| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 27 | 2 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 10 | 0 | 0% |
What each file covers
Sections
0 shared · 27 only in A · 2 only in B- − Generated Project Configuration
- − 🚨 MANDATORY: Load CodeOps Rules Before Any Work
- − Project Overview
- − Toolchain
- − Commands
- − Terminal Delay
- − Build
- − Test
- − Run all tests
- − Verify (before commit)
- − Full verification — run this before any git commit
- − Schema Pipeline (offline, build-time)
- − Scrape props/slots/stories from FluentUI source
- − Enhance with AI descriptions, best practices, a11y, guides/patterns
- − Whole pipeline (scrape → enhance → build → test)
- − Project Structure
- − Type: Single repository
- − Directory Layout
- − Coding Conventions
- − Naming
- − Git & Commit Conventions
- − Commit Scope
- − Use module/feature as scope:
- − feat(module): description
- − Branch Strategy
- − Special Rules (Project-Specific)
- − Cross-References
- + IMPORTANT: WHEN EXECUTING A PLAN:
- + IMPORTANT:
Commands
neither file has anySection tags
0 shared · 10 only in A · 0 only in B- − build
- − test
- − code-style
- − architecture
- − types
- − git-pr
- − database
- − ui
- − deployment
- − do-not
Line diff
blendsdk/fluentui-mcp · .clinerules/project.md
@@ −1 @@
1# Generated Project Configuration
2
3> **🔄 Updated by `analyze_project`** (incremental update)
4> **Scanned:** 2026-06-03
5
6> **Auto-generated by `analyze_project`**
7> **Project:** fluentui-mcp
8> **Type:** library
9
10Save this content to `.clinerules/project.md` in your project root,
11then review and adjust the values as needed.
12
13---
14
15## 🚨 MANDATORY: Load CodeOps Rules Before Any Work
16
17**Before ANY planning or implementation, the AI agent MUST load these rules
18using the codeops-mcp tools:**
19
201. `get_rule("agents")` — Load agent behavior rules **(REQUIRED FIRST)**
212. `get_rule("code")` — Load coding standards
223. `get_rule("testing")` — Load testing workflows
234. `get_rule("git-commands")` — Load git commit protocols
24
25These rules are **mandatory** and must be consulted before every task.
26**Do NOT skip this step. Do NOT proceed without reading these documents.**
27
28---
29
30## Project Overview
31
32- **Name:** fluentui-mcp
33- **Description:** MCP server providing FluentUI v9 documentation, component references, patterns, and implementation guides as tools and resources for AI agents. Backed by a schema-driven pipeline (scraper → LLM enhancer → bundled enhanced JSON schema) served from an in-memory store.
34- **Type:** library
35
36## Toolchain
37
38- **Language(s):** TypeScript
39- **Framework(s):** MCP SDK
40- **Package Manager:** yarn
41- **Test Framework:** Vitest
42
43**Manifest files found:** package.json, tsconfig.json
44
45## Commands
46
47All commands assume execution from the project root. Prefix all shell commands with `clear && sleep [delay] &&` (see Terminal Delay below).
48
49### Terminal Delay
50
51- **Delay (seconds):** 3
52- The `clear` ensures a clean terminal; the `sleep` gives VS Code time to initialize the terminal before the command runs.
53- Adjust the delay for your environment: `1` for fast machines, `3` (default) for normal, `5` for slower environments.
54- All command examples below use `sleep 3` — replace `3` with your configured delay.
55
56### Build
57
58```bash
59clear && sleep 3 && yarn build
60```
61
62### Test
63
64```bash
65# Run all tests
66clear && sleep 3 && yarn test
67```
68
69### Verify (before commit)
70
71```bash
72# Full verification — run this before any git commit
73clear && sleep 3 && yarn build && yarn test
74```
75
76### Schema Pipeline (offline, build-time)
77
78```bash
79# Scrape props/slots/stories from FluentUI source
80clear && sleep 3 && yarn scrape --version v9 --clone --verbose
81
82# Enhance with AI descriptions, best practices, a11y, guides/patterns
83clear && sleep 3 && yarn enhance --version v9 --full --verbose
84
85# Whole pipeline (scrape → enhance → build → test)
86clear && sleep 3 && yarn pipeline:full
87```
88
89## Project Structure
90
91### Type: Single repository
92
93### Directory Layout
94
95```
96LICENSE/
97data/
98docs/
99maintenance/
100node_modules/
101plans/
102scripts/
103src/
104```
105
106## Coding Conventions
107
108### Naming
109
110- **Files:** kebab-case
111- **Components/Classes:** PascalCase
112- **Functions/Methods:** camelCase
113- **Constants:** UPPER_SNAKE_CASE
114
115## Git & Commit Conventions
116
117### Commit Scope
118
119```
120# Use module/feature as scope:
121# feat(module): description
122```
123
124### Branch Strategy
125
126- **Main branch:** `main`
127- **Feature branches:** `feature/[name]`
128
129## Special Rules (Project-Specific)
130
131```
132- The bundled enhanced schema lives in data/v9/fluentui-schema-enhanced.json and is the
133 single source of truth served at runtime. It is generated offline by the scraper + enhancer.
134- Schema pipeline tooling lives in scripts/: scripts/scraper/ (ts-morph extraction) and
135 scripts/enhancer/ (LLM enrichment + guide/pattern generation). Run via tsx, not built.
136- MCP tools are defined in src/tools/ as individual files per tool (12 tools).
137- Runtime schema subsystem: src/schema/ (loader, store, validator), src/search/ (TF-IDF
138 search engine + index), src/formatters/ (render schema entries → markdown).
139- All enhanced-schema enrichment fields are OPTIONAL/additive — formatters render a section
140 only when its field is present, preserving back-compat with un-enhanced schemas.
141- LLM provider note: newer OpenAI models (gpt-5.x / o-series) require max_completion_tokens
142 and reject custom temperature; the OpenAI provider branches on model family accordingly.
143```
144
145## Cross-References
146
147The generic rule files that read this `project.md`:
148
149- **make_plan.md** — Uses verify command, file paths, commit scope, task file path patterns
150- **code.md** — Uses language conventions, architecture rules
151- **testing.md** — Uses test commands, test locations, test framework
152- **git-commands.md** — Uses commit scope, verify command
153- **agents.md** — Uses shell commands, verify command
154- **requirements.md** — Uses project type, tech stack, and conventions for requirements discovery
155- **retro_requirements.md** — Uses project type, tech stack for codebase analysis adaptation
156- **techdocs.md** — Uses project type, tech stack for documentation generation
157- **upgrade_plan.md** — Uses project context for upgrade compatibility checks
158- **grill_me.md** — Uses project context for deep disambiguation before planning or requirements
159- **preflight.md** — Uses project type, tech stack, and conventions for grounded quality audits
160
blendsdk/fluentui-mcp · .clinerules/plan_execution.md
@@ +1 @@
1# IMPORTANT: WHEN EXECUTING A PLAN:
2
3When executing a plan, start or proceed with the next logical phase of the plan and if there is still room in the context window proceed or start to the next logical phase after that, then check and repeat if there is still room in the context window, otherwise wrap up so we can perform `/compact` the context and proceed further.
4
5# IMPORTANT:
6
7If possible do auto `/compact` after implementing each phase
8
@@ −1 +1 @@
1−# Generated Project Configuration
1+# IMPORTANT: WHEN EXECUTING A PLAN:
22
3−> **🔄 Updated by `analyze_project`** (incremental update)
4−> **Scanned:** 2026-06-03
3+When executing a plan, start or proceed with the next logical phase of the plan and if there is still room in the context window proceed or start to the next logical phase after that, then check and repeat if there is still room in the context window, otherwise wrap up so we can perform `/compact` the context and proceed further.
54
6−> **Auto-generated by `analyze_project`**
7−> **Project:** fluentui-mcp
8−> **Type:** library
5+# IMPORTANT:
96
10−Save this content to `.clinerules/project.md` in your project root,
11−then review and adjust the values as needed.
12−
13−---
14−
15−## 🚨 MANDATORY: Load CodeOps Rules Before Any Work
16−
17−**Before ANY planning or implementation, the AI agent MUST load these rules
18−using the codeops-mcp tools:**
19−
20−1. `get_rule("agents")` — Load agent behavior rules **(REQUIRED FIRST)**
21−2. `get_rule("code")` — Load coding standards
22−3. `get_rule("testing")` — Load testing workflows
23−4. `get_rule("git-commands")` — Load git commit protocols
24−
25−These rules are **mandatory** and must be consulted before every task.
26−**Do NOT skip this step. Do NOT proceed without reading these documents.**
27−
28−---
29−
30−## Project Overview
31−
32−- **Name:** fluentui-mcp
33−- **Description:** MCP server providing FluentUI v9 documentation, component references, patterns, and implementation guides as tools and resources for AI agents. Backed by a schema-driven pipeline (scraper → LLM enhancer → bundled enhanced JSON schema) served from an in-memory store.
34−- **Type:** library
35−
36−## Toolchain
37−
38−- **Language(s):** TypeScript
39−- **Framework(s):** MCP SDK
40−- **Package Manager:** yarn
41−- **Test Framework:** Vitest
42−
43−**Manifest files found:** package.json, tsconfig.json
44−
45−## Commands
46−
47−All commands assume execution from the project root. Prefix all shell commands with `clear && sleep [delay] &&` (see Terminal Delay below).
48−
49−### Terminal Delay
50−
51−- **Delay (seconds):** 3
52−- The `clear` ensures a clean terminal; the `sleep` gives VS Code time to initialize the terminal before the command runs.
53−- Adjust the delay for your environment: `1` for fast machines, `3` (default) for normal, `5` for slower environments.
54−- All command examples below use `sleep 3` — replace `3` with your configured delay.
55−
56−### Build
57−
58−```bash
59−clear && sleep 3 && yarn build
60−```
61−
62−### Test
63−
64−```bash
65−# Run all tests
66−clear && sleep 3 && yarn test
67−```
68−
69−### Verify (before commit)
70−
71−```bash
72−# Full verification — run this before any git commit
73−clear && sleep 3 && yarn build && yarn test
74−```
75−
76−### Schema Pipeline (offline, build-time)
77−
78−```bash
79−# Scrape props/slots/stories from FluentUI source
80−clear && sleep 3 && yarn scrape --version v9 --clone --verbose
81−
82−# Enhance with AI descriptions, best practices, a11y, guides/patterns
83−clear && sleep 3 && yarn enhance --version v9 --full --verbose
84−
85−# Whole pipeline (scrape → enhance → build → test)
86−clear && sleep 3 && yarn pipeline:full
87−```
88−
89−## Project Structure
90−
91−### Type: Single repository
92−
93−### Directory Layout
94−
95−```
96−LICENSE/
97−data/
98−docs/
99−maintenance/
100−node_modules/
101−plans/
102−scripts/
103−src/
104−```
105−
106−## Coding Conventions
107−
108−### Naming
109−
110−- **Files:** kebab-case
111−- **Components/Classes:** PascalCase
112−- **Functions/Methods:** camelCase
113−- **Constants:** UPPER_SNAKE_CASE
114−
115−## Git & Commit Conventions
116−
117−### Commit Scope
118−
119−```
120−# Use module/feature as scope:
121−# feat(module): description
122−```
123−
124−### Branch Strategy
125−
126−- **Main branch:** `main`
127−- **Feature branches:** `feature/[name]`
128−
129−## Special Rules (Project-Specific)
130−
131−```
132−- The bundled enhanced schema lives in data/v9/fluentui-schema-enhanced.json and is the
133− single source of truth served at runtime. It is generated offline by the scraper + enhancer.
134−- Schema pipeline tooling lives in scripts/: scripts/scraper/ (ts-morph extraction) and
135− scripts/enhancer/ (LLM enrichment + guide/pattern generation). Run via tsx, not built.
136−- MCP tools are defined in src/tools/ as individual files per tool (12 tools).
137−- Runtime schema subsystem: src/schema/ (loader, store, validator), src/search/ (TF-IDF
138− search engine + index), src/formatters/ (render schema entries → markdown).
139−- All enhanced-schema enrichment fields are OPTIONAL/additive — formatters render a section
140− only when its field is present, preserving back-compat with un-enhanced schemas.
141−- LLM provider note: newer OpenAI models (gpt-5.x / o-series) require max_completion_tokens
142− and reject custom temperature; the OpenAI provider branches on model family accordingly.
143−```
144−
145−## Cross-References
146−
147−The generic rule files that read this `project.md`:
148−
149−- **make_plan.md** — Uses verify command, file paths, commit scope, task file path patterns
150−- **code.md** — Uses language conventions, architecture rules
151−- **testing.md** — Uses test commands, test locations, test framework
152−- **git-commands.md** — Uses commit scope, verify command
153−- **agents.md** — Uses shell commands, verify command
154−- **requirements.md** — Uses project type, tech stack, and conventions for requirements discovery
155−- **retro_requirements.md** — Uses project type, tech stack for codebase analysis adaptation
156−- **techdocs.md** — Uses project type, tech stack for documentation generation
157−- **upgrade_plan.md** — Uses project context for upgrade compatibility checks
158−- **grill_me.md** — Uses project context for deep disambiguation before planning or requirements
159−- **preflight.md** — Uses project type, tech stack, and conventions for grounded quality audits
7+If possible do auto `/compact` after implementing each phase
1608
