Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-comments --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .claude/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .claude/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-commentsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-comments --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .agents/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .agents/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-comments --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .cursor/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .cursor/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NeoLabHQ/context-engineering-kit.git --path skills/resolve-fixed-pr-comments--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-comments --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .gemini/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .gemini/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-commentsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .github/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .github/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NeoLabHQ/context-engineering-kit resolve-fixed-pr-comments --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/resolve-fixed-pr-comments .opencode/skills/resolve-fixed-pr-comments && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "resolve-fixed-pr-comments" agent skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/skills/resolve-fixed-pr-comments into .opencode/skills/resolve-fixed-pr-comments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-fixed-pr-comments", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
resolve-fixed-pr-commentsVerify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
Resolve Fixed PR Comments is an agent skill from NeoLabHQ/context-engineering-kit. Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Pull requests. It works with Git. The repository describes itself as: Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source… The licence is GPL-3.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 23e2428. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ghgitFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Resolve Fixed PR Comments loads about 4.1k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 2,075 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from NeoLabHQ/context-engineering-kit at commit 23e2428, republished under its GPL-3.0 licence (© NeoLabHQ). 2,075 words, ~4,106 tokens.
.claude/skills/resolve-fixed-pr-comments/SKILL.md (or your agent's skills folder).Load ONLY open/UNRESOLVED PR review threads, verify each one against the CURRENT state of the codebase (the fix may be committed/pushed OR exist only as uncommitted local changes — both count), and resolve ONLY the threads that are genuinely fixed or no longer relevant. The single permitted write action is resolving a thread. Nothing else is touched.
Violating the letter of these rules means failing the task. If you fail the task, you will be killed!
isResolved/is_resolved is false. Skip resolved threads.git status, git diff, git log, git branch) is allowed, and only to observe the current state.If any of these describe your reasoning, do NOT resolve the thread:
| Excuse | Reality |
|---|---|
| "The fix was committed, so it's done." | Read the CURRENT file and confirm the requirement is satisfied. Committed ≠ verified. |
| "Git diff shows the change." | A diff is historical reasoning. Confirm the requirement holds in the current file content, not that something changed. |
| "It's uncommitted, so it doesn't count yet." | Uncommitted local changes ARE valid evidence. Inspect the working tree as-is. |
| "I'll just make the small fix and resolve." | Editing code is strictly forbidden. Unfixed → unresolved. |
| "A reply would be polite." | No replies/comments. The only write action is resolving. |
| "Nitpick is trivial, resolve to tidy up." | Unaddressed = unresolved, regardless of triviality. |
| "Reviewer would obviously accept this." | You are not the reviewer. Resolve only on satisfied requirements, not on predicted approval. |
| "Not 100% sure, but likely fixed." | Unsure = leave unresolved. |
Work one thread at a time: (1) load unresolved threads with their GraphQL node id, (2) for each, read the current file(s) referenced and check every requirement against the present content, (3) resolve ONLY if fully satisfied/obsolete, otherwise skip. Report what was resolved and what was left and why.
Check if GitHub CLI is installed and authenticated:
gh auth statusCheck if the GitHub MCP server is available:
mcp__MCP_DOCKER__pull_request_reador simular command without MCP_DOCKER prefix, if installed directly.
gh auth login to authenticate.https://github.com/{owner}/{repo}/pull/{n} → number {n}) and do NOT consult the current branch.gh pr view --json number,url,headRefName # current branch's PRgh repo view --json owner,name.gh pr view errors with "no pull requests found" — STOP and report that no PR is associated with the branch (ask for a PR number/URL).Resolved/unresolved is a GraphQL reviewThreads { isResolved } concept — the REST /pulls/{n}/comments endpoint does NOT expose it. Use one of the two approaches below; if the primary is unavailable, fall back to the other.
Filter isResolved == false directly in the jq:
gh api graphql -f query='
query($owner:String!,$repo:String!,$pr:Int!){
repository(owner:$owner,name:$repo){
pullRequest(number:$pr){
reviewThreads(first:100){
nodes {
id
isResolved
isOutdated
path
line
startLine
originalLine
comments(first:50){
nodes { author{login} body diffHunk url }
}
}
}
}
}
}' -F owner=OWNER -F repo=REPO -F pr=PR_NUMBER \
--jq '[.data.repository.pullRequest.reviewThreads.nodes[]
| select(.isResolved==false)
| {id, path, isOutdated,
line: (.line // .startLine // .originalLine),
comments: [.comments.nodes[]
| {author: .author.login, url, body, diffHunk}]}]'This returns each unresolved thread with its GraphQL node id (needed to resolve it in Step 4), its file path, an isOutdated flag, a usable line, and ordered comments (author, body, permalink url, diffHunk).
IMPORTANT: For OUTDATED threads line is null (the diff moved). The jq above already falls back line // startLine // originalLine, so line is never null when any anchor exists. When ALL three are null, omit the :<line> segment entirely in the template — never render path:null.
If the GitHub MCP server (MCP_DOCKER) is available, use the mcp__MCP_DOCKER__pull_request_read tool with method: "get_review_comments":
mcp__MCP_DOCKER__pull_request_read
method: "get_review_comments"
owner: "OWNER"
repo: "REPO"
pullNumber: PR_NUMBER
perPage: 100It returns review_threads[], each with is_resolved, is_outdated, is_collapsed (all snake_case — verified against this tool's response) and comments[] (body, path, author, html_url). Keep only threads where is_resolved is false. Note the MCP comment objects expose path but NOT a line number, so use the html_url as the location anchor. Paginate with after: <endCursor> while pageInfo.hasNextPage is true.
The MCP review-thread object also carries the thread node
id(thePRRT_...node ID). Capture it per thread —mcp__MCP_DOCKER__pull_request_review_writewithmethod: "resolve_thread"needs it in Step 4.
For EACH unresolved thread, gather the concrete requirement(s) and verify them against the present file content. Apply the Critical Guidelines strictly.
path and read the CURRENT content (use the Read tool / git show :<path> is NOT needed — just read the working-tree file). Optionally run git diff -- <path> or git status ONLY to observe current uncommitted changes; never to reason about history as proof.| Disposition | Condition | Action |
|---|---|---|
| FIXED | Every requirement in the thread is fully satisfied in the current file content (committed OR uncommitted). | Mark to resolve in Step 4. |
| OBSOLETE | The code the comment referred to genuinely no longer exists / the concern is genuinely moot in the current code. | Mark to resolve in Step 4. |
| NOT FIXED | Any requirement is unmet, partially met, or you cannot confirm it from the current files. | LEAVE UNRESOLVED. Do nothing. |
| UNSURE | You cannot confidently verify satisfaction. | LEAVE UNRESOLVED. Do nothing. |
Do NOT edit code to make a thread pass. Do NOT run tests/builds/linters to "check". Verification is reading the current source and judging whether the requirement is met.
For each thread marked FIXED or OBSOLETE, resolve it using the thread's node id captured in Step 2. Use whichever path is available (prefer the one you used to load comments). Resolving an already-resolved thread is a harmless no-op.
resolveReviewThread mutation)The resolveReviewThread mutation takes a ResolveReviewThreadInput whose required field is threadId (the GraphQL node id from Step 2's reviewThreads.nodes[].id). Verified against GitHub's GraphQL schema via introspection (ResolveReviewThreadInput.threadId: ID!).
gh api graphql -f query='
mutation($threadId:ID!){
resolveReviewThread(input:{threadId:$threadId}){
thread { id isResolved }
}
}' -F threadId='PRRT_kwDOxxxxxxxxxxxxxxxx'On success the response is {"data":{"resolveReviewThread":{"thread":{"id":"PRRT_...","isResolved":true}}}}. Confirm isResolved is true.
pull_request_review_write → resolve_thread)The GitHub MCP server CAN resolve threads via mcp__MCP_DOCKER__pull_request_review_write with method: "resolve_thread". It requires only threadId (the thread node ID, e.g. PRRT_kwDOxxx). Per the tool's own documentation, owner/repo/pullNumber are NOT used by this method, but the tool schema marks them required — pass the PR's owner/repo/pullNumber to satisfy validation; they are ignored for the resolve operation.
mcp__MCP_DOCKER__pull_request_review_write
method: "resolve_thread"
threadId: "PRRT_kwDOxxxxxxxxxxxxxxxx"
owner: "OWNER"
repo: "REPO"
pullNumber: PR_NUMBERIf the MCP server is NOT available or its pull_request_review_write lacks resolve_thread, fall back to the gh CLI GraphQL mutation above.
ONLY
resolve_threadis permitted. Do NOT useunresolve_thread,create,submit_pending,delete_pending, or anyevent(APPROVE/REQUEST_CHANGES/COMMENT) — those are write actions this skill forbids.
| Parameter | Path | Type | Required | Description |
|---|---|---|---|---|
threadId | gh CLI & MCP | string (ID!) | Yes | The review thread's GraphQL node id (reviewThreads.nodes[].id, e.g. PRRT_kwDO...). This is the thread id, NOT a comment id and NOT a numeric REST id. |
method | MCP | string | Yes (MCP) | Must be "resolve_thread". |
owner | MCP | string | Yes (MCP schema) | Repo owner. Ignored by resolve_thread but required by the tool schema. |
repo | MCP | string | Yes (MCP schema) | Repo name. Ignored by resolve_thread but required by the tool schema. |
pullNumber | MCP | number | Yes (MCP schema) | PR number. Ignored by resolve_thread but required by the tool schema. |
clientMutationId | gh CLI | string | No | Optional dedupe token on the GraphQL input. Omit normally. |
Summarize without taking any further action:
path:line (or path if outdated) and a one-line reason (FIXED / OBSOLETE) plus the evidence in the current code.Input: resolve-fixed-pr-comments (no argument, current branch has PR #42)
Process: Load PR #42's unresolved threads (Step 2). Thread A on src/auth.ts:30 requires "add error handling for invalid token". Read current src/auth.ts — a try/catch now wraps the token check (uncommitted local change). Disposition FIXED → resolve via resolveReviewThread(threadId: "PRRT_..."). Thread B on README.md:10 is a nitpick "fix typo 'teh'". Read current README.md — still says "teh". Disposition NOT FIXED → leave unresolved.
Output: "PR #42: 2 unresolved threads loaded. Resolved 1 — src/auth.ts:30 (FIXED: try/catch added around token validation in working tree). Left unresolved 1 — README.md:10 (NOT FIXED: 'teh' typo still present)."
Input: resolve-fixed-pr-comments https://github.com/acme/app/pull/7
Process: Argument takes precedence over current branch. PR #7. One thread requires renaming getUser → fetchUser AND updating its callers. Current code renamed the function but one caller still uses getUser. Requirement only partially met → NOT FIXED → leave unresolved.
Output: "PR #7: 1 unresolved thread loaded. Resolved 0. Left unresolved 1 — src/user.ts:12 (NOT FIXED: function renamed but caller in src/page.ts:5 still calls getUser)."
| Situation | Handling |
|---|---|
| No PR for current branch | gh pr view errors → report and request a PR number/URL. |
| Argument is a URL | Extract trailing number after /pull/. |
| Zero unresolved threads | Resolve nothing; report "no unresolved comments". |
| >100 threads | Paginate (GraphQL after cursor / MCP after) before verifying. |
| MCP unavailable | Use gh GraphQL for both loading and resolving; if both unavailable, report limitation. |
MCP resolve_thread rejects missing owner/repo/pullNumber | The tool schema requires them even though the method ignores them — pass the PR's owner/repo/pullNumber. |
Could not resolve to a node with the global id | Wrong id — ensure you pass the thread node id (PRRT_...) from reviewThreads.nodes[].id, not a comment id or numeric REST id. |
Resolve mutation returns isResolved: true for a thread you didn't mean to touch | You resolved the wrong thread — there is no safe auto-undo permitted by this skill (unresolve is a forbidden write); report it to the user. |
| Fix exists only as uncommitted changes | Valid evidence — inspect the working-tree file and resolve if the requirement is satisfied. |
| Cannot confirm a requirement from current files | Leave the thread UNRESOLVED. Never resolve on assumption. |
| Tempted to edit code so a thread passes | Forbidden. No code modifications. Unfixed stays unresolved. |
© NeoLabHQ, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/resolve-fixed-pr-comments of NeoLabHQ/context-engineering-kit.
Open the folder on GitHubat commit 23e2428
Resolve Fixed PR Comments next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Resolve Fixed PR Comments this skillNeoLabHQ/context-engineering-kit | 1.7k | — | ~4.1k | Automated safety check: Pass | GPL-3.0 | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Contributor-First PR MergeHKUDS/OpenHarness | 16k | 1 repos | ~847 | Automated safety check: Pass | MIT | |
| Open Code Review CLIalibaba/open-code-review | 45k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Create Pull Requestcline/cline | 70k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Pull Request Title and Body Writeropeninterpreter/openinterpreter | 69k | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 |
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
alibaba/open-code-review
Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.
cline/cline
Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.
openinterpreter/openinterpreter
Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
NeoLabHQ/context-engineering-kit
A skill your agent uses when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides…
NeoLabHQ/context-engineering-kit
A skill your agent uses to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/.md for parallel agents to fix.
NeoLabHQ/context-engineering-kit
A skill your agent uses when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing…
NeoLabHQ/context-engineering-kit
Design multi-agent architectures for complex tasks. An agent skill from NeoLabHQ/context-engineering-kit.
NeoLabHQ/context-engineering-kit
Review an existing GitHub pull request and post inline review comments on its diff.
NeoLabHQ/context-engineering-kit
A skill your agent uses when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or…
Works with
Categories
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant. Resolve Fixed PR Comments is an agent skill from NeoLabHQ/context-engineering-kit. Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
Resolve Fixed PR Comments fits situations like: tasks that involve Pull requests.
Run `npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a claude-code`. Or copy the skill folder (skills/resolve-fixed-pr-comments in NeoLabHQ/context-engineering-kit) into .claude/skills/resolve-fixed-pr-comments in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a codex`. Or copy the skill folder (skills/resolve-fixed-pr-comments in NeoLabHQ/context-engineering-kit) into .agents/skills/resolve-fixed-pr-comments in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NeoLabHQ/context-engineering-kit --skill resolve-fixed-pr-comments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resolve-fixed-pr-comments, .gemini/skills/resolve-fixed-pr-comments, .github/skills/resolve-fixed-pr-comments and .opencode/skills/resolve-fixed-pr-comments in your project.
Going by SKILL.md and its folder, Resolve Fixed PR Comments needs the command-line tools its instructions call (gh and git).
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Resolve Fixed PR Comments is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Resolve Fixed PR Comments: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Open Code Review CLI (alibaba/open-code-review, 45k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
NeoLabHQ (a GitHub organization) maintains it in NeoLabHQ/context-engineering-kit, which has 1,749 GitHub stars. The repository holds 57 skills in this directory. The repository was last updated on August 26, 2026.
Source: NeoLabHQ/context-engineering-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.