Agent skill

Extending Previous Architectural Models

by lukapiskorec in lukapiskorec/craftbot

Rules for continuing or remodeling a prior CraftBot building script: treat the inherited model as a found object, audit it against the brief, and track every change.

Custom licenceAuto-check passedDevelopment

Install Extending Previous Architectural Models

skills CLI
$ npx skills add lukapiskorec/craftbot --skill extending-previous-models -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lukapiskorec/craftbot extending-previous-models --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lukapiskorec/craftbot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/extending-previous-models .claude/skills/extending-previous-models && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
extending-previous-models
GitHub stars
152
Token cost
~750 tokens
SKILL.md length
414 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Rules for continuing or remodeling a prior CraftBot building script: treat the inherited model as a found object, audit it against the brief, and track every change.

  • Continuing another run's building model with new requirements
  • SKILL.md covers Overview, Taking over a model, Using what earlier runs learned and Provenance
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Adding sheathing or finish layers over an inherited frame

What it does

When one generated building design builds on, sheathes over or compares against an earlier one, this skill treats the inherited script as a found object: brought in unchanged, then changed only through explicit, auditable moves, each logged as old, change and why, so it stays clear what was kept versus deliberately altered. Before generating anything, the agent audits the inherited geometry against the new brief; if the frame makes a clean result impossible, such as hips standing proud of the board plane, correcting the frame is in scope because the real requirement is no geometric inconsistencies, and each conflict is listed with its measured excess.

Single members are overridden by re-creating them under their original name so a short pass after the inherited script can rebuild exactly the wrong parts without forking the whole script. Inherited dimensions are always re-derived with the source's own shared helper functions, never recomputed by hand. Prior runs' recorded failures, such as a hard corner-stud junction, become design constraints from the start rather than being rediscovered, and the current reference always adjudicates disputed choices against the earlier run's defaults, naming the figure that settles it.

When your agent uses it

  • Continuing another run's building model with new requirements
  • Adding sheathing or finish layers over an inherited frame
  • Comparing a new design against an earlier building for consistency
  • Fixing a geometric conflict that an inherited frame introduces

Example prompts

  • “Add sheathing over the inherited frame from the last run and list every change you make and why.”
  • “Audit the inherited roof geometry against this brief and flag any conflicts before generating anything.”
  • “Override just the corner post members by name without forking the whole script.”

Requirements

  • A prior CraftBot model or script to extend

What it can do on your machine

Read from SKILL.md and the folder at commit 2c9715b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Extending Previous Architectural Models loads about 750 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 414 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~750

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 414 words (~750 tokens).

“An inherited model is a found object: it comes in verbatim, gets changed only through explicit, auditable moves, and is expected to need fixing where the new work touches it.”

— opening of SKILL.md by lukapiskorec, Custom licence
name
extending-previous-models

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/extending-previous-models of lukapiskorec/craftbot.

Open the folder on GitHubat commit 2c9715b

Compare with similar skills

Extending Previous Architectural Models next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Extending Previous Architectural Models compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Extending Previous Architectural Models this skilllukapiskorec/craftbot152—~750Automated safety check: PassCustom licence
Dignified Python Standardsdocling-project/docling69k—~1.5kAutomated safety check: PassApache-2.0
Code Refactoring Workflowluongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT
Readable Pycrazyguitar/pysheeet8.2k—~2.4kAutomated safety check: PassMIT
jscpd Code Migration Trackerkucherenko/jscpd6.4k—~5kAutomated safety check: PassMIT
Refactor OpCVCUDA/CV-CUDA2.7k—~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Dignified Python Standards

    docling-project/docling

    Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.

    69k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Refactoring Workflow

    luongnv89/claude-howto

    Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.

    42k GitHub stars~3.1k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Readable Py

    crazyguitar/pysheeet

    Readable Python code rules inspired by The Art of Readable Code.

    8.2k GitHub stars~2.4k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Measures a code port between languages or frameworks with jscpd's function-level comparison, porting tests before code and tracking what is left unmatched.

    6.4k GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check passed
  • Refactor Op

    CVCUDA/CV-CUDA

    Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).

    2.7k GitHub stars~1.5k tokensUpdated 22 days ago
    DevelopmentAuto-check passed
  • Readable Verilog Generator

    Eriemon/verilog-generator

    A skill your agent uses when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL…

    312 GitHub stars~5.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from lukapiskorec/craftbot

All 13 skills in this repo
  • Turns a finished CraftBot building model into cut lists, stick orders and full-scale printable sheets for building a physical scale model by hand.

    152 GitHub stars~2.8k tokensUpdated 8 days ago
    Auto-check passed
  • Running a CraftBot Experiment

    lukapiskorec/craftbot

    Runs the six-agent CraftBot workflow in this specific repository, turning a design brief and references into versioned Blender Python scripts, renders, a rationale and an archived transcript.

    152 GitHub stars~9.1k tokensUpdated 8 days ago
    Auto-check passed
  • Modular Grids and Panelization

    lukapiskorec/craftbot

    Derives a building's dimensional grid from real sheet, panel, and transport constraints instead of hard-coding spacing numbers.

    152 GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed
  • Non-Orthogonal Timber Geometry

    lukapiskorec/craftbot

    Rules for modeling sloped, twisted and warped timber structures from straight members: ruled surfaces, per-bay framing, plane-cut legs and slab-exact clipping.

    152 GitHub stars~1.2k tokensUpdated 8 days ago
    Auto-check passed
  • Guides Blender Python that generates construction geometry from derived parametric expressions instead of hand-typed coordinates, so changes propagate and overlaps stay checkable.

    152 GitHub stars~1.4k tokensUpdated 8 days ago
    Auto-check passed
  • Reading Visual References

    lukapiskorec/craftbot

    A skill your agent uses when the reference material for an experiment is photographs, drawings, or floor plans rather than (or alongside) a dimensioned manual, and dimensions or topology must be…

    152 GitHub stars~994 tokensUpdated 8 days ago
    Auto-check passed

Works with

Categories

Questions about Extending Previous Architectural Models

What does Extending Previous Architectural Models do?

Rules for continuing or remodeling a prior CraftBot building script: treat the inherited model as a found object, audit it against the brief, and track every change. When one generated building design builds on, sheathes over or compares against an earlier one, this skill treats the inherited script as a found object: brought in unchanged, then changed only through explicit, auditable moves, each logged as old, change and why, so it stays clear what was kept versus deliberately altered. Before generating anything, the agent audits the inherited geometry against the new brief; if the frame makes a clean result impossible, such as hips standing proud of the board plane, correcting the frame is in scope because the real requirement is no geometric inconsistencies, and each conflict is listed with its measured excess.

When should I use Extending Previous Architectural Models?

Extending Previous Architectural Models fits situations like: continuing another run's building model with new requirements; adding sheathing or finish layers over an inherited frame; comparing a new design against an earlier building for consistency; fixing a geometric conflict that an inherited frame introduces.

How do I install Extending Previous Architectural Models in Claude Code?

Run `npx skills add lukapiskorec/craftbot --skill extending-previous-models -a claude-code`. Or copy the skill folder (skills/extending-previous-models in lukapiskorec/craftbot) into .claude/skills/extending-previous-models in your project. Claude Code loads it when a task matches its description.

How do I install Extending Previous Architectural Models in Codex?

Run `npx skills add lukapiskorec/craftbot --skill extending-previous-models -a codex`. Or copy the skill folder (skills/extending-previous-models in lukapiskorec/craftbot) into .agents/skills/extending-previous-models in your project. Codex loads it when a task matches its description.

Can I use Extending Previous Architectural Models in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lukapiskorec/craftbot --skill extending-previous-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extending-previous-models, .gemini/skills/extending-previous-models, .github/skills/extending-previous-models and .opencode/skills/extending-previous-models in your project.

What does Extending Previous Architectural Models need to run?

SKILL.md names no scripts, command-line tools or credentials: Extending Previous Architectural Models is instructions for the agent only. Our summary lists: A prior CraftBot model or script to extend.

Does Extending Previous Architectural Models access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Extending Previous Architectural Models safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Extending Previous Architectural Models use?

Extending Previous Architectural Models has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Extending Previous Architectural Models use?

About 750 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Extending Previous Architectural Models?

Skills that share tags, products or a category with Extending Previous Architectural Models: Dignified Python Standards (docling-project/docling, 69k stars), Code Refactoring Workflow (luongnv89/claude-howto, 42k stars), Readable Py (crazyguitar/pysheeet, 8.2k stars) and jscpd Code Migration Tracker (kucherenko/jscpd, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Extending Previous Architectural Models?

lukapiskorec (a GitHub user) maintains it in lukapiskorec/craftbot, which has 152 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 30, 2026.

Source: lukapiskorec/craftbot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.