跳到正文
cccskills
免费在 GitHub 公开

triage-reviews

Collect PR review feedback, check each finding against code and documentation, and fix valid issues. Run project checks, commit and push changes, then reply to review threads and resolve fixed findings or false positives.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Fetch PR review comments, verify each against real code/docs, fix valid issues, commit and push

集成工具GitHub
查看安装方法

适用场景

  • Deduplicating feedback from multiple reviewers
  • Checking review findings against current code
  • Testing and pushing fixes for valid findings
  • Replying to threads and tracking unresolved issues

包含的文件(1)

  • SKILL.md5.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Triage PR Review Comments

Fetch all review comments on the current PR, verify each finding against real code, fix valid issues, and push.

Phase 1: Gather Comments

  1. Determine the PR number:

    • Use $ARGUMENTS if provided
    • Otherwise: gh pr view --json number --jq .number
  2. Fetch ALL comments (reviewers post in multiple places):

    gh api --paginate repos/{owner}/{repo}/pulls/{pr}/reviews
    gh api --paginate repos/{owner}/{repo}/pulls/{pr}/comments
    gh api --paginate repos/{owner}/{repo}/issues/{pr}/comments
    
  3. Extract unique findings — deduplicate across Copilot, Greptile, and human reviewers. Group by file and line.

Phase 2: Verify Each Finding

For EVERY finding, verify against real code before accepting or rejecting:

  1. Read the actual code at the referenced file:line
  2. Check if the issue still exists — it may already be fixed in a later commit
  3. Verify correctness using:
    • Code analysis (read surrounding context, trace call paths)
    • Run btca resources to see what's available, then btca ask -r <resource> -q "..." for library/framework questions
    • Web search for API behavior, language semantics, or CVEs
  4. Classify each finding:
    • Valid — real bug, real gap, or real improvement needed
    • False positive — reviewer misread the code, outdated reference, or style preference

Phase 3: Fix & Ship

  1. Fix all Valid findings
  2. Run the project's lint/test commands
    • If lint/tests fail, fix the failures before committing
    • If a failure cannot be fixed automatically, skip that fix and report it as Valid (unfixed) in the Phase 4 table
  3. git add only changed files, git commit with message:
    fix: Address PR review feedback
    
    - <one-line summary per fix>
    
  4. Push: gt submit (or git push if not using Graphite)

Phase 3.5: Reply on each thread, then resolve it

Pushing the fix isn't enough. Each inline review comment lives in its own thread that GitHub keeps showing as "Unresolved" until someone explicitly resolves it. The skill must close that loop for every Valid and False-positive finding so the PR view actually reflects what was triaged.

Workflow per finding:

  1. Reply on the thread with the verdict and evidence:

    • Valid + fixed: Fixed in <short-sha>. <one-line what changed>.
    • Valid + unfixed: Valid, deferred to follow-up. Reason: <why>.
    • False positive: False positive. <one-line evidence: file:line shows X, or doc link Y>.
  2. Resolve the thread only when the finding is Fixed or False positive. Valid + unfixed threads must stay open so the PR view continues to surface the real bug. Resolving them would let the PR look ready while the bug is still in the code. Leave the maintainer to close those threads when they file the follow-up.

GitHub's review threads can only be resolved via GraphQL (REST has no endpoint). The thread ID is a GraphQL node ID, not the REST comment ID, so fetch both together. Use --paginate so PRs with more than 100 threads are covered, the page size cap is per-request not total:

PR=<pr-number>
OWNER=<owner>
REPO=<repo>

gh api graphql --paginate -f query='
  query($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) {
    repository(owner: $owner, name: $repo) {
      pullRequest(number: $pr) {
        reviewThreads(first: 100, after: $endCursor) {
          pageInfo { hasNextPage endCursor }
          nodes {
            id
            isResolved
            comments(first: 1) { nodes { databaseId path line body } }
          }
        }
      }
    }
  }' \
  -F owner="$OWNER" -F repo="$REPO" -F pr=$PR \
  --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false) | {threadId: .id, commentId: .comments.nodes[0].databaseId, path: .comments.nodes[0].path, line: .comments.nodes[0].line}' \
  > /tmp/triage-threads-$PR.json

Each entry now has {threadId, commentId, path, line}. Match it against your Phase-2 finding map (by path + line or commentId). For each match:

# Post reply (REST endpoint for replies on a specific review comment)
gh api -X POST "/repos/$OWNER/$REPO/pulls/$PR/comments/$COMMENT_ID/replies" \
  -f body="Fixed in $SHORT_SHA. <one-line>."

# Resolve the thread (GraphQL) — Fixed and False-positive only. SKIP for Valid+unfixed.
gh api graphql -f query="
  mutation {
    resolveReviewThread(input: {threadId: \"$THREAD_ID\"}) {
      thread { isResolved }
    }
  }"

If the parent review left a separate top-level summary comment (Greptile's Greptile Summary issue-level comment, for example), leave it alone, only inline review threads need resolving.

Cap: resolve only threads tied to findings you actually classified. Do not bulk-resolve unrelated threads (other reviewers, human discussion, follow-up questions that aren't from this triage round).

Phase 4: Report

Present a final summary table of ALL findings with verdicts:

#SourceFile:LineFindingVerdictReasonThread

Last column: replied + resolved, replied + still open (e.g. waiting on reviewer), or n/a (no inline thread, only summary). If any thread stayed open, name it explicitly so the next pass picks it up.

Notes

  • Never dismiss a finding without reading the actual code first
  • If unsure, err toward "Valid" — it's cheaper to fix than to miss a bug
  • For library/API questions, always use btca or web search — don't guess

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Prioritize open LinkedIn integration issues and pull requests, or proposed code changes, using report completeness, severity, reach, and readiness checks. Produce ranked lists, identify missing evidence, and recommend concrete next steps for maintainers.

中文简介正在准备中。当前显示英语简介。

  • Prioritizing a backlog of open issues
  • Separating reports that need more evidence
  • Comparing pull requests for production readiness
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

Investigate LinkedIn integration bugs by comparing issue reports with source code. Separate established facts from unverified claims, identify missing evidence, and optionally check reproduction in a live environment after explicit approval.

中文简介正在准备中。当前显示英语简介。

  • Investigating a reported LinkedIn integration bug
  • Identifying evidence missing from an issue report
  • Checking live reproduction after approval
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

Evaluate whether a proposed LinkedIn integration fix addresses its linked issue by reviewing the report, code changes, and tests. Flag implementation concerns and optionally compare live results with a genuine recorded baseline after approval.

中文简介正在准备中。当前显示英语简介。

  • Checking whether a PR addresses its linked issue
  • Reviewing language-dependent detection and selectors
  • Comparing live results with a recorded baseline
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

Search Git repositories locally to answer questions about implementation or usage. The skill clones or updates repositories, examines their contents, and presents findings with source links and complete code examples, including necessary imports.

中文简介正在准备中。当前显示英语简介。

  • Investigating how a repository implements a feature
  • Finding usage examples with complete imports
  • Revisiting and searching previously cloned repositories
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

Prepare GitHub bug reports, feature requests, documentation issues, and chores using repository forms and supporting evidence. Search existing issues to choose between a new report and a comment, then publish only after approval of the exact public text.

中文简介正在准备中。当前显示英语简介。

  • Preparing a bug report with supporting evidence
  • Drafting a feature request using the repository form
  • Adding new evidence to an existing issue
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

Use LinkedIn profiles, company information, jobs, posts, and inbox conversations for recruiting, job searches, and outreach research. Through the bundled MCP server, an agent connection to LinkedIn, the skill also handles explicitly authorized messages and connection requests.

中文简介正在准备中。当前显示英语简介。

  • Researching people and companies for recruiting
  • Finding jobs and checking application links
  • Reviewing posts and feed content
stickerdaniel/linkedin-mcp-server39892026年10月22日 更新

查看 stickerdaniel 的全部技能

报告此技能的问题