Skip to content

Commit ee6f857

Browse files
feat(brand): framework-agnostic messaging, logo in README, remove scorer from GitHub Packages, remove em dashes from prose
- Replace arrow icon with logo SVG in README header - Retitle as "The Open Standard for Human-AI Collaboration: AI Fluency" - Remove direct 4D Framework coupling from platform-level descriptions - Remove scorer from GitHub Packages release step (fluently-scorer is on npm) - Replace all em dashes in user-visible prose across site HTML files - Make site copy framework-agnostic at platform level; keep 4D refs where content is specifically about 4D Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1 parent 7939190 commit ee6f857

7 files changed

Lines changed: 118 additions & 105 deletions

File tree

.github/workflows/release.yml

Lines changed: 3 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,9 @@ jobs:
5959

6060
# ── Publish to GitHub Packages ────────────────────────────────────────
6161
# GitHub Packages requires scoped names (@owner/package).
62-
# We temporarily rewrite package.json before publishing — CI is ephemeral.
62+
# We temporarily rewrite package.json before publishing. CI is ephemeral.
63+
# Note: fluently-scorer is published to npm only (already present as
64+
# fluently-scorer). CLI and MCP Server are mirrored here for discoverability.
6365

6466
- name: Setup Node.js for GitHub Packages
6567
uses: actions/setup-node@v4
@@ -68,20 +70,6 @@ jobs:
6870
registry-url: 'https://npm.pkg.github.com'
6971
scope: '@${{ github.repository_owner }}'
7072

71-
- name: Publish scorer to GitHub Packages
72-
working-directory: packages/scorer
73-
run: |
74-
node -e "
75-
const fs = require('fs');
76-
const pkg = JSON.parse(fs.readFileSync('package.json', 'utf8'));
77-
pkg.name = '@${{ github.repository_owner }}/scorer';
78-
pkg.publishConfig = { registry: 'https://npm.pkg.github.com', access: 'public' };
79-
fs.writeFileSync('package.json', JSON.stringify(pkg, null, 2));
80-
"
81-
npm publish
82-
env:
83-
NODE_AUTH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
84-
8573
- name: Publish CLI to GitHub Packages
8674
working-directory: packages/cli
8775
run: |

README.md

Lines changed: 73 additions & 48 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,8 @@
1-
# 🎯 Fluently — The Open Standard for Human-AI Collaboration Quality
1+
<p align="center">
2+
<img src="site/logo.svg" alt="Fluently" height="64">
3+
</p>
4+
5+
# Fluently: The Open Standard for Human-AI Collaboration
26

37
[![fluently-cli](https://img.shields.io/npm/v/fluently-cli?label=fluently-cli&style=flat-square&color=3B82F6)](https://www.npmjs.com/package/fluently-cli)
48
[![fluently-mcp-server](https://img.shields.io/npm/v/fluently-mcp-server?label=fluently-mcp-server&style=flat-square&color=6B6CB5)](https://www.npmjs.com/package/fluently-mcp-server)
@@ -10,11 +14,15 @@
1014

1115
---
1216

13-
## Why 4D Fluency?
17+
## What is Fluently?
18+
19+
AI is powerful but not magic. The gap between good and poor AI-assisted work is not the model — it is the collaboration. Fluently is an open platform that operationalizes **human-AI collaboration frameworks** as a shared knowledge commons, a scoring engine, a CLI, and an MCP server.
1420

15-
AI is powerful—but not magic. Teams shipping with AI today face a hard truth: **output quality depends entirely on clarity**. You need to know *what to delegate*, *how to describe it*, *how to verify it works*, and *who's accountable*. That's the **4D Framework**: Delegation, Description, Discernment, Diligence.
21+
Fluently ships with the **AI Fluency 4D Framework** by Dakan & Feller (Delegation, Description, Discernment, Diligence) as its bundled standard. Any framework with named dimensions can be registered alongside it, enabling teams to benchmark the same task across multiple frameworks and choose the one that fits their context.
1622

17-
**Fluently operationalizes the 4D Framework.** It gives you a CLI, MCP server, and a growing knowledge base of best practices—built on Anthropic's AI Fluency research by Dakan & Feller. Score your team's AI workflows. Learn from the community's Fluently 4D cycles. Ship with confidence.
23+
**Agent-agnostic.** Works with Claude, GPT, Gemini, Mistral, Copilot, and any MCP-compatible client.
24+
25+
**Framework-agnostic.** Start with 4D. Bring your own framework. Compare them side by side.
1826

1927
---
2028

@@ -26,31 +34,31 @@ AI is powerful—but not magic. Teams shipping with AI today face a hard truth:
2634
$ fluent compare --task "Automated code review with human sign-off"
2735

2836
┌─────────────────────────────────────────────────────────┐
29-
│ TOP 3 SIMILAR FLUENTLY 4D CYCLES FROM KNOWLEDGE BASE │
37+
│ TOP 3 MATCHING CYCLES FROM THE KNOWLEDGE BASE
3038
├─────────────────────────────────────────────────────────┤
3139
│ 1. Code Review: Review Depth vs. Speed Tradeoffs │
3240
│ Delegation: 75 Description: 82 Discernment: 78 │
3341
│ Diligence: 71 OVERALL: 76/100 │
34-
42+
│ │
3543
│ 2. Bug Fix Prioritization │
3644
│ Delegation: 68 Description: 74 Discernment: 71 │
3745
│ Diligence: 69 OVERALL: 71/100 │
38-
46+
│ │
3947
│ 3. Test Case Generation │
4048
│ Delegation: 72 Description: 76 Discernment: 70 │
4149
│ Diligence: 68 OVERALL: 72/100 │
4250
└─────────────────────────────────────────────────────────┘
4351
```
4452

45-
Each suggestion links to the full Fluently 4D cycledelegation guidelines, framing prompts, hallucination patterns to watch for, and approval workflows.
53+
Each result links to the full cycle: delegation guidelines, framing prompts, hallucination patterns to watch for, and approval workflows.
4654

4755
---
4856

4957
## Install in 30 Seconds
5058

5159
**Option 1 — Zero install (browser):** Use the [live scorer](https://fluently-org.github.io/fluently/) right now. No setup required.
5260

53-
**Option 2 — Zero install (terminal):** Run instantly with npx no PATH changes needed:
61+
**Option 2 — Zero install (terminal):** Run instantly with npx, no PATH changes needed:
5462
```bash
5563
npx fluently-cli score "Automated bug triage with human review"
5664
```
@@ -61,27 +69,35 @@ npm install -g fluently-cli
6169
fluent --help
6270
```
6371

64-
Requires Node.js 20+. The CLI is self-contained no configuration files needed.
72+
Requires Node.js 20+. The CLI is self-contained, no configuration files needed.
6573

6674
---
6775

6876
## What's Inside
6977

70-
**CLI** — Run `fluent` in your terminal to score 4D workflows, compare against community patterns, and contribute new Fluently 4D cycles.
78+
**CLI** — Run `fluent` in your terminal to score workflows, compare against community cycles, and contribute new patterns across any registered framework.
79+
80+
**MCP Server** — Embed collaboration scoring into any AI agent or MCP-compatible client (VS Code Copilot, Cursor, Continue, Claude Desktop, Claude Code, and more). Tools like `find_relevant_cycles()`, `get_dimension_guidance()`, `evaluate_compliance()`, and `compare_frameworks()` are available to your agent.
7181

72-
**MCP Server**Embed 4D scoring into any AI agent or MCP-compatible client (VS Code Copilot, Cursor, Continue, Claude Desktop, Claude Code, and more). Expose tools like `find_relevant_cycles()`, `get_dimension_guidance()`, and `contribute_cycle()` to your agent.
82+
**Knowledge Base**Community-contributed collaboration cycles organized by domain (coding, writing, research, education, legal, healthcare, general). Each cycle belongs to a framework, carries per-dimension guidance, and is validated before merge.
7383

74-
**Knowledge Base** — 50+ community-contributed Fluently 4D cycles organized by domain (coding, writing, research, management, product, etc.). Each cycle is scored on the 4D dimensions and peer-reviewed before merge.
84+
**Scorer** — The shared engine (`fluently-scorer` on npm) that validates schemas, computes similarity, scores collaboration quality, and evaluates framework compliance. Used internally by the CLI and MCP Server. Import it directly if you need programmatic access:
85+
```bash
86+
npm install fluently-scorer
87+
```
88+
```js
89+
import { scoreTask, evaluateCompliance } from 'fluently-scorer';
90+
```
7591

7692
---
7793

7894
## The Knowledge Base Matters
7995

80-
This isn't just a framework—it's a **commons for AI fluency**. Every Fluently 4D cycle you contribute teaches thousands of teams how to collaborate smarter with AI.
96+
This is not just a framework. It is a **commons for AI collaboration literacy**. Every cycle you contribute teaches teams how to collaborate smarter with AI, regardless of which model or tool they use.
8197

82-
Built on the **AI Fluency 4D Framework** by Dakan & Feller. Everything code, knowledge cycles, and tooling is released under the **MIT License**.
98+
Built on the **AI Fluency 4D Framework** by Dakan & Feller as the founding standard. Everything (code, cycles, and tooling) is released under the **MIT License**.
8399

84-
[Browse the Knowledge Base](https://fluently-org.github.io/fluently/)
100+
[Browse the Knowledge Base](https://fluently-org.github.io/fluently/)
85101

86102
---
87103

@@ -90,45 +106,55 @@ Built on the **AI Fluency 4D Framework** by Dakan & Feller. Everything — code,
90106
### For Teams Using AI
91107

92108
1. **Install the CLI** and run `fluent compare --task "your workflow"` to see how others solve similar problems.
93-
2. **Check the Fluently 4D cycles** — find your use case in the knowledge base above.
94-
3. **Score your process** — run `fluent score` with your delegation intent to identify gaps.
109+
2. **Check the cycles** in the knowledge base for your use case.
110+
3. **Score your process** with `fluent score` to identify gaps.
95111

96112
### For Teams Building AI Tools
97113

98114
1. **Integrate the MCP server** into your AI agent or IDE plugin (any MCP-compatible client).
99-
2. **Expose 4D scoring** to your users — let them verify AI output quality before shipping.
100-
3. **Use the scorer engine** directly `const { scoreTask } = require('@fluently/scorer')`.
115+
2. **Expose compliance scoring** to your users with `evaluate_compliance()` so they can verify collaboration quality before shipping.
116+
3. **Use the scorer engine** directly with `npm install fluently-scorer`.
101117

102118
### For Contributors
103119

104-
**Share your Fluently 4D cycles and help the community.** We're looking for patterns, anti-patterns, and real-world lessons from teams shipping AI features.
120+
**Share collaboration cycles and help the community.** We are looking for patterns, antipatterns, and real-world lessons from teams shipping AI features.
105121

106-
[**Contributing Guide**](CONTRIBUTING.md) — Detailed walkthrough for submitting a new Fluently 4D cycle.
122+
[Contributing Guide](CONTRIBUTING.md) — Detailed walkthrough for submitting a new cycle.
107123

108124
---
109125

110-
## How 4D Scoring Works
126+
## How Compliance Scoring Works
111127

112-
Every task, workflow, or prompt gets scored across four dimensions:
128+
Every collaboration session can be evaluated against a framework's named dimensions. The 4D Framework uses four:
113129

114130
| Dimension | Question | What We Measure |
115131
|-----------|----------|-----------------|
116-
| **Delegation** | *Who decides?* | Clarity on AI autonomy vs. human oversight. Escalation triggers matter. |
117-
| **Description** | *What context?* | Quality of framing + examples + constraints. Reduces ambiguity. |
118-
| **Discernment** | *Is it right?* | Your ability to spot hallucinations and overconfidence. Red flags & green signals. |
119-
| **Diligence** | *Who's accountable?* | Governance, review workflows, audit trails. Who approves before shipping. |
132+
| **Delegation** | Who decides? | Clarity on AI autonomy vs. human oversight. Escalation triggers matter. |
133+
| **Description** | What context? | Quality of framing, examples, and constraints. Reduces ambiguity. |
134+
| **Discernment** | Is it right? | Your ability to spot hallucinations and overconfidence. Red flags and green signals. |
135+
| **Diligence** | Who's accountable? | Governance, review workflows, audit trails. Who approves before shipping. |
136+
137+
Each dimension scores 0 to 100. The framework does not replace human judgment. It sharpens it.
120138

121-
Each scores 0–100. The framework doesn't replace human judgment—it sharpens it.
139+
Any framework registered in Fluently can define its own dimensions, evaluation criteria, best practices, and dimension combinations. The scorer and MCP server adapt automatically.
140+
141+
---
142+
143+
## Cross-Framework Benchmarking
144+
145+
Fluently's `compare_frameworks` MCP tool and `compare` CLI command let you run the same task through every registered framework simultaneously. This surfaces which framework's vocabulary and structure best fits your collaboration context, without having to commit to one upfront.
146+
147+
Agents can also call `evaluate_compliance(text, framework_id)` mid-session to check whether the current conversation adheres to the chosen framework, and receive actionable guidance on which dimensions need attention.
122148

123149
---
124150

125151
## Roadmap
126152

127-
**Embeddings-based similarity** — Replace keyword matching with semantic search so `find_similar_cycles()` surfaces truly relevant patterns regardless of terminology.
153+
**Embeddings-based similarity** — Replace keyword matching with semantic search so `find_relevant_cycles()` surfaces truly relevant patterns regardless of terminology.
128154

129-
**VS Code extension** — Inline 4D scoring in your editor. @fluently in comments to get suggestions while you write, review, or debug.
155+
**VS Code extension** — Inline scoring in your editor. Mention `@fluently` in comments to get suggestions while you write, review, or debug.
130156

131-
**Web playground** — Try 4D scoring live without installing. Experiment with Fluently 4D cycles. Generate your own.
157+
**Web playground** — Try scoring live without installing. Experiment with cycles. Generate your own.
132158

133159
---
134160

@@ -142,38 +168,39 @@ Knowledge → YAML + JSON + GitHub API
142168
Tests → Vitest
143169
```
144170

145-
**Language**: TypeScript **Runtime**: Node.js 20+ **Module**: ESM
171+
**Language:** TypeScript **Runtime:** Node.js 20+ **Module:** ESM
146172

147173
---
148174

149-
## Contribution is Free
175+
## Contribution is Open
150176

151-
- **Share a Fluently 4D cycle** — Takes 15 minutes. Write YAML. Open a PR. CI validates schema.
177+
- **Share a cycle** — Takes 15 minutes. Write YAML. Open a PR. CI validates schema.
152178
- **Improve the scorer** — Suggest semantic improvements, new dimensions, new domains.
153-
- **Build an integration** — MCP server is stable. Write a Slack app. A GitHub Action. A web service.
179+
- **Register a framework** — Add a YAML framework definition to `frameworks/`. CI validates it.
180+
- **Build an integration** — MCP server is stable. Write a Slack app, a GitHub Action, a web service.
154181

155-
**By contributing, you help us scale the standard.** Every Fluently 4D cycle in the knowledge base teaches thousands of teams.
182+
**By contributing, you help scale the standard.** Every cycle in the knowledge base teaches teams to collaborate better with AI.
156183

157184
---
158185

159186
## Quick Links
160187

161-
- 🌐 [Live Site & Knowledge Browser](https://fluently-org.github.io/fluently/)
162-
- 📖 [Full Documentation](packages/cli/README.md)
163-
- 💬 [GitHub Discussions](https://github.com/Fluently-Org/fluently/discussions)
164-
- 🐛 [Report Issues](https://github.com/Fluently-Org/fluently/issues)
165-
- 🤝 [Contributing Guide](CONTRIBUTING.md)
188+
- [Live Site and Knowledge Browser](https://fluently-org.github.io/fluently/)
189+
- [Full Documentation](packages/cli/README.md)
190+
- [GitHub Discussions](https://github.com/Fluently-Org/fluently/discussions)
191+
- [Report Issues](https://github.com/Fluently-Org/fluently/issues)
192+
- [Contributing Guide](CONTRIBUTING.md)
166193

167194
---
168195

169196
## Credits
170197

171-
**The AI Fluency 4D Framework** was developed by **Dakan & Feller** as a collaborative model for operationalizing AI fluency.
198+
**The AI Fluency 4D Framework** was developed by **Dakan & Feller** as a collaborative model for operationalizing AI fluency in teams.
172199

173-
**Fluently** brings that framework to life as an open-source tool + knowledge commons.
200+
**Fluently** brings that framework and others to life as an open-source tool and knowledge commons.
174201

175202
- Framework: Dakan & Feller — AI Fluency 4D Framework
176-
- License: MIT (code + knowledge)
203+
- License: MIT (code and knowledge)
177204

178205
---
179206

@@ -185,6 +212,4 @@ Mix and match. Share freely. Build better AI collaboration.
185212

186213
---
187214

188-
Happy shipping. 🚀
189-
190-
215+
Happy shipping.

site/contribute.html

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ <h1 class="text-4xl font-bold text-gray-900 mb-4">
3838
<i class="fas fa-code-branch mr-2 text-blue-600"></i>Contribute to Fluently
3939
</h1>
4040
<p class="text-xl text-gray-600">
41-
Share your Fluently 4D cycles with the community
41+
Share collaboration cycles with the community
4242
</p>
4343
</div>
4444
</section>
@@ -608,7 +608,7 @@ <h2 class="text-2xl font-bold text-gray-900 mb-6">
608608
<div class="bg-gray-800 px-4 py-3">
609609
<span class="text-gray-300 font-mono text-sm">Pull Request Description</span>
610610
</div>
611-
<pre class="text-gray-200 p-6 overflow-x-auto text-sm font-mono"><code>## What's the Fluently 4D Cycle About?
611+
<pre class="text-gray-200 p-6 overflow-x-auto text-sm font-mono"><code>## What's the Fluently Cycle About?
612612

613613
Brief explanation of your cycle and why it matters.
614614

@@ -651,7 +651,7 @@ <h2 class="text-2xl font-bold text-gray-900 mb-4">Questions?</h2>
651651
<div class="grid md:grid-cols-4 gap-8 mb-8">
652652
<div>
653653
<h4 class="text-white font-bold mb-4">Fluently</h4>
654-
<p class="text-sm">Operationalizing the AI Fluency 4D Framework</p>
654+
<p class="text-sm">Open Standard for Human-AI Collaboration</p>
655655
</div>
656656
<div>
657657
<h4 class="text-white font-bold mb-4">Links</h4>

site/frameworks.html

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -128,7 +128,7 @@ <h1 class="text-3xl sm:text-4xl lg:text-5xl font-bold text-gray-900 mb-4 leading
128128
Every framework,<br class="hidden sm:block"> one knowledge base
129129
</h1>
130130
<p class="text-lg text-gray-600 max-w-2xl mx-auto mb-8">
131-
Fluently supports any collaboration framework not just 4D.
131+
Fluently supports any collaboration framework, not just 4D.
132132
Each framework defines its own dimensions and validation rules.
133133
Knowledge cycles are validated against their specific framework's schema.
134134
</p>
@@ -174,7 +174,7 @@ <h2 class="text-2xl font-bold text-gray-900 mb-2">
174174
<i class="fas fa-columns text-indigo-600 mr-2"></i>Compare Frameworks
175175
</h2>
176176
<p class="text-gray-600 text-sm sm:text-base">
177-
Describe your task and see what each framework's best cycle looks like side by side.
177+
Describe your task and see what each framework's best cycle looks like, side by side.
178178
</p>
179179
</div>
180180

0 commit comments

Comments
 (0)