Agent skill

Review Comments Resolver

by mohitagw15856 in mohitagw15856/pm-claude-skills

Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile…

MITAuto-check passedBusiness, Finance & HR

Install Review Comments Resolver

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill review-comments-resolver -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills review-comments-resolver --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/review-comments-resolver .claude/skills/review-comments-resolver && rm -rf skills-src

Use ~/.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/

Facts

Skill name
review-comments-resolver
GitHub stars
1.4k
Token cost
~1.4k tokens
SKILL.md length
692 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile…

  • Works in 5 steps: Triage before touching: read all… → Mechanical means batch: typos, clarity… → Push-back is a reply, not a silence:… → …
  • Asked work through these review comments
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Resolution Rules and Output Format, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review Comments Resolver is an agent skill from mohitagw15856/pm-claude-skills. Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile reviewers who contradict each other. Use when asked work through these review comments, two reviewers want opposite things, close out the feedback on this doc, or which comments do I actually have to take. Produces the comment triage, the batched fixes, the push-back replies, the conflict reconciliations, and the closure…

Its SKILL.md is about 1.4k 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 Business, Finance & HR, covering GraphQL and Accounting and bookkeeping. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked work through these review comments
  • Two reviewers want opposite things
  • Close out the feedback on this doc
  • Which comments do I actually have to take

Example prompts

  • “/review-comments-resolver”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Triage before touching: read all comments first, sort into the five bins — resolving in document-order mixes typo fixes with strategy…
  2. Mechanical means batch: typos, clarity nits, formatting — apply all, resolve all, one aggregate thank-you. Individually replying "good…
  3. Push-back is a reply, not a silence: declining a comment requires saying so — "Kept as-is: the recommendation stays unhedged because…
  4. Conflicts get named, not averaged: when reviewer A wants detail added and reviewer B wants the section cut, the author doesn't split the…
  5. The sweep closes everything: every comment ends in resolved / replied / escalated — a doc with lingering open comments reads as contested…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Comments Resolver loads about 1.4k tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 692 words, ~1,366 tokens.

Download SKILL.mdSave it as .claude/skills/review-comments-resolver/SKILL.md (or your agent's skills folder).
name
review-comments-resolver
description
Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile reviewers who contradict each other. Use when asked work through these review comments, two reviewers want opposite things, close out the feedback on this doc, or which comments do I actually have to take. Produces the comment triage, the batched fixes, the push-back replies, the conflict reconciliations, and the closure sweep.

Review Comments Resolver Skill

A document with forty comments induces either capitulation (accept-all, the doc becomes committee mush) or avoidance (the comments age until the doc ships around them). Resolution is triage: most comments are mechanical (accept in batch, thank in aggregate), some are substantive-and-right (accept with the change named), some deserve push-back (drafted politely, decided by the doc's owner), and a few contradict each other — those aren't the author's to split; they get reconciled by naming the conflict to its parties. Every comment ends closed, and the doc stays the author's.

What This Skill Produces

  • The triage table — every comment sorted: accept-mechanical / accept-substantive / push-back / conflict / out-of-scope
  • The batch plan — mechanical fixes applied in one pass, resolved with one courtesy note
  • The push-back replies — drafted: the reviewer's point honored, the decision explained, the owner's call made
  • The conflict reconciliations — contradicting reviewers named to each other with the author's recommendation
  • The closure sweep — nothing left dangling; the resolved-vs-declined summary if the doc's approver wants it

Required Inputs

Ask for these if not provided:

  • The comments and the doc — the actual comment set; triage reads them, not a summary of them
  • The authority map — whose comments are directives (the approver), whose are advice (peers), whose are taste — the same words resolve differently by author; "consider rewording" from the VP and from a peer are different speech acts
  • The doc's non-negotiables — what the author is defending (the recommendation, the scope, the tone) — push-back needs a spine to push from
  • The deadline — a closing date makes "let's discuss" comments convert to decisions instead of orbit

Framework: The Resolution Rules

  1. Triage before touching: read all comments first, sort into the five bins — resolving in document-order mixes typo fixes with strategy debates and exhausts the author by page three. The bins get processed cheapest-first: mechanical batch, then substantive accepts, then push-backs, then conflicts.
  2. Mechanical means batch: typos, clarity nits, formatting — apply all, resolve all, one aggregate thank-you. Individually replying "good catch!" forty times is a day lost to etiquette.
  3. Push-back is a reply, not a silence: declining a comment requires saying so — "Kept as-is: the recommendation stays unhedged because [reason]; happy to discuss" — because silently-unaddressed comments return in the next review round with reinforcements. The author owns the call on advice-comments; directive-comments that the author disagrees with get escalated as a conversation, not quietly overridden.
  4. Conflicts get named, not averaged: when reviewer A wants detail added and reviewer B wants the section cut, the author doesn't split the difference into mush — the conflict is surfaced ("A and B, you're asking for opposites here — my recommendation is B's cut because [header test]; A, does the appendix satisfy the need?") and decided once, on the record.
  5. The sweep closes everything: every comment ends in resolved / replied / escalated — a doc with lingering open comments reads as contested, and approvers notice. The closing summary ("38 taken, 4 declined with reasons, 2 conflicts resolved with A/B") converts the review round into a credibility artifact.
Show full SKILL.md (194 more words)Show less

Output Format

Comment Resolution: [doc] — [N] comments

The Triage

#Comment (gist)FromBinAction

Batch Pass

[The mechanical list → applied · the aggregate note]

Push-Backs (drafted)

[Per comment: the honor-then-decide reply, verbatim]

Conflicts (reconciled)

[Per pair: the naming message + the author's recommendation]

The Sweep

[All closed · the summary line for the approver]

Quality Checks

  • Every comment landed in exactly one bin before any fix was made
  • The authority map informed the bins — directives and advice resolved differently
  • Every decline has a stated reason in a reply
  • No conflict was averaged into mush — each was named and decided
  • Zero comments remain open at the end

Anti-Patterns

  • Do not accept-all — forty reviewers produce committee prose; the author is the editor
  • Do not resolve in page order — bins first, or the strategy debates drown in typo fixes
  • Do not decline silently — unaddressed comments respawn with allies
  • Do not split contradictory feedback down the middle — mush satisfies neither reviewer and weakens the doc
  • Do not leave "let's discuss" comments orbiting — the deadline converts them to decisions

Example Trigger Phrases

  • "Work through these review comments."
  • "Close out the feedback on this doc."
  • "Which comments do I actually have to take?"

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/review-comments-resolver of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Review Comments Resolver 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.

Review Comments Resolver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Comments Resolver this skillmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
Configure Authdotnet/skills5.6k1 repos~1.8kAutomated safety check: PassMIT
Sync State Invariantsopenchamber/openchamber11k—~2.7kAutomated safety check: PassMIT
Gh QueueLanternOps/breeze133—~5kAutomated safety check: PassAGPL-3.0
Web AutopilotLeoYeAI/openclaw-master-skills2.2k—~4.5kAutomated safety check: PassMIT
Fastllm Limits Budgetsazrtydxb/Fastllm-proxy108—~467Automated safety check: PassApache-2.0

Similar skills

  • Configure Auth

    dotnet/skills

    Official

    Add authentication and authorization to a Blazor Web App, accounting for the app's render mode.

    5.6k GitHub starsUsed in 1 repo~1.8k tokens
    Business, Finance & HRAuto-check passed
  • Sync State Invariants

    openchamber/openchamber

    A skill your agent uses when changing session synchronization, bootstrap or reconnect state, event reducers, polling, optimistic updates, message queues, live activity, ordering/reconciliation…

    11k GitHub stars~2.7k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Gh Queue

    LanternOps/breeze

    A skill your agent uses when reviewing, triaging, or managing the incoming GitHub backlog on the Breeze repo — PRs, Discussions, AND Issues.

    133 GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check passed
  • Web Autopilot

    LeoYeAI/openclaw-master-skills

    Record any web app operation once, AI turns it into a reusable automation tool.

    2.2k GitHub stars~4.5k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed
  • Fastllm Limits Budgets

    azrtydxb/Fastllm-proxy

    Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices.

    108 GitHub stars~467 tokensUpdated 5 days ago
    Business, Finance & HRAuto-check passed
  • Unit Commitment Operating Rules

    benchflow-ai/skillsbench

    A skill your agent uses for day-ahead or multi-period unit commitment problems, including thermal on/off schedules, dispatch, startup/shutdown logic, minimum up/down time, ramping, spinning reserve…

    1.8k GitHub stars~2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Review Comments Resolver

What does Review Comments Resolver do?

Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile…. Review Comments Resolver is an agent skill from mohitagw15856/pm-claude-skills. Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile reviewers who contradict each other.

When should I use Review Comments Resolver?

Review Comments Resolver fits situations like: asked work through these review comments; two reviewers want opposite things; close out the feedback on this doc; which comments do I actually have to take.

How do I install Review Comments Resolver in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill review-comments-resolver -a claude-code`. Or copy the skill folder (skills/review-comments-resolver in mohitagw15856/pm-claude-skills) into .claude/skills/review-comments-resolver in your project. Claude Code loads it when a task matches its description.

How do I install Review Comments Resolver in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill review-comments-resolver -a codex`. Or copy the skill folder (skills/review-comments-resolver in mohitagw15856/pm-claude-skills) into .agents/skills/review-comments-resolver in your project. Codex loads it when a task matches its description.

Can I use Review Comments Resolver in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill review-comments-resolver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-comments-resolver, .gemini/skills/review-comments-resolver, .github/skills/review-comments-resolver and .opencode/skills/review-comments-resolver in your project.

What does Review Comments Resolver need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Comments Resolver is instructions for the agent only.

Does Review Comments Resolver access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Comments Resolver safe to install?

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.

What licence does Review Comments Resolver use?

Review Comments Resolver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Comments Resolver use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Comments Resolver?

Skills that share tags, products or a category with Review Comments Resolver: Configure Auth (dotnet/skills, 5.6k stars), Sync State Invariants (openchamber/openchamber, 11k stars), Gh Queue (LanternOps/breeze, 133 stars) and Web Autopilot (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Comments Resolver?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.