docs: replace deprecated --ai flag with --integration in all documentation (#2359)

* docs: replace deprecated --ai flag with --integration in all documentation

Replace all user-facing --ai, --ai-skills, and --ai-commands-dir references
with their modern equivalents:

- --ai <agent> → --integration <agent>
- --ai-skills → --integration-options="--skills"
- --ai-commands-dir <dir> → --integration generic --integration-options="--commands-dir <dir>"

Updated files:
- README.md (~17 occurrences)
- docs/installation.md (~8 occurrences)
- docs/upgrade.md (~11 occurrences)
- docs/local-development.md (~5 occurrences)
- CONTRIBUTING.md (1 occurrence)
- extensions/EXTENSION-USER-GUIDE.md (1 occurrence)
- src/specify_cli/__init__.py (docstring examples and error messages)

Left unchanged:
- CHANGELOG.md (historical record)
- Test files (intentionally exercise deprecated flag path)
- CLI flag implementation (backward compatibility)

Closes #2358

* docs: address review feedback on pre-existing issues

- Fix duplicate copilot example in README.md (replace with codex)
- Fix invalid gemini --integration-options="--skills" example (gemini
  does not support --skills)
- Update generic integration comment from 'Unsupported agent' to
  'Bring your own agent; requires --commands-dir'
- Clarify EXTENSION-USER-GUIDE.md: skills auto-register for
  skills-based integrations, not only with --integration-options

* docs: replace bare 'AI agent' / 'AI assistant' with 'coding agent' throughout

Full sweep across all documentation and user-facing CLI messages to
align terminology. Bare references like 'AI agent', 'AI assistant',
and 'AI Agent' are replaced with 'coding agent' or 'coding agent
integration' as appropriate.

Intentionally left unchanged:
- 'AI coding agent' (already correct expanded form)
- Deprecated --ai flag help text and error messages (describes the
  deprecated flag itself)
- Community extension descriptions (external project text)
- 'generated by an AI' in CONTRIBUTING.md (general AI, not agent)

* docs: address review — remove deprecated --offline, qualify --skills scope

- Remove --offline from docstring examples (deprecated no-op)
- Remove --offline from CONTRIBUTING.md testing example
- Replace --offline instructions in docs/installation.md with note that
  bundled assets are used by default
- Qualify --integration-options="--skills" in README.md to note it only
  applies to integrations that support skills mode

docs/installation.md

@@ -39,16 +39,16 @@ uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init .
 uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init --here
 ```
 
-### Specify AI Agent
+### Specify Integration
 
-You can proactively specify your AI agent during initialization:
+You can proactively specify your coding agent integration during initialization:
 
 ```bash
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai claude
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai gemini
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai copilot
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai codebuddy
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai pi
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration claude
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration gemini
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration copilot
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration codebuddy
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration pi
 ```
 
 ### Specify Script Type (Shell vs PowerShell)
@@ -73,7 +73,7 @@ uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <proje
 If you prefer to get the templates without checking for the right tools:
 
 ```bash
-uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --ai claude --ignore-agent-tools
+uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <project_name> --integration claude --ignore-agent-tools
 ```
 
 ## Verification
@@ -86,7 +86,7 @@ specify version
 
 This helps verify you are running the official Spec Kit build from GitHub, not an unrelated package with the same name.
 
-After initialization, you should see the following commands available in your AI agent:
+After initialization, you should see the following commands available in your coding agent:
 
 - `/speckit.specify` - Create specifications
 - `/speckit.plan` - Generate implementation plans  
@@ -131,12 +131,10 @@ pip install --no-index --find-links=./dist specify-cli
 
 ```bash
 # Initialize a project — no GitHub access needed
-specify init my-project --ai claude --offline
+specify init my-project --integration claude
 ```
 
-The `--offline` flag tells the CLI to use the templates, commands, and scripts bundled inside the wheel instead of downloading from GitHub.
-
-> **Deprecation notice:** Starting with v0.6.0, `specify init` will use bundled assets by default and the `--offline` flag will be removed. The GitHub download path will be retired because bundled assets eliminate the need for network access, avoid proxy/firewall issues, and guarantee that templates always match the installed CLI version. No action will be needed — `specify init` will simply work without network access out of the box.
+Bundled assets are used by default — no network access is required.
 
 > **Note:** Python 3.11+ is required.