review-comments

Name: review-comments
Author: webflow

106stars16forks

How to install review-comments?

webflow/webflow-skills/review-comments

$npx -y skills add webflow/webflow-skills --skill review-comments

Installs into the current project.

Summary

Review open comment threads on a Webflow site and triage each one.

Files · 1

View on GitHub

SKILL.md

1	Review open comment threads on a Webflow site and triage each one.
2
3	Input: `$ARGUMENTS` — a site name (e.g. "Workhaus"), site ID (e.g. `6808fd4eff835ee3af009d6f`), or either with the `-reply` flag (e.g. `Workhaus -reply`).
4
5	Flags:
6	- `-reply` — in addition to writing the report, post a bot reply to each non-open thread. Without this flag, the skill runs in report-only mode (read-only).
7
8	Parse `$ARGUMENTS` at the start: strip `-reply` from the input to get the site identifier, and set `replyMode = true` if `-reply` was present, `false` otherwise.
9
10	---
11
12	## Step 1 — Resolve the site
13
14	### If the site identifier is empty or blank — cross-site comment survey
15
16	1. Call `data_sites_tool > list_sites` to get all sites. Page through until all are collected.
17	2. For each site, call `data_comments_tool > list_comment_threads` with `isResolved: false` and `limit: 100`. Page through until all unresolved threads are collected. If the API does not support `isResolved` filtering, fetch all threads and filter client-side to `isResolved === false`. Process sites in batches of 20 (batch multiple actions in a single tool call). After each batch completes, log a progress line: `Batch {N}/{total} done (sites {start}–{end}): {summary of findings, e.g. "all 0 threads" or "SiteName has X threads, rest 0"}.`
18	3. For each site, compute:
19	- `unresolvedCount` = total unresolved threads
20	- `newestDate` = the maximum `lastUpdated` value across all unresolved threads for that site (ISO → human-readable date, e.g. "Apr 3, 2026"). If no threads, show `—`.
21	- `oldestDate` = the minimum `lastUpdated` value across all unresolved threads for that site (ISO → human-readable date). If no threads, show `—`.
22	4. Sort sites by `unresolvedCount` descending. Take the top 10.
23	5. Above the table, show a heading line: `### Checked {totalSiteCount} sites — {sitesWithUnresolved} have unresolved comments.`
24	6. Display a table in this format (link just the site name to `https://webflow.com/design/{siteId}`):
25
26	```
27	\| Site \| Unresolved Comments \| Newest / Oldest \|
28	\|------\|---------------------\|-----------------\|
29	\| [Site Name](https://webflow.com/design/{siteId}) ({siteId}) \| {N} \| {newestDate} / {oldestDate} \|
30	```
31
32	7. After the table, tell the user: "Run `/webflow-mcp:review-comments <site name or ID>` to review a specific site."
33	8. Write the survey output to a file:
34	- Ensure `comment-reviews/` exists (create with `mkdir comment-reviews` if not).
35	- Filename: `comment-reviews/triage-report-{YYYY-MM-DD-HH-MM}.md` using the current local time (zero-padded).
36	- File contents: a bold H1 title `# Webflow Comment Review`, then a blank line, then an H3 line `### Report created on: {human-readable date, time, and timezone, e.g. "April 16, 2026 at 10:39 AM PDT"}`, then a blank line, then the H3 heading line (`### Checked …`) and the full table from steps 5–6 above, in markdown.
37	- Log the path after writing, e.g. `Report written to comment-reviews/triage-report-2026-04-16-14-30.md`.
38	9. Stop — do not proceed to Step 2.
39
40	### If the site identifier looks like a Webflow site ID (24-char hex), use it directly.
41
42	### Otherwise call `data_sites_tool > list_sites` and find the site whose `displayName` matches the identifier (case-insensitive). If no match, tell the user and stop.
43
44	---
45
46	## Step 2 — Fetch all open threads
47
48	Always make a fresh API call here — never reuse thread data from earlier in the conversation. The user may have added or resolved comments since the last run.
49
50	Call `data_comments_tool > list_comment_threads` with `isResolved: false` and `limit: 100`. Page through results until all threads are collected.
51
52	Log: `Site: {displayName}` and `Found {N} open thread(s)`.
53
54	---
55
56	## Step 3 — Build page-level element map
57
58	From the already-fetched thread list, build a frequency map of `elementId.element → Set<pageId>` across all threads. Any `elementId.element` that appears on 2 or more distinct pages is almost certainly the page root/body element (a real element ID would be page-scoped; only shared structural roots repeat across pages).
59
60	No API calls needed — this is a local computation on the thread data.
61
62	---
63
64	## Step 4 — Triage each thread
65
66	For each thread:
67
68	### 4a — Fetch replies
69
70	Call `data_comments_tool > list_comment_replies` for this thread.
71
72	### 4b — Dedup check
73
74	Look for replies whose `content` includes the string `— 🤖 Comment Review Agent`.
75
76	If found, note the most recent one (`lastAgentReply`). If no human reply exists with a `createdOn` after `lastAgentReply.createdOn`, skip this thread (increment skipped count, continue to next thread).
77
78	### 4c — Compute element context
79
80	- `elementId` = `thread.elementId?.element`
81	- `isPageLevel` = `elementId` appears on 2 or more distinct `pageId`s in the frequency map from Step 3
82
83	### 4d — Classify the thread
84
85	Use the following criteria:
86
87	noise — No real design or

People who liked this also viewed

6 picks

Type

web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026483k29k
lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026332k16k
design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026280k66k
ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026280k109k
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026249k92k
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026225k182k

review-comments

106stars16forks

View on GitHub

How to install review-comments?

webflow/webflow-skills/review-comments

$npx -y skills add webflow/webflow-skills --skill review-comments

Installs into the current project.

Summary

Review open comment threads on a Webflow site and triage each one.

Files · 1

View on GitHub

SKILL.md

1	Review open comment threads on a Webflow site and triage each one.
2
3	Input: `$ARGUMENTS` — a site name (e.g. "Workhaus"), site ID (e.g. `6808fd4eff835ee3af009d6f`), or either with the `-reply` flag (e.g. `Workhaus -reply`).
4
5	Flags:
6	- `-reply` — in addition to writing the report, post a bot reply to each non-open thread. Without this flag, the skill runs in report-only mode (read-only).
7
8	Parse `$ARGUMENTS` at the start: strip `-reply` from the input to get the site identifier, and set `replyMode = true` if `-reply` was present, `false` otherwise.
9
10	---
11
12	## Step 1 — Resolve the site
13
14	### If the site identifier is empty or blank — cross-site comment survey
15
16	1. Call `data_sites_tool > list_sites` to get all sites. Page through until all are collected.
17	2. For each site, call `data_comments_tool > list_comment_threads` with `isResolved: false` and `limit: 100`. Page through until all unresolved threads are collected. If the API does not support `isResolved` filtering, fetch all threads and filter client-side to `isResolved === false`. Process sites in batches of 20 (batch multiple actions in a single tool call). After each batch completes, log a progress line: `Batch {N}/{total} done (sites {start}–{end}): {summary of findings, e.g. "all 0 threads" or "SiteName has X threads, rest 0"}.`
18	3. For each site, compute:
19	- `unresolvedCount` = total unresolved threads
20	- `newestDate` = the maximum `lastUpdated` value across all unresolved threads for that site (ISO → human-readable date, e.g. "Apr 3, 2026"). If no threads, show `—`.
21	- `oldestDate` = the minimum `lastUpdated` value across all unresolved threads for that site (ISO → human-readable date). If no threads, show `—`.
22	4. Sort sites by `unresolvedCount` descending. Take the top 10.
23	5. Above the table, show a heading line: `### Checked {totalSiteCount} sites — {sitesWithUnresolved} have unresolved comments.`
24	6. Display a table in this format (link just the site name to `https://webflow.com/design/{siteId}`):
25
26	```
27	\| Site \| Unresolved Comments \| Newest / Oldest \|
28	\|------\|---------------------\|-----------------\|
29	\| [Site Name](https://webflow.com/design/{siteId}) ({siteId}) \| {N} \| {newestDate} / {oldestDate} \|
30	```
31
32	7. After the table, tell the user: "Run `/webflow-mcp:review-comments <site name or ID>` to review a specific site."
33	8. Write the survey output to a file:
34	- Ensure `comment-reviews/` exists (create with `mkdir comment-reviews` if not).
35	- Filename: `comment-reviews/triage-report-{YYYY-MM-DD-HH-MM}.md` using the current local time (zero-padded).
36	- File contents: a bold H1 title `# Webflow Comment Review`, then a blank line, then an H3 line `### Report created on: {human-readable date, time, and timezone, e.g. "April 16, 2026 at 10:39 AM PDT"}`, then a blank line, then the H3 heading line (`### Checked …`) and the full table from steps 5–6 above, in markdown.
37	- Log the path after writing, e.g. `Report written to comment-reviews/triage-report-2026-04-16-14-30.md`.
38	9. Stop — do not proceed to Step 2.
39
40	### If the site identifier looks like a Webflow site ID (24-char hex), use it directly.
41
42	### Otherwise call `data_sites_tool > list_sites` and find the site whose `displayName` matches the identifier (case-insensitive). If no match, tell the user and stop.
43
44	---
45
46	## Step 2 — Fetch all open threads
47
48	Always make a fresh API call here — never reuse thread data from earlier in the conversation. The user may have added or resolved comments since the last run.
49
50	Call `data_comments_tool > list_comment_threads` with `isResolved: false` and `limit: 100`. Page through results until all threads are collected.
51
52	Log: `Site: {displayName}` and `Found {N} open thread(s)`.
53
54	---
55
56	## Step 3 — Build page-level element map
57
58	From the already-fetched thread list, build a frequency map of `elementId.element → Set<pageId>` across all threads. Any `elementId.element` that appears on 2 or more distinct pages is almost certainly the page root/body element (a real element ID would be page-scoped; only shared structural roots repeat across pages).
59
60	No API calls needed — this is a local computation on the thread data.
61
62	---
63
64	## Step 4 — Triage each thread
65
66	For each thread:
67
68	### 4a — Fetch replies
69
70	Call `data_comments_tool > list_comment_replies` for this thread.
71
72	### 4b — Dedup check
73
74	Look for replies whose `content` includes the string `— 🤖 Comment Review Agent`.
75
76	If found, note the most recent one (`lastAgentReply`). If no human reply exists with a `createdOn` after `lastAgentReply.createdOn`, skip this thread (increment skipped count, continue to next thread).
77
78	### 4c — Compute element context
79
80	- `elementId` = `thread.elementId?.element`
81	- `isPageLevel` = `elementId` appears on 2 or more distinct `pageId`s in the frequency map from Step 3
82
83	### 4d — Classify the thread
84
85	Use the following criteria:
86
87	noise — No real design or

People who liked this also viewed

6 picks

Type