gossipcat 0.4.20 → 0.4.21
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist-dashboard/assets/index-Ci46EANB.css +1 -0
- package/dist-dashboard/assets/index-aXAMEMbl.js +70 -0
- package/dist-dashboard/index.html +2 -2
- package/dist-mcp/default-skills/code-review.md +6 -5
- package/dist-mcp/mcp-server.js +40061 -41797
- package/package.json +1 -1
- package/dist-dashboard/assets/index-DmoFYGg1.css +0 -1
- package/dist-dashboard/assets/index-oIF838yl.js +0 -68
|
@@ -22,8 +22,8 @@
|
|
|
22
22
|
<link rel="icon" type="image/png" href="/dashboard/favicon.png" />
|
|
23
23
|
<link rel="preconnect" href="https://fonts.googleapis.com" />
|
|
24
24
|
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
|
|
25
|
-
<script type="module" crossorigin src="/dashboard/assets/index-
|
|
26
|
-
<link rel="stylesheet" crossorigin href="/dashboard/assets/index-
|
|
25
|
+
<script type="module" crossorigin src="/dashboard/assets/index-aXAMEMbl.js"></script>
|
|
26
|
+
<link rel="stylesheet" crossorigin href="/dashboard/assets/index-Ci46EANB.css">
|
|
27
27
|
</head>
|
|
28
28
|
<body>
|
|
29
29
|
<div id="root"></div>
|
|
@@ -10,20 +10,21 @@
|
|
|
10
10
|
- Prioritize findings so the author knows what must change vs. what is optional
|
|
11
11
|
|
|
12
12
|
## Approach
|
|
13
|
-
1. Read the full diff before
|
|
13
|
+
1. Read the full diff before emitting any finding
|
|
14
14
|
2. Check correctness first: does it do what it claims?
|
|
15
15
|
3. Check edge cases: null, empty, concurrent, large input
|
|
16
16
|
4. Check error handling: are errors surfaced or silently swallowed?
|
|
17
17
|
5. Check test coverage: are the new paths tested?
|
|
18
18
|
6. Check naming and structure: will this make sense in 6 months?
|
|
19
|
-
7.
|
|
19
|
+
7. Order findings critical → low within your response — every finding still ships as one `<agent_finding>` tag, never as a Markdown heading, `**F1 —**` numbering, or top-of-output summary prose
|
|
20
20
|
|
|
21
21
|
## Output Format
|
|
22
|
-
Use the FINDING TAG SCHEMA from the system prompt. Do NOT invent skill-specific output formats; they break parsing and cross-review.
|
|
22
|
+
Use the FINDING TAG SCHEMA from the system prompt. Do NOT invent skill-specific output formats; they break parsing and cross-review. The natural shape of a "code review" is prose with bullets and a summary — resist that shape; the parser only sees `<agent_finding>` tags.
|
|
23
23
|
|
|
24
24
|
## Don't
|
|
25
25
|
- Don't nitpick style issues that a linter should catch
|
|
26
|
-
- Don't
|
|
26
|
+
- Don't write vague findings like "this could be better" — say how
|
|
27
27
|
- Don't approve PRs with unresolved critical findings
|
|
28
|
-
- Don't
|
|
28
|
+
- Don't emit a finding for every line — group related issues into one tag
|
|
29
29
|
- Don't skip reading the tests
|
|
30
|
+
- Don't open or close your response with summary prose; the orchestrator synthesises across agents
|