Agent skill · Audited from source
Culture Architect
skill · borghei/Claude-SkillsNOASSERTION licenceAudited 19 Oct 2026 · source 6e3fcbdbb5cf
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6e3fcbdbb5cf and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Build, measure, and evolve company culture as operational behavior, not wall posters. Use when building company values, assessing culture health, designing rituals, creating culture codes, or handling culture clashes.
Cite
Cite this page
ModelsAtlas. “Culture Architect (borghei/Claude-Skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/borghei/culture-architect
2 skills are called “Culture Architect”. You are viewing borghei/Claude-Skills.
- borghei/Claude-Skills★ 949!CAUTION
- alirezarezvani/claude-skills★ 28k!CAUTION
Trust audit
Audit 0.4.1 · source read 19 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 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
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 5 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (5)
MEDIUMInventory / provenanceinv.symlink · .codex/skills/a11y-audit
.codex/skills/a11y-audit
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/ab-test-setup
.codex/skills/ab-test-setup
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/account-executive
.codex/skills/account-executive
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/ad-creative
.codex/skills/ad-creative
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/aeo
.codex/skills/aeo
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherborghei GitHub userOwner of the repository this skill is read from
- Source folderborghei/Claude-Skills/c-level-advisor/culture-architectThe exact folder we audited
- LicenceNOASSERTIONAs the repository states it
- Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
- Repository statusNot archivedLast push 12 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Build, measure, and evolve company culture as operational behavior, not wall posters. Use when building company values, assessing culture health, designing rituals, creating culture codes, or handling culture clashes.
---
name: culture-architect
description: >
Build, measure, and evolve company culture as operational behavior, not wall
posters. Use when building company values, assessing culture health, designing
rituals, creating culture codes, or handling culture clashes.
license: MIT + Commons Clause
metadata:
version: 2.0.0
author: borghei
category: c-level
domain: culture-leadership
updated: 2026-03-09
frameworks:
- culture-playbook
- culture-code-template
- values-to-behaviors
- culture-health-assessment
- ritual-design
- culture-debt-framework
triggers:
- culture
- company culture
- values
- mission
- vision
- culture code
- cultural rituals
- culture health
- values-to-behaviors
- founder culture
- culture debt
- value-washing
- culture assessment
- culture survey
- psychological safety
- culture scaling
- engagement
- eNPS
- remote culture
- hybrid culture
- culture clash
- M&A culture
- employer brand
---
# Culture Architect
Culture is what you DO, not what you SAY. This skill builds culture as an operational system -- observable behaviors, measurable health, and rituals that scale from 5 people to 500.
## Keywords
culture, company culture, values, mission, vision, culture code, cultural rituals, culture health, values-to-behaviors, founder culture, culture debt, value-washing, culture assessment, culture survey, psychological safety, culture scaling, engagement, eNPS, remote culture, hybrid culture, culture clash, employer brand, onboarding culture, performance culture, recognition
---
## Core Principle
**Culture = (What you reward) + (What you tolerate) + (What you celebrate)**
If your values say "transparency" but you punish bearers of bad news, your real value is "optics." Culture is not aspirational. It is descriptive. The work is closing the gap between stated and actual.
---
## Clarify First
Before generating, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- [ ] **Which deliverable is needed** (values + behaviors, culture code, health survey, ritual calendar, culture-debt audit, or M&A integration) — each has its own template
- [ ] **Company stage and headcount** — rituals and transmission mechanisms that work at 15 people break at 150; the ritual matrix is stage-keyed
- [ ] **What is actually rewarded, tolerated, and celebrated today** — culture is descriptive, not aspirational; without the honest current state you produce wall-poster platitudes
- [ ] **Work model** (in-person, remote, hybrid) — determines which operating principles and meeting rules apply
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
---
## Culture Diagnostic Decision Tree
```
START: "How is our culture?"
|
v
[Run the Values Audit]
Ask: "What did the last person who got promoted demonstrate?"
|
+-- Answer matches stated values --> Values are real. Check transmission.
| |
| v
| [Can a 30-day employee describe the culture accurately?]
| +-- YES --> Culture is operational. Maintain and evolve.
| +-- NO --> Transmission gap. Fix onboarding and rituals.
|
+-- Answer differs from stated values --> Values are performative.
|
v
[Do leaders model the real (non-stated) values?]
+-- YES --> Rewrite values to match reality, then iterate.
+-- NO --> Deeper problem: no coherent culture exists. Build from scratch.
```
---
## Framework 1: Mission / Vision / Values Workshop
### Mission (Why We Exist)
| Element | Test | Example |
|---------|------|---------|
| Present-tense | Is it about what we do now, not what we aspire to? | "We reduce preventable falls in elderly care" |
| Specific | Could a competitor claim the exact same thing? If yes, too generic. | Not "We make the world better" |
| Meaningful | Would something be lost if we disappeared? | Answer must be concrete |
### Vision (What Winning Looks Like)
| Quality | Bad | Good |
|---------|-----|------|
| Specificity | "Be the market leader" | "Every care home in Europe uses our system by 2030" |
| Falsifiability | "Transform healthcare" | "Reduce fall-related injuries by 50% in partner facilities" |
| Timeline | No date | 5-10 year horizon with milestones |
### Values (What We Actually Do)
| Rule | Explanation |
|------|-------------|
| 3-5 values maximum | More than 5 and none are memorable |
| Derived from observation | "What did our best hire do that nobody asked?" |
| Each has behavioral anchors | Specific enough to judge against |
| Include the tension | Good values have a cost ("Speed" means "we accept some risk") |
---
## Framework 2: Values-to-Behaviors Translation
This is the work that makes values operational. Every value needs concrete behavioral anchors.
| Value | Vague Version | Behavioral Anchor | How You'd Observe It |
|-------|---------------|-------------------|---------------------|
| Transparency | "We're open and honest" | "We share bad news within 24 hours, including to our manager" | Bad news travels fast, no surprises |
| Ownership | "We take responsibility" | "We don't hand off problems -- we own until resolved, even across team boundaries" | No orphaned issues |
| Speed | "We move fast" | "Decisions under $5K happen at team level, same day" | Low decision latency |
| Quality | "We don't cut corners" | "We stop the line before shipping something we're not proud of" | Teams delay launches for quality |
| Customer-first | "Customers are our priority" | "Any team member can escalate a customer issue to leadership, bypassing normal channels" | Escalation is celebrated, not punished |
### Translation Workshop (90 minutes)
```
For each value:
Step 1: State the value in 2-3 words
Step 2: Ask "How would a new hire know we live this on day 30?"
Step 3: Write 3 observable behaviors that Excerpt, first 6,000 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 6e3fcbd
git clone https://github.com/borghei/Claude-Skills git -C Claude-Skills checkout 6e3fcbdbb5cf
The author documents no install command, so this uses the repository directly. Our verdict covers commit 6e3fcbdbb5cf 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
- !CAUTION B 89 / 100
first audit · source
6e3fcbdbb5cf
Similar skills
All coding & review skills →borghei/Claude-Skills
This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".
borghei/Claude-Skills
Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent…
borghei/Claude-Skills
Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.
borghei/Claude-Skills
Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant…
borghei/Claude-Skills
Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to…
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, or optimizing warehouse…
Questions about Culture Architect
What does the Culture Architect skill do?
Is Culture Architect safe to install?
What can Culture Architect access on my machine?
How current is this page?
Sources
- github.com/borghei/Claude-Skills/tree/main/c-level-advisor/cultu — the audited source at commit 6e3fcbdbb5cf and every finding aboveObserved · 19 Oct 2026
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.
- What does the Culture Architect skill do?
- Is Culture Architect safe to install?
- What can Culture Architect access on my machine?