Menu
Bierut lens — Does the design think? Form follows content, not style. Problem-solving over decoration. Read-only diagnostic.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Context-aware story extraction. Loads the maker's full context — identity, expertise, voice, published work — then reads the narrative architecture to understand the story being told and what's missing. Interviews the maker to fill gaps with real moments. Modular: works with any project.
Evaluate the IP constellation — dispatches baseline checks, then 9 lenses in parallel (Millman, Bierut, Appleton, Shaw, Peers, Victore, The Walk, The Walls). Coordinator skill.
Cross-page coherence. Do the three tiers form a coherent argument when read as a sequence? Read-only diagnostic.
Baseline checks — mechanical health of the constellation. Links, images, cross-refs, attribution, voice violations, SEO, tooltips. Read-only diagnostic.
Where lenses agree and disagree. Maps consensus vs. contradiction across audit results. Read-only diagnostic.
Copy verification checklist — 13-item pass/fail check on draft or published copy. Voice rules, grounding, Shaw check, steward voice. Read-only diagnostic.
| name | bierut |
| description | Bierut lens — Does the design think? Form follows content, not style. Problem-solving over decoration. Read-only diagnostic. |
| user_invocable | true |
Michael Bierut's standard: "I don't like doing design for designers — I like problem-solving." This lens evaluates whether the site's design serves the content and audience, or performs for a design-literate crowd.
Read-only diagnostic. Reports a verdict, never auto-fixes.
/bierut # Evaluate full constellation
/bierut [page-path] # Evaluate a single page
_governance/, _infrastructure/, _output/, _blog/bio/index.md, contact.md, colophon.md, thinking.md, vocabulary.md_data/index.json + _layouts/systemworks.html.audit/screenshots/ (latest set)docs/visual-reference-index.md → active reference set.audit/rubric.md if it exists — Peter's annotations override defaults/knowledge → search ideation history for grounding → source-attributed results/baseline → mechanical health facts (link status, image status) → pass/fail per checkThe evaluation questions below ARE this lens's criteria.
Read: site structure, CSS approach (can assess structure, cannot assess visual quality) Evaluate: Does the site's organization make the work accessible to the intended audience? Or does it signal sophistication to a design-literate audience at the expense of clarity? Flag: Structure or terminology that requires design-world literacy to parse.
Read: every project page's opening and frontmatter (context, drift fields) Evaluate: Are constraint, context, and difficulty visible — or just polished deliverables? Does the reader understand what was hard before seeing what was built? Flag: Pages that jump to the solution. Missing context/drift.
Read: all project pages Evaluate: Evidence that Peter engaged deeply with each project's actual domain (jewelry, recruiting, music, narrative, household systems) rather than applying a visual style to interchangeable subjects. Flag: Projects that feel like design applied TO a subject rather than design emerging FROM understanding the subject.
Read: manifesto, bio, project pages Evaluate: Is the narrative accessible to someone outside design/engineering? Could a founder, a hiring manager, a potential client follow the story? Flag: Jargon, insider terminology, unexplained concepts. Note: verify vocabulary tooltips produce visible output — check baseline results. A tooltip mechanism with no visible matches is not sufficient.
Read: all page content as pure text Evaluate: Would the ideas survive without the CSS? Is there an editorial point of view, a structural argument, a way of seeing — or is this content that only works because it looks good? Flag: Pages that are thin on ideas. Content that describes rather than argues.
Print in conversation. No file changes. Format:
# Bierut Lens — "Does the design think?"
## Overall: [STRONG / HOLDS / WEAK / BROKEN]
**B1. Design serving content?** — [verdict]
[Evidence.]
**B2. Problem visible?** — [verdict]
[Evidence.]
**B3. Curiosity beyond design?** — [verdict]
[Evidence.]
**B4. Non-designer accessibility?** — [verdict]
[Evidence.]
**B5. Point of view without visuals?** — [verdict]
[Evidence.]
For each non-passing question, state:
/audit run — runs in parallel with other lenses/full-pass run — via audit