diffity 0.1.0 → 0.1.1

package/packages/parser/tests/parse.test.ts

@@ -1,312 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { readFileSync } from 'node:fs';
-import { resolve, dirname } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { parseDiff } from '../src/parse.js';
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const fixture = (name: string) =>
-  readFileSync(resolve(__dirname, './fixtures', name), 'utf-8');
-
-describe('parseDiff', () => {
-  describe('basic formats', () => {
-    it('parses single file with additions only', () => {
-      const result = parseDiff(fixture('single-file-additions.diff'));
-
-      expect(result.files).toHaveLength(1);
-      expect(result.files[0].oldPath).toBe('hello.ts');
-      expect(result.files[0].newPath).toBe('hello.ts');
-      expect(result.files[0].status).toBe('modified');
-      expect(result.files[0].hunks).toHaveLength(1);
-
-      const hunk = result.files[0].hunks[0];
-      expect(hunk.oldStart).toBe(1);
-      expect(hunk.oldCount).toBe(3);
-      expect(hunk.newStart).toBe(1);
-      expect(hunk.newCount).toBe(6);
-
-      const addLines = hunk.lines.filter(l => l.type === 'add');
-      expect(addLines).toHaveLength(3);
-      expect(addLines[0].content).toBe("const name = 'world';");
-      expect(addLines[0].newLineNumber).toBe(2);
-      expect(addLines[0].oldLineNumber).toBeNull();
-
-      const contextLines = hunk.lines.filter(l => l.type === 'context');
-      expect(contextLines).toHaveLength(3);
-      expect(contextLines[0].oldLineNumber).toBe(1);
-      expect(contextLines[0].newLineNumber).toBe(1);
-
-      expect(result.files[0].additions).toBe(3);
-      expect(result.files[0].deletions).toBe(0);
-    });
-
-    it('parses single file with deletions', () => {
-      const result = parseDiff(fixture('single-file-deletions.diff'));
-
-      expect(result.files).toHaveLength(1);
-      const hunk = result.files[0].hunks[0];
-      const delLines = hunk.lines.filter(l => l.type === 'delete');
-      expect(delLines).toHaveLength(3);
-      expect(delLines[0].content).toBe("  console.log('adding', a, b);");
-      expect(delLines[0].oldLineNumber).toBe(2);
-      expect(delLines[0].newLineNumber).toBeNull();
-
-      expect(result.files[0].additions).toBe(1);
-      expect(result.files[0].deletions).toBe(3);
-    });
-
-    it('parses single file with mixed changes', () => {
-      const result = parseDiff(fixture('single-file-mixed.diff'));
-
-      expect(result.files).toHaveLength(1);
-      const hunk = result.files[0].hunks[0];
-
-      expect(hunk.lines.filter(l => l.type === 'add')).toHaveLength(3);
-      expect(hunk.lines.filter(l => l.type === 'delete')).toHaveLength(2);
-      expect(hunk.lines.filter(l => l.type === 'context')).toHaveLength(5);
-
-      expect(result.files[0].additions).toBe(3);
-      expect(result.files[0].deletions).toBe(2);
-    });
-
-    it('parses single file with multiple hunks', () => {
-      const result = parseDiff(fixture('single-file-multi-hunk.diff'));
-
-      expect(result.files).toHaveLength(1);
-      expect(result.files[0].hunks).toHaveLength(2);
-
-      expect(result.files[0].hunks[0].oldStart).toBe(1);
-      expect(result.files[0].hunks[0].newStart).toBe(1);
-      expect(result.files[0].hunks[1].oldStart).toBe(20);
-      expect(result.files[0].hunks[1].newStart).toBe(20);
-    });
-
-    it('parses multiple files', () => {
-      const result = parseDiff(fixture('multi-file.diff'));
-
-      expect(result.files).toHaveLength(2);
-      expect(result.files[0].newPath).toBe('index.ts');
-      expect(result.files[1].newPath).toBe('runner.ts');
-
-      expect(result.stats.filesChanged).toBe(2);
-      expect(result.stats.totalAdditions).toBe(
-        result.files[0].additions + result.files[1].additions
-      );
-      expect(result.stats.totalDeletions).toBe(
-        result.files[0].deletions + result.files[1].deletions
-      );
-    });
-
-    it('parses empty diff', () => {
-      const result = parseDiff(fixture('empty.diff'));
-
-      expect(result.files).toHaveLength(0);
-      expect(result.stats.filesChanged).toBe(0);
-      expect(result.stats.totalAdditions).toBe(0);
-      expect(result.stats.totalDeletions).toBe(0);
-    });
-  });
-
-  describe('hunk header parsing', () => {
-    it('parses standard hunk header', () => {
-      const result = parseDiff(fixture('single-file-additions.diff'));
-      const hunk = result.files[0].hunks[0];
-
-      expect(hunk.oldStart).toBe(1);
-      expect(hunk.oldCount).toBe(3);
-      expect(hunk.newStart).toBe(1);
-      expect(hunk.newCount).toBe(6);
-    });
-
-    it('parses hunk header with function context', () => {
-      const result = parseDiff(fixture('hunk-with-context.diff'));
-      const hunk = result.files[0].hunks[0];
-
-      expect(hunk.oldStart).toBe(10);
-      expect(hunk.oldCount).toBe(5);
-      expect(hunk.newStart).toBe(10);
-      expect(hunk.newCount).toBe(7);
-      expect(hunk.context).toBe('function processData() {');
-    });
-
-    it('parses new file hunk header with 0,0', () => {
-      const result = parseDiff(fixture('new-file.diff'));
-      const hunk = result.files[0].hunks[0];
-
-      expect(hunk.oldStart).toBe(0);
-      expect(hunk.oldCount).toBe(0);
-      expect(hunk.newStart).toBe(1);
-      expect(hunk.newCount).toBe(3);
-    });
-  });
-
-  describe('line number assignment', () => {
-    it('assigns correct line numbers to context lines', () => {
-      const result = parseDiff(fixture('single-file-additions.diff'));
-      const contextLines = result.files[0].hunks[0].lines.filter(
-        l => l.type === 'context'
-      );
-
-      expect(contextLines[0].oldLineNumber).toBe(1);
-      expect(contextLines[0].newLineNumber).toBe(1);
-    });
-
-    it('assigns correct line numbers to addition lines', () => {
-      const result = parseDiff(fixture('single-file-additions.diff'));
-      const addLines = result.files[0].hunks[0].lines.filter(
-        l => l.type === 'add'
-      );
-
-      expect(addLines[0].oldLineNumber).toBeNull();
-      expect(addLines[0].newLineNumber).toBe(2);
-      expect(addLines[1].newLineNumber).toBe(3);
-      expect(addLines[2].newLineNumber).toBe(4);
-    });
-
-    it('assigns correct line numbers to deletion lines', () => {
-      const result = parseDiff(fixture('single-file-deletions.diff'));
-      const delLines = result.files[0].hunks[0].lines.filter(
-        l => l.type === 'delete'
-      );
-
-      expect(delLines[0].newLineNumber).toBeNull();
-      expect(delLines[0].oldLineNumber).toBe(2);
-      expect(delLines[1].oldLineNumber).toBe(3);
-      expect(delLines[2].oldLineNumber).toBe(4);
-    });
-  });
-
-  describe('file status detection', () => {
-    it('detects new files', () => {
-      const result = parseDiff(fixture('new-file.diff'));
-
-      expect(result.files[0].status).toBe('added');
-      expect(result.files[0].oldPath).toBe('/dev/null');
-      expect(result.files[0].newPath).toBe('newfile.ts');
-    });
-
-    it('detects deleted files', () => {
-      const result = parseDiff(fixture('deleted-file.diff'));
-
-      expect(result.files[0].status).toBe('deleted');
-      expect(result.files[0].oldPath).toBe('old-file.ts');
-      expect(result.files[0].newPath).toBe('/dev/null');
-    });
-
-    it('detects renamed files', () => {
-      const result = parseDiff(fixture('renamed-file.diff'));
-
-      expect(result.files[0].status).toBe('renamed');
-      expect(result.files[0].oldPath).toBe('old-name.ts');
-      expect(result.files[0].newPath).toBe('new-name.ts');
-      expect(result.files[0].similarityIndex).toBe(85);
-    });
-
-    it('detects copied files', () => {
-      const result = parseDiff(fixture('copied-file.diff'));
-
-      expect(result.files[0].status).toBe('copied');
-      expect(result.files[0].oldPath).toBe('original.ts');
-      expect(result.files[0].newPath).toBe('copy.ts');
-      expect(result.files[0].similarityIndex).toBe(90);
-    });
-
-    it('detects mode-only changes', () => {
-      const result = parseDiff(fixture('mode-change.diff'));
-
-      expect(result.files[0].status).toBe('modified');
-      expect(result.files[0].oldMode).toBe('100644');
-      expect(result.files[0].newMode).toBe('100755');
-      expect(result.files[0].hunks).toHaveLength(0);
-    });
-
-    it('detects mode change with content', () => {
-      const result = parseDiff(fixture('mode-change-with-content.diff'));
-
-      expect(result.files[0].oldMode).toBe('100644');
-      expect(result.files[0].newMode).toBe('100755');
-      expect(result.files[0].hunks).toHaveLength(1);
-      expect(result.files[0].additions).toBe(1);
-    });
-  });
-
-  describe('edge cases', () => {
-    it('handles no newline at end of file', () => {
-      const result = parseDiff(fixture('no-newline.diff'));
-      const lines = result.files[0].hunks[0].lines;
-      const lastContext = lines.filter(l => l.type === 'context').pop();
-
-      expect(lastContext?.noNewline).toBe(true);
-    });
-
-    it('handles binary files (new)', () => {
-      const result = parseDiff(fixture('binary-file.diff'));
-
-      expect(result.files[0].isBinary).toBe(true);
-      expect(result.files[0].status).toBe('added');
-      expect(result.files[0].hunks).toHaveLength(0);
-      expect(result.files[0].additions).toBe(0);
-      expect(result.files[0].deletions).toBe(0);
-    });
-
-    it('handles binary files (modified)', () => {
-      const result = parseDiff(fixture('binary-modified.diff'));
-
-      expect(result.files[0].isBinary).toBe(true);
-      expect(result.files[0].status).toBe('modified');
-    });
-
-    it('handles binary files (deleted)', () => {
-      const result = parseDiff(fixture('binary-deleted.diff'));
-
-      expect(result.files[0].isBinary).toBe(true);
-      expect(result.files[0].status).toBe('deleted');
-    });
-
-    it('handles files with spaces in path', () => {
-      const result = parseDiff(fixture('spaces-in-path.diff'));
-
-      expect(result.files[0].oldPath).toBe('my folder/my file.ts');
-      expect(result.files[0].newPath).toBe('my folder/my file.ts');
-    });
-
-    it('handles unicode content', () => {
-      const result = parseDiff(fixture('unicode-content.diff'));
-
-      expect(result.files).toHaveLength(1);
-      const addLine = result.files[0].hunks[0].lines.find(l => l.type === 'add' && l.content.includes('emoji'));
-      expect(addLine).toBeDefined();
-    });
-
-    it('handles submodule changes', () => {
-      const result = parseDiff(fixture('submodule.diff'));
-
-      expect(result.files).toHaveLength(1);
-      expect(result.files[0].newPath).toBe('vendor/lib');
-    });
-  });
-
-  describe('stats computation', () => {
-    it('computes per-file stats', () => {
-      const result = parseDiff(fixture('single-file-mixed.diff'));
-
-      expect(result.files[0].additions).toBe(3);
-      expect(result.files[0].deletions).toBe(2);
-    });
-
-    it('computes total stats across files', () => {
-      const result = parseDiff(fixture('multi-file.diff'));
-
-      expect(result.stats.filesChanged).toBe(2);
-      expect(result.stats.totalAdditions).toBeGreaterThan(0);
-      expect(result.stats.totalDeletions).toBeGreaterThan(0);
-    });
-
-    it('binary files report 0 additions/deletions', () => {
-      const result = parseDiff(fixture('binary-file.diff'));
-
-      expect(result.files[0].additions).toBe(0);
-      expect(result.files[0].deletions).toBe(0);
-    });
-  });
-});

package/packages/parser/tests/word-diff-integration.test.ts

@@ -1,52 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { readFileSync } from 'node:fs';
-import { resolve, dirname } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { parseDiff } from '../src/index.js';
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const fixture = (name: string) =>
-  readFileSync(resolve(__dirname, './fixtures', name), 'utf-8');
-
-describe('word diff integration', () => {
-  it('attaches word diff to paired delete+add lines', () => {
-    const result = parseDiff(fixture('single-file-deletions.diff'));
-    const hunk = result.files[0].hunks[0];
-
-    const delLines = hunk.lines.filter(l => l.type === 'delete');
-    const addLines = hunk.lines.filter(l => l.type === 'add');
-
-    expect(delLines[0].wordDiff).toBeDefined();
-    expect(addLines[0].wordDiff).toBeDefined();
-  });
-
-  it('does not attach word diff to pure additions', () => {
-    const result = parseDiff(fixture('single-file-additions.diff'));
-    const hunk = result.files[0].hunks[0];
-    const addLines = hunk.lines.filter(l => l.type === 'add');
-
-    for (const line of addLines) {
-      expect(line.wordDiff).toBeUndefined();
-    }
-  });
-
-  it('pairs consecutive delete+add sequences for word diff', () => {
-    const result = parseDiff(fixture('single-file-mixed.diff'));
-    const hunk = result.files[0].hunks[0];
-
-    const lines = hunk.lines;
-    const portDel = lines.find(
-      l => l.type === 'delete' && l.content.includes('3000')
-    );
-    const portAdd = lines.find(
-      l => l.type === 'add' && l.content.includes('8080')
-    );
-
-    expect(portDel?.wordDiff).toBeDefined();
-    expect(portAdd?.wordDiff).toBeDefined();
-
-    const portDelSegments = portDel!.wordDiff!;
-    const hasDelete = portDelSegments.some(s => s.type === 'delete');
-    expect(hasDelete).toBe(true);
-  });
-});

package/packages/parser/tests/word-diff.test.ts

@@ -1,121 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { computeWordDiff } from '../src/word-diff.js';
-
-describe('computeWordDiff', () => {
-  it('returns equal segment for identical lines', () => {
-    const result = computeWordDiff('hello world', 'hello world');
-
-    expect(result).toEqual([{ text: 'hello world', type: 'equal' }]);
-  });
-
-  it('detects single word change', () => {
-    const result = computeWordDiff('const x = 5;', 'const x = 10;');
-
-    expect(result).toEqual([
-      { text: 'const x = ', type: 'equal' },
-      { text: '5', type: 'delete' },
-      { text: '10', type: 'insert' },
-      { text: ';', type: 'equal' },
-    ]);
-  });
-
-  it('detects word added at end', () => {
-    const result = computeWordDiff('hello', 'hello world');
-
-    expect(result).toEqual([
-      { text: 'hello', type: 'equal' },
-      { text: ' world', type: 'insert' },
-    ]);
-  });
-
-  it('detects word deleted from beginning', () => {
-    const result = computeWordDiff('const x = 1;', 'x = 1;');
-
-    expect(result).toEqual([
-      { text: 'const ', type: 'delete' },
-      { text: 'x = 1;', type: 'equal' },
-    ]);
-  });
-
-  it('detects multiple word changes', () => {
-    const result = computeWordDiff(
-      'import { foo } from "bar";',
-      'import { baz } from "qux";'
-    );
-
-    expect(result).toEqual([
-      { text: 'import { ', type: 'equal' },
-      { text: 'foo', type: 'delete' },
-      { text: 'baz', type: 'insert' },
-      { text: ' } from "', type: 'equal' },
-      { text: 'bar', type: 'delete' },
-      { text: 'qux', type: 'insert' },
-      { text: '";', type: 'equal' },
-    ]);
-  });
-
-  it('handles entirely different lines', () => {
-    const result = computeWordDiff('abc', 'xyz');
-
-    expect(result).toEqual([
-      { text: 'abc', type: 'delete' },
-      { text: 'xyz', type: 'insert' },
-    ]);
-  });
-
-  it('handles empty old line', () => {
-    const result = computeWordDiff('', 'hello');
-
-    expect(result).toEqual([{ text: 'hello', type: 'insert' }]);
-  });
-
-  it('handles empty new line', () => {
-    const result = computeWordDiff('hello', '');
-
-    expect(result).toEqual([{ text: 'hello', type: 'delete' }]);
-  });
-
-  it('handles indentation change', () => {
-    const result = computeWordDiff('  return x;', '    return x;');
-
-    expect(result).toEqual([
-      { text: '  ', type: 'delete' },
-      { text: '    ', type: 'insert' },
-      { text: 'return x;', type: 'equal' },
-    ]);
-  });
-
-  it('handles case change', () => {
-    const result = computeWordDiff('Foo', 'foo');
-
-    expect(result).toEqual([
-      { text: 'Foo', type: 'delete' },
-      { text: 'foo', type: 'insert' },
-    ]);
-  });
-
-  it('handles string content change', () => {
-    const result = computeWordDiff(
-      'const msg = "hello";',
-      'const msg = "world";'
-    );
-
-    expect(result).toEqual([
-      { text: 'const msg = "', type: 'equal' },
-      { text: 'hello', type: 'delete' },
-      { text: 'world', type: 'insert' },
-      { text: '";', type: 'equal' },
-    ]);
-  });
-
-  it('handles whitespace-only change between words', () => {
-    const result = computeWordDiff('a  b', 'a b');
-
-    expect(result).toEqual([
-      { text: 'a', type: 'equal' },
-      { text: '  ', type: 'delete' },
-      { text: ' ', type: 'insert' },
-      { text: 'b', type: 'equal' },
-    ]);
-  });
-});

package/packages/parser/tsconfig.json

@@ -1,10 +0,0 @@
-{
-  "extends": "../../tsconfig.json",
-  "compilerOptions": {
-    "outDir": "./dist",
-    "rootDir": "./src",
-    "composite": true
-  },
-  "include": ["src/**/*.ts"],
-  "exclude": ["src/__tests__", "src/__fixtures__"]
-}

package/packages/skills/diffity-resolve/SKILL.md

@@ -1,55 +0,0 @@
----
-name: diffity-resolve
-description: Read open review comments and resolve them by making code fixes
-user-invocable: true
----
-
-# Diffity Resolve Skill
-
-You are reading open review comments and resolving them by making the requested code changes.
-
-## Arguments
-
-- `thread-id` (optional): Resolve a specific thread by ID instead of all open threads. Example: `/diffity-resolve abc123`
-
-## CLI Reference
-
-```
-{{binary}} agent list [--status open|resolved|dismissed] [--json]
-{{binary}} agent comment --file <path> --line <n> [--end-line <n>] [--side new|old] --body "<text>"
-{{binary}} agent general-comment --body "<text>"
-{{binary}} agent resolve <id> [--summary "<text>"]
-{{binary}} agent dismiss <id> [--reason "<text>"]
-{{binary}} agent reply <id> --body "<text>"
-```
-
-- `--file`, `--line`, `--body` are required for `comment`
-- `--end-line` defaults to `--line` (single-line comment)
-- `--side` defaults to `new`
-- `general-comment` creates a diff-level comment not tied to any file or line
-- `<id>` accepts full UUID or 8-char prefix
-
-## Prerequisites
-
-1. Check that `{{binary}}` is available: run `which {{binary}}`. If not found, {{install_hint}}.
-2. Check that a review session exists: run `cat .diffity/current-session`. If the file doesn't exist or is stale, tell the user to start diffity first.
-
-## Instructions
-
-1. List open comment threads with full details:
-   ```
-   {{binary}} agent list --status open --json
-   ```
-   If a `thread-id` argument was provided, filter to just that thread. The JSON output includes the full comment body, file path, line numbers, and side for each thread.
-2. If there are no open threads, tell the user there's nothing to resolve.
-3. For each open thread:
-   a. **Skip** general comments (filePath `__general__`) — these are summaries, not actionable code changes.
-   b. **Skip** threads tagged `[question]` or `[nit]` — these don't require code changes. Tell the user you skipped them and why.
-   c. Read the comment body from the JSON output and understand what change is requested.
-   d. Read the relevant source file to understand the full context around the commented lines, then make the requested code change using the Edit tool.
-   e. After making the change, resolve the thread with a summary:
-      ```
-      {{binary}} agent resolve <thread-id> --summary "Fixed: <brief description of what was changed>"
-      ```
-4. After resolving all applicable threads, run `{{binary}} agent list` to confirm status.
-5. Tell the user to check the browser — resolved status will appear within 2 seconds via polling.

package/packages/skills/diffity-review/SKILL.md

@@ -1,74 +0,0 @@
----
-name: diffity-review
-description: Review current diff and leave comments using diffity agent commands
-user-invocable: true
----
-
-# Diffity Review Skill
-
-You are reviewing a diff and leaving inline comments using the `{{binary}} agent` CLI.
-
-## Arguments
-
-- `focus` (optional): Focus the review on a specific area. One of: `security`, `performance`, `naming`, `errors`, `types`, `logic`. If omitted, review everything.
-
-## CLI Reference
-
-```
-{{binary}} agent list [--status open|resolved|dismissed] [--json]
-{{binary}} agent comment --file <path> --line <n> [--end-line <n>] [--side new|old] --body "<text>"
-{{binary}} agent general-comment --body "<text>"
-{{binary}} agent resolve <id> [--summary "<text>"]
-{{binary}} agent dismiss <id> [--reason "<text>"]
-{{binary}} agent reply <id> --body "<text>"
-```
-
-- `--file`, `--line`, `--body` are required for `comment`
-- `--end-line` defaults to `--line` (single-line comment)
-- `--side` defaults to `new`
-- `general-comment` creates a diff-level comment not tied to any file or line
-- `<id>` accepts full UUID or 8-char prefix
-
-## Prerequisites
-
-1. Check that `{{binary}}` is available: run `which {{binary}}`. If not found, {{install_hint}}.
-2. Check that a review session exists: run `cat .diffity/current-session`. If the file doesn't exist or is stale, tell the user to start diffity first (e.g. `{{binary}}`).
-
-## Instructions
-
-1. Read the current diff using `git diff`. Check `.diffity/current-session` to determine which ref is active.
-2. For each changed file, read the **entire file** (not just the diff hunks) to understand the full context. This prevents false positives from missing surrounding code.
-3. Analyze the code changes thoroughly. If a `focus` argument was provided, concentrate on that area. Otherwise look for:
-   - Bugs, logic errors, off-by-one errors
-   - Security issues (injection, XSS, auth bypass)
-   - Performance problems
-   - Missing error handling at system boundaries
-   - Race conditions
-   - API contract violations
-   - Unclear or misleading naming
-4. **Only comment on code that was changed in the diff.** Do not flag pre-existing issues in unchanged code — this is a review of the diff, not an audit of the entire file. The only exception is if a change in the diff introduces a bug in combination with existing code.
-5. **Prioritize signal over volume.** A clean diff should get a clean review. Do not manufacture findings to appear thorough. If a diff with 5 changed lines only has 1 real issue, leave 1 comment.
-6. **Do not repeat the same issue across files.** If the same pattern appears in multiple places, leave one inline comment on the first occurrence and mention it in the general summary instead of commenting on every instance.
-7. Categorize each finding with a severity prefix in the comment body:
-   - `[must-fix]` — Bugs, security issues, data loss risks. These must be addressed.
-   - `[suggestion]` — Improvements that would meaningfully improve the code.
-   - `[nit]` — Style or preference. Fine to ignore.
-   - `[question]` — Something unclear that needs clarification from the author.
-8. For each finding, leave a comment using:
-   ```
-   {{binary}} agent comment --file <path> --line <n> [--end-line <n>] [--side new] --body "<comment>"
-   ```
-   - Use `--side new` (default) for comments on added/modified code
-   - Use `--side old` for comments on removed code
-   - Use `--end-line` when the issue spans multiple lines
-   - Be specific and actionable in your comments
-9. After leaving all inline comments, write a general comment that summarizes your overall assessment of the diff. This should cover:
-   - Overall quality verdict (e.g. "Looks good with minor issues" or "Needs significant changes before merging")
-   - Cross-cutting concerns that don't belong on any single line (architecture, naming consistency across files, missing tests, etc.)
-   - A count of findings by severity (e.g. "2 must-fix, 3 suggestions, 1 nit")
-   ```
-   {{binary}} agent general-comment --body "<overall review summary>"
-   ```
-   If there are no inline findings, still leave a general comment with your assessment (e.g. "Clean diff — no issues found").
-10. Run `{{binary}} agent list` to confirm all comments were created.
-11. Tell the user to check the browser — comments will appear within 2 seconds via polling.

package/packages/skills/diffity-start/SKILL.md

@@ -1,25 +0,0 @@
----
-name: diffity-start
-description: Start the diffity diff viewer server for the current working tree or staged changes
-user-invocable: true
----
-
-# Diffity Start Skill
-
-You are starting the diffity diff viewer so the user can see their changes in the browser.
-
-## Instructions
-
-1. Check that `{{binary}}` is available: run `which {{binary}}`. If not found, {{install_hint}}.
-2. Start the server using the Bash tool with `run_in_background: true`:
-   - Command: `{{binary}}`
-   - Do NOT use `&` or `--quiet` — let the Bash tool handle backgrounding
-   - The browser will open automatically and the session is auto-created on startup
-4. Wait 2 seconds, then verify the session exists by checking that `.diffity/current-session` file is present.
-5. Tell the user diffity is running and show them what they can do next. Keep it short — don't show session IDs, hashes, or other internals. Example:
-
-   > Diffity is running — check your browser.
-   >
-   > Here's what you can do:
-   > - **{{slash}}review** — get a code review on your changes
-   > - **{{slash}}resolve** — fix issues from review comments