agentleFS
MakeItEzzz555MakeItEzzz555/Gridline/skills/precedent-research/SKILL.md

precedent-research

Skill39 starsChanged 23 days agoMITView on GitHub

Research and compare architectural precedents by typology, climate, program, circulation, structure, envelope, materials, construction, performance and design intent. Use for precedent studies, case-study matrices, design references, lessons learned, and evidence-backed concept inputs.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use precedents as evidence and transferable lessons, not as designs to copy.

    line 8
  2. Very specific:

    Keep verified facts, project assumptions, design options, and unresolved questions visibly separate.

    line 15
  3. Distinctive:

    Do not infer hidden structural, cost or performance data from photographs.

    line 34
  4. Distinctive:

    Do not present resemblance to a precedent as proof of performance or compliance.

    line 41
  5. Distinctive:

    If the native application is unavailable, produce a reproducible plan, script, structured data, SVG/DXF artifact, or exact in-application …

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Architectural Precedent Research

Use precedents as evidence and transferable lessons, not as designs to copy.

Preflight

  • Project type, scale, climate, site/context and design question.
  • Which attributes matter: plan, section, circulation, facade, structure, envelope, material, public realm, flexibility, sustainability or delivery.

Keep verified facts, project assumptions, design options, and unresolved questions visibly separate. If a required input is absent, record it as UNKNOWN rather than inventing it.

Workflow

  1. Find primary project sources, architect/engineer documentation, reputable publications and drawings where legally available.
  2. Extract comparable facts into a matrix; distinguish documented fact from visual interpretation.
  3. Identify transferable principles and failure risks; explain why each precedent is relevant to this project.
  4. Translate findings into design criteria rather than stylistic imitation.

Deliverables

  • Sourced precedent matrix
  • Diagram brief for plan/section/massing comparisons
  • Transferable principles
  • Open questions and evidence gaps

Verification

  • Citations identify project/source and date where available.
  • Do not infer hidden structural, cost or performance data from photographs.

For file/model changes, compare the result against a pre-change baseline and report changed items, skipped items, failures, and checks actually run.

Professional boundaries

  • Respect copyright; summarize and diagram rather than reproducing protected drawing sets.
  • Do not present resemblance to a precedent as proof of performance or compliance.

If a live CAD/BIM/GIS/analysis tool or MCP integration is available, inspect the current document/model and tool version before write operations. Prefer read-only inspection, dry runs, bounded samples, new output paths, and native undo/transaction mechanisms. Never claim a model or drawing was changed unless the tool confirms it.

If the native application is unavailable, produce a reproducible plan, script, structured data, SVG/DXF artifact, or exact in-application procedure instead of pretending to have operated the software.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.