@weavetab/skills 2.5.0-beta.5 → 2.5.1
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/README.md +108 -108
- package/ROUTER.md +43 -43
- package/bin/cli.js +232 -232
- package/browser/dom-strategy.md +121 -119
- package/browser/form-automation.md +84 -87
- package/browser/interaction-pipeline.md +242 -216
- package/browser/tab-and-window.md +136 -136
- package/desktop/desktop-targeting.md +85 -85
- package/desktop/electron-discovery.md +115 -115
- package/developer/github-forensics.md +89 -74
- package/dist/bundled/weavetab-all.md +1885 -1709
- package/dist/bundled/weavetab-browser.md +504 -479
- package/dist/bundled/weavetab-desktop.md +164 -164
- package/dist/bundled/weavetab-developer.md +77 -60
- package/dist/bundled/weavetab-documents.md +173 -131
- package/dist/bundled/weavetab-memory.md +259 -233
- package/dist/bundled/weavetab-network-and-perf.md +233 -206
- package/dist/bundled/weavetab-plugins.md +30 -25
- package/dist/bundled/weavetab-resilience.md +229 -201
- package/dist/bundled/weavetab-security.md +81 -75
- package/dist/granular/browser_dom-strategy.md +121 -119
- package/dist/granular/browser_form-automation.md +84 -87
- package/dist/granular/browser_interaction-pipeline.md +242 -216
- package/dist/granular/browser_tab-and-window.md +136 -136
- package/dist/granular/desktop_desktop-targeting.md +85 -85
- package/dist/granular/desktop_electron-discovery.md +115 -115
- package/dist/granular/developer_github-forensics.md +89 -74
- package/dist/granular/documents_canvas-and-visual-capture.md +117 -103
- package/dist/granular/documents_office-document-ingestion.md +91 -63
- package/dist/granular/memory_selector-memory-system.md +127 -127
- package/dist/granular/memory_session-trail.md +111 -95
- package/dist/granular/memory_site-learning.md +62 -53
- package/dist/granular/network-and-perf_device-and-environment.md +100 -87
- package/dist/granular/network-and-perf_network-intercept-and-mock.md +97 -84
- package/dist/granular/network-and-perf_performance-and-vitals.md +86 -84
- package/dist/granular/plugins_hooks-and-overrides.md +40 -35
- package/dist/granular/plugins_plugin-runtime.md +3 -3
- package/dist/granular/resilience_loop-breaker.md +72 -67
- package/dist/granular/resilience_session-time-travel.md +146 -131
- package/dist/granular/resilience_stale-ref-recovery.md +61 -53
- package/dist/granular/security_rbac-and-policies.md +50 -47
- package/dist/granular/security_secret-containment-protocol.md +62 -59
- package/documents/canvas-and-visual-capture.md +117 -103
- package/documents/office-document-ingestion.md +91 -63
- package/evals/evaluator.js +146 -146
- package/evals/scenarios.json +239 -239
- package/memory/selector-memory-system.md +127 -127
- package/memory/session-trail.md +111 -95
- package/memory/site-learning.md +62 -53
- package/network-and-perf/device-and-environment.md +100 -87
- package/network-and-perf/network-intercept-and-mock.md +97 -84
- package/network-and-perf/performance-and-vitals.md +86 -84
- package/package.json +4 -3
- package/plugins/hooks-and-overrides.md +40 -35
- package/plugins/plugin-runtime.md +3 -3
- package/resilience/loop-breaker.md +72 -67
- package/resilience/session-time-travel.md +146 -131
- package/resilience/stale-ref-recovery.md +61 -53
- package/security/rbac-and-policies.md +50 -47
- package/security/secret-containment-protocol.md +62 -59
- package/skills.json +26 -27
- package/src/api.js +239 -239
|
@@ -1,74 +1,89 @@
|
|
|
1
|
-
---
|
|
2
|
-
id: github-forensics
|
|
3
|
-
domain: developer
|
|
4
|
-
triggers:
|
|
5
|
-
- "analyze github"
|
|
6
|
-
- "read repository"
|
|
7
|
-
- "check pull request"
|
|
8
|
-
- "github issues"
|
|
9
|
-
- "inspect repo"
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
---
|
|
20
|
-
|
|
21
|
-
## 1. High-Level Repository Analysis (action: "analyze")
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
```json
|
|
26
|
-
{
|
|
27
|
-
"action": "analyze",
|
|
28
|
-
"repo": "Weavetab/MCP"
|
|
29
|
-
}
|
|
30
|
-
```
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
```
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
1
|
+
---
|
|
2
|
+
id: github-forensics
|
|
3
|
+
domain: developer
|
|
4
|
+
triggers:
|
|
5
|
+
- "analyze github"
|
|
6
|
+
- "read repository"
|
|
7
|
+
- "check pull request"
|
|
8
|
+
- "github issues"
|
|
9
|
+
- "inspect repo"
|
|
10
|
+
weavetab: ">=2.5.0"
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
# GitHub Forensics & Repository Architecture Inspection
|
|
14
|
+
|
|
15
|
+
Navigating GitHub repositories via web browsing burns massive token budgets loading HTML chrome, comment threads, and diff trees. The official `@weavetab/plugin-github` plugin provides a dedicated `github` tool that talks to the GitHub REST API and raw content endpoints directly — no browser DOM, no cloning.
|
|
16
|
+
|
|
17
|
+
Responses are cached on disk (`~/.weavetab-system/github_cache`) and subject to GitHub's API rate limits.
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## 1. High-Level Repository Analysis (action: "analyze")
|
|
22
|
+
|
|
23
|
+
Fetches repo metadata, the default branch, a flat recursive file tree, and a README snippet (first 100 lines). Results are cached and reused by `read`:
|
|
24
|
+
|
|
25
|
+
```json
|
|
26
|
+
{
|
|
27
|
+
"action": "analyze",
|
|
28
|
+
"repo": "Weavetab/MCP"
|
|
29
|
+
}
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
Returns fields such as `owner`, `repo`, `default_branch`, `description`, `language`, `file_tree` (array of `{path, type, size, sha}`), and `readme_snippet`.
|
|
33
|
+
|
|
34
|
+
If `repo` is omitted, the active tab's repository is used.
|
|
35
|
+
|
|
36
|
+
---
|
|
37
|
+
|
|
38
|
+
## 2. Reading Repository Source Files (action: "read")
|
|
39
|
+
|
|
40
|
+
Stream specific files from a public or authenticated repo via `raw.githubusercontent.com`. Requires a prior `analyze` (to cache the default branch and tree), or it will run one automatically:
|
|
41
|
+
|
|
42
|
+
```json
|
|
43
|
+
{
|
|
44
|
+
"action": "read",
|
|
45
|
+
"repo": "Weavetab/MCP",
|
|
46
|
+
"paths": ["src/server.ts"],
|
|
47
|
+
"line_range": [1, 200]
|
|
48
|
+
}
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
`paths` is relative to the repo root; `line_range` is an optional `[start, end]` (1-indexed).
|
|
52
|
+
|
|
53
|
+
---
|
|
54
|
+
|
|
55
|
+
## 3. Pull Request Forensics (action: "pr")
|
|
56
|
+
|
|
57
|
+
Retrieve PR details, changed files, and review comments:
|
|
58
|
+
|
|
59
|
+
```json
|
|
60
|
+
{
|
|
61
|
+
"action": "pr",
|
|
62
|
+
"repo": "Weavetab/MCP",
|
|
63
|
+
"number": 42
|
|
64
|
+
}
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
Passing `number` fetches that PR; omitting it lists recent PRs.
|
|
68
|
+
|
|
69
|
+
---
|
|
70
|
+
|
|
71
|
+
## 4. Issue Triage & Search (action: "issues")
|
|
72
|
+
|
|
73
|
+
Query the issue tracker with state, label, keyword, and limit filters:
|
|
74
|
+
|
|
75
|
+
```json
|
|
76
|
+
{
|
|
77
|
+
"action": "issues",
|
|
78
|
+
"repo": "Weavetab/MCP",
|
|
79
|
+
"state": "open",
|
|
80
|
+
"labels": ["bug"],
|
|
81
|
+
"limit": 5
|
|
82
|
+
}
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
- **`number`** fetches a single issue plus its comments.
|
|
86
|
+
- **`search`** runs a keyword search across issues.
|
|
87
|
+
- **`state`** (`open`/`closed`/`all`) and **`labels`** filter the listing; `limit` caps results (default 5).
|
|
88
|
+
|
|
89
|
+
> The GitHub **search** API is rate-limited more aggressively than raw/GET reads. `read` and `analyze` file fetches do not consume search-quota calls. If a call fails with a rate-limit message, wait until the reported reset time before retrying.
|