docs: reframe toolkit for reviewer team, add Matrix link

Reframe "Advanced: Claude Code Plugin (Optional)" as "Complete Toolkit"
to present skills as complementary tools rather than experimental extras.

Add CI badge, Matrix room link, and explicit contribution types beyond
writing rules (validate existing rules, propose severity changes, report
missing patterns).

Update CONTRIBUTING.md: note auto-discovery of assertion files, add
single-fixture testing tip, move validate-fixture.sh mention earlier
in the workflow.

Commit commands/ directory (Claude Code slash command definitions).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: ZviBaratz

CONTRIBUTING.md

@@ -66,6 +66,8 @@ export default class TestExtension extends Extension {
 SPDX-License-Identifier: GPL-2.0-or-later
 ```
 
+**Verify your fixture** before continuing — run `bash scripts/validate-fixture.sh` to catch common mistakes (missing `@`, UUID mismatch, missing URL/LICENSE).
+
 ### Step 3: Add a test assertion
 
 Create a new file `tests/assertions/your-category.sh` (or add to an existing one):
@@ -79,25 +81,7 @@ assert_output_contains "fails on navigator.clipboard" "\[FAIL\].*R-WEB-12"
 echo ""
 ```
 
-If you created a new assertion file, source it in `tests/run-tests.sh` by adding before the summary section:
-
-```bash
-if [[ -f "$ASSERTIONS_DIR/your-category.sh" ]]; then
-    source "$ASSERTIONS_DIR/your-category.sh"
-fi
-```
-
-### Before running tests: Verify your fixture
-
-Common fixture mistakes that cause confusing failures:
-
-- Directory name contains `@` (e.g., `my-rule@test`)
-- `uuid` in metadata.json matches directory name exactly
-- metadata.json includes a `"url"` field
-- LICENSE file exists with SPDX identifier
-- UUID/name does not contain "gnome" (trademark check will fail)
-
-Or run `bash scripts/validate-fixture.sh` to check all of the above automatically.
+New files in `tests/assertions/` are automatically discovered — no need to edit `run-tests.sh`.
 
 ### Step 4: Run tests
 
@@ -107,6 +91,12 @@ bash tests/run-tests.sh
 
 All existing tests must still pass alongside your new assertion.
 
+To test just your fixture in isolation (without running the full suite):
+
+```bash
+./ego-lint tests/fixtures/your-rule@test --verbose
+```
+
 ### Debugging tips
 
 - **Pattern doesn't match?** Test your rule in isolation: `bash scripts/validate-rule.sh R-XXXX-NN tests/fixtures/your-fixture@test`

README.md

@@ -1,3 +1,5 @@
+![Tests](https://github.com/ZviBaratz/gnome-extension-reviewer/actions/workflows/test.yml/badge.svg)
+
 # gnome-extension-reviewer
 
 Automated pre-submission checks for GNOME Shell extensions, built from analysis of real EGO review decisions. ego-lint catches the mechanical issues that cause the most common rejections — so extensions arrive cleaner and reviewers spend less time on round-trips.
@@ -171,6 +173,18 @@ Full research: [docs/research/](docs/research/) | Coverage gaps: [docs/research/
 
 The rules belong to whoever shapes them. Reviewers who contribute checks, adjust severity, or report false positives define what ego-lint enforces and how. If you see a rejection pattern that ego-lint misses, [adding it](CONTRIBUTING.md) is a 4-line YAML change. See [GOVERNANCE.md](GOVERNANCE.md) for how rule decisions are made.
 
+### Discussion
+
+Join the conversation in [#extensions:gnome.org](https://matrix.to/#/#extensions:gnome.org) on Matrix.
+
+### Ways to Contribute
+
+Beyond writing new rules:
+
+- **Validate existing rules** — run ego-lint on extensions from your queue and report where it gets things right or wrong
+- **Propose severity changes** — if a WARN should be a FAIL (or vice versa), open an issue with your reasoning
+- **Report missing patterns** — rejection reasons ego-lint doesn't catch yet
+
 ### Help Wanted
 
 Self-contained improvements where reviewer expertise would be especially valuable:
@@ -189,9 +203,9 @@ Self-contained improvements where reviewer expertise would be especially valuabl
 
 Full gap list: [docs/research/gap-analysis.md](docs/research/gap-analysis.md)
 
-## Advanced: Claude Code Plugin (Optional)
+## Complete Toolkit
 
-ego-lint is the primary offering — it works standalone without Claude Code or any AI. The skills below are experimental extras for developers who use [Claude Code](https://docs.anthropic.com/en/docs/claude-code).
+ego-lint is the standalone core — deterministic, no dependencies, works in CI. The Claude Code skills extend it with AI-powered analysis for developers who want deeper review coverage:
 
 | Skill | Description |
 |-------|-------------|

commands/ego-lint.md

@@ -0,0 +1,22 @@
+---
+description: Run automated EGO compliance checks on a GNOME Shell extension
+allowed-tools: Bash(bash *ego-lint.sh*), Read, Glob, Grep
+---
+
+Run the ego-lint automated compliance checker on the target extension.
+
+## Target
+
+Extension directory: $ARGUMENTS (if empty, use the current working directory).
+
+## Instructions
+
+1. Locate `ego-lint.sh` in this plugin's `skills/ego-lint/scripts/` directory and run it:
+
+```bash
+bash <plugin-path>/skills/ego-lint/scripts/ego-lint.sh <extension-directory>
+```
+
+2. Present the results grouped by severity (FAIL first, then WARN, then SKIP, then PASS).
+3. If any FAILs exist, summarize the blocking issues and suggest fixes using the table in `skills/ego-lint/SKILL.md` under "Common Fixes".
+4. For `--verbose` output, add the flag to the command.

commands/ego-review.md

@@ -0,0 +1,15 @@
+---
+description: Perform a manual EGO code review of a GNOME Shell extension
+---
+
+Perform a manual code review simulating what an EGO (extensions.gnome.org) reviewer checks.
+
+## Target
+
+Extension directory: $ARGUMENTS (if empty, use the current working directory).
+
+## Instructions
+
+Read and follow the full review process defined in this plugin's `skills/ego-review/SKILL.md`. It defines a multi-phase review (Phase 0 through Phase 5a) with checklists in `skills/ego-review/references/`.
+
+Start with Phase 0 (run ego-lint for automated baseline), then proceed through each phase sequentially.

commands/ego-scaffold.md

@@ -0,0 +1,11 @@
+---
+description: Create a new GNOME Shell extension with EGO-compliant structure
+---
+
+Scaffold a new GNOME Shell extension project with correct structure and EGO-compliant metadata.
+
+## Instructions
+
+Read and follow the scaffolding process defined in this plugin's `skills/ego-scaffold/SKILL.md`. It gathers required information (name, UUID, GNOME versions, etc.), then generates files from templates in `skills/ego-scaffold/assets/`.
+
+$ARGUMENTS

commands/ego-simulate.md

@@ -0,0 +1,14 @@
+---
+description: Simulate an EGO review submission with pass/fail verdict
+allowed-tools: Bash(bash *ego-lint.sh*), Read, Glob, Grep
+---
+
+Simulate how an EGO reviewer would evaluate this extension submission.
+
+## Target
+
+Extension directory: $ARGUMENTS (if empty, use the current working directory).
+
+## Instructions
+
+Read and follow the simulation process in this plugin's `skills/ego-simulate/SKILL.md`. It runs ego-lint first, then applies a 23-reason rejection taxonomy with weighted scoring from `skills/ego-simulate/references/rejection-taxonomy.md`, and produces a structured readiness report.

commands/ego-submit.md

@@ -0,0 +1,14 @@
+---
+description: Complete pre-submission validation for extensions.gnome.org
+allowed-tools: Bash(bash *ego-lint.sh*), Read, Glob, Grep
+---
+
+Run the full pre-submission validation pipeline for extensions.gnome.org.
+
+## Target
+
+Extension directory: $ARGUMENTS (if empty, use the current working directory).
+
+## Instructions
+
+Read and follow the submission pipeline in this plugin's `skills/ego-submit/SKILL.md`. It orchestrates: ego-lint (automated checks) → ego-review (manual code review) → packaging validation, producing a final submission readiness report.