Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Architecture

skill · InternLM/WildClawBenchMIT licenceAudited 15 Oct 2026 · source a79d9cd3663a

★ 533pushed 27 days ago
✓SAFEGrade B · 89/100 · 15 Oct 2026 · a79d9cd
533repo stars · whole InternLM/WildClawBench

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit a79d9cd3663a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Support architectural understanding from home projects to professional practice and theory.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Architecture (InternLM/WildClawBench)”. Retrieved 15 Oct 2026. https://modelsatlas.com/skills/internlm/architecture

3 skills are called “Architecture”. You are viewing InternLM/WildClawBench.

Trust audit

Audit 0.4.1 · source read 15 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha a79d9cd3663a · 15 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherInternLM GitHub organizationOwner of the repository this skill is read from
  • Source folderInternLM/WildClawBench/skills/2/architectureThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicta79d9cd3663aA new audit runs when the source changes
  • Repository statusNot archivedLast push 27 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Support architectural understanding from home projects to professional practice and theory.

---
name: Architecture
description: Support architectural understanding from home projects to professional practice and theory.
metadata: {"clawdbot":{"emoji":"🏛️","os":["linux","darwin","win32"]}}
---

## Detect Level, Adapt Everything
- Context reveals level: vocabulary, technical depth, professional credentials
- When unclear, ask about their role before giving specific guidance
- Ask project location for code and zoning questions; requirements vary by jurisdiction

## For Homeowners: Clear Expectations
- Translate drawings into plain language — explain floor plans, elevations, sections; what symbols mean; how to read scale notations
- Explain design phases — Schematic Design → Design Development → Construction Documents → Bidding → Construction Administration; what happens when
- Demystify fee structures — percentage of construction, hourly, fixed fee; what's included vs extra; contract red flags
- Clarify permit thresholds — structural changes, electrical, plumbing, adding space need permits; cosmetic updates usually don't; verify locally
- Set budget reality — 15-20% contingency rule; why estimates differ from bids; common surprises (soil, asbestos, code upgrades); soft vs hard costs
- Prepare for realistic timelines — permit review 2-12+ weeks; design takes longer than expected; construction almost always extends
- Decode terminology on demand — setback, FAR, egress, bearing wall, as-built, punch list with context for why it matters
- Guide productive communication — how to give useful feedback; questions before hiring; when to push back vs trust professional

## For Students: Design and Rigor
- Explain principles with visual language — reference built examples; describe how principles manifest physically; never speak abstractly
- Cite movements with precision — time period, seminal buildings, key architects, theoretical context; students need citation accuracy
- Support technical drawing conventions — orthographic projection, axonometric, perspective; lineweights, notation, scale; match professional standards
- Guide precedent analysis — program, site response, structure, circulation, spatial sequence, materiality, theoretical positioning
- Use studio vocabulary — parti, poché, datum, threshold, hierarchy, procession, figure-ground, phenomenology; language of architecture juries
- Support thesis-level theory — Vitruvius to Venturi to Koolhaas; phenomenologists like Pallasmaa and Zumthor; help position work in frameworks
- Distinguish concept from resolution — early stage needs conceptual provocation; later stages need technical resolution; ask where in process
- Respect drawing as thinking — encourage sketching and diagramming; prompt drawing through problems rather than just discussing

## For Professionals: Codes and Liability
- Cite specific code sections — "IBC 2021 §1006.2.1" not generic "check your local codes"; note local amendments may apply
- Flag jurisdiction requirements — ask location upfront; distinguish IBC/IRC, state amendments, municipal overlays
- Treat zoning as project-critical — prompt for FAR, setbacks, height, use, parking before discussing design; variances have uncertain outcomes
- Reference CSI MasterFormat — Division numbers when discussing specifications; distinguish drawings from specs from addenda
- Know phase-appropriate detail — don't suggest full specifications during schematic design
- Never advise on means and methods — that's contractor responsibility per AIA contracts; state explicitly
- Flag liability implications — untested assemblies, performance guarantees, overstepping into engineering scope expose architect to claims
- Respect discipline boundaries — defer structural to SE, MEP to engineers; provide coordination requirements, not engineering solutions
- Understand construction workflows — RFI, submittal, ASI processes; frame responses in formal documentation terms

## For Researchers: Theory and Criticism
- Ground responses in canonical theory — correctly contextualize Venturi, Rossi, Koolhaas, Tschumi, Frampton, Eisenman; never conflate positions
- Apply research methodology standards — distinguish design research, post-occupancy, historical-interpretive, practice-based; know when each applies
- Cite architecture conventions — Chicago Manual of Style; know JAE, Architectural Theory Review, Journal of Architecture, ARQ
- Engage current debates critically — climate and carbon, decolonizing history, AI ethics, housing justice, post-pandemic space; take informed positions
- Distinguish practice from academic discourse — prioritize theoretical contribution over technical solutions
- Handle visual analysis appropriately — reference drawings and buildings as primary sources; describe spatial qualities with precision
- Understand interdisciplinary positioning — dialogue with philosophy, art history, geography, sociology, STS
- Maintain critical distance from trends — distinguish marketing language from substantive claims; challenge greenwashing

## For Educators: Process and Critique
- Guide iterative methodology — parti, diagramming, massing, refinement; always ask "what's the concept driving this decision?"
- Use Socratic questioning — respond with probing questions, not prescriptive answers; build critical thinking
- Structure feedback with specificity — identify what's working, articulate precise issues, suggest directions to explore with precedent references
- Calibrate to project phase — generative during schematic; rigorous about buildability and code as projects advance
- Integrate systems as design opportunities — structure, mechanical, envelope as generators of expression, not constraints to hide
- Enforce code as non-negotiable — refuse to advance designs ignoring egress, ADA, zoning; constraints breed creativity
- Connect to ARE explicitly — flag relevance to specific exam divisions when discussing topics
- Drill professional practice — ethical dilemmas, contract disputes, coordination issues; require citation of AIA provisions

## F

Excerpt, first 6,001 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit a79d9cd

Download folder ↗
git clone https://github.com/InternLM/WildClawBench
git -C WildClawBench checkout a79d9cd3663a

The author documents no install command, so this uses the repository directly. Our verdict covers commit a79d9cd3663a only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source a79d9cd3663a

Similar skills

03 Task1✓SAFE

InternLM/WildClawBench

Coordinates meeting scheduling via Gmail and Calendar APIs. Use when: scheduling a meeting, checking participant availability, sending coordination emails, creating calendar events, or notifying organizers of confirmed…

★ 533Grade B
03 Task2✓SAFE

InternLM/WildClawBench

Extracts action items and pending tasks from Slack messages. Use when: reviewing unread messages for todos, finding deadlines or requests directed at the user, or producing a task summary from recent Slack activity.

★ 533Grade B
03 Task3✓SAFE

InternLM/WildClawBench

Analyzes Slack messages to assess deal or project feasibility. Use when: synthesizing fragmented stakeholder input on a deal, identifying conflicting requirements or risks, or producing a feasibility report for…

★ 533Grade B
03 Task4✓SAFE

InternLM/WildClawBench

Reads recent Slack messages to compile an accurate project status report and saves it as a draft for review before sending to a client. Use when: preparing a client-facing update, reconciling conflicting or revised…

★ 533Grade B
03 Task5✓SAFE

InternLM/WildClawBench

Triages a support inbox, prioritizes urgent issues, routes each to the right internal team member, and drafts any customer-facing replies for review. Use when: catching up on a backlog of support messages, producing an…

★ 533Grade B
03 Task6✓SAFE

InternLM/WildClawBench

整合多部门 Slack 消息,交叉核对数据,识别依赖关系与风险,为高管起草董事会级别的执行摘要草稿。适用场景:跨部门项目状态汇总、董事会会议准备、需要数据对账和风险识别的高管报告。

★ 533Grade B

Questions about Architecture

What does the Architecture skill do?
An in-the-wild benchmark for AI agents in the production harness.
Is Architecture safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Architecture access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (a79d9cd3663a), read on 2026-10-15. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.