited dossiers can still be checked.

Done means

  • README identity table: every architect/year/client cell has ids and a confidence word
  • check_ledger.py exits 0; each remaining warning is fixed or explained in VERIFICATION
  • No dimension without a drawing/record id and a stated scale or "written"
  • Each note: intent layers separated, ## Contradictions, ## Do not reintroduce, search audit
  • Every saved file is in ASSET-INVENTORY.json with source id and sha256
  • DRAWINGS.md says what was not found (no sections? say so) and the best next access route
  • SYNTHESIS proposes tests, labelled inference; nothing claimed as adopted design
  • NEXT-AGENT.md written; open questions listed, not smoothed over

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

physical-model-prep

Prepare physical architecture studio models for fabrication - 3D-print STLs and laser-cut .3dm files generated from the saved Rhino model, with the scales, materials, layer colours, fit clearances, measured laser burn, laser settings per material (basswood, plywood, MDF engrave, mat board) and USB hand-off that one real studio project's models (Oct 2026) actually used, plus the rules the user's corrections set. Use when asked for a "laser file", to "laser cut" or "score" or "engrave" parts, "laser settings", square or round "post holes", "kerf", to "3D print the model", to build a "massing model" or "chunk model", for a "cut list", for anything at the "fab lab" or the "plotter USB", or when making a "model base" or "lot insert". Not for image-editing effects such as an engraved look in Photoshop, which involve no laser or printer.

sheet-review

Preflight and review an exported presentation sheet (PDF) and its InDesign source before calling it done — page size, embedded fonts, image PPI, small and placeholder text, scale notations, hairlines, off-palette and legend-only colors, a change diff against the previous export, InDesign overset / links / placed-drawing scale / missing fonts, then a tile-by-tile visual pass for stray linework and legend-to-symbol mismatches. Use when the user says "check the sheet", "review the PDF", "is the board ready", "preflight", "before I print / plot / submit", after any InDesign export, or before reporting a layout as verified.

相關技能