razorpayrazorpay/blade/.agents/skills/resolve-comments/SKILL.md

resolve-comments

Skill658 starsChanged 4 months agoMITView on GitHub

Resolve comments on a pull request. Use whenever the user asks to resolve comments on a pull request.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Invalid Comment: After exploring the comment, codebase, and PR, you found the comment to be not applicable to the PR.
line 17
Distinctive:
Create a todo list with each comment, and its category so that its easier for you to track in next steps.
line 22
Distinctive:
Always respond to the comment as mentioned in the step 2.
line 33

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Your role is to read the comments that are given to you, validate them to see if they are valid, resolve them, and comment the resolution back to the user. You smartly delegate the comment to human when you're not sure.

Arguments

comments: the comments to resolve
pr_url: the URL of the pull request to resolve the comments on

Step 1: Validating the Comment

Comment can be clubbed into one of the following 4 categories:

Invalid Comment: After exploring the comment, codebase, and PR, you found the comment to be not applicable to the PR.
Requires Human Intervention: You are not sure or confident about your analysis and need human intervention (always be biased towards this category when you have smallest of doubt). For any large change or change in core behaviour, always classify it as Requires Human Intervention.
Requires Small/Medium Code Changes: The comment is valid and the change required is small or medium. For any large change, change in core behaviour, or any failure in resolution or inability to push commit to the PR, always classify it as Requires Human Intervention.
Query: General questions, feedback, notes, anything worth mentioning, etc.

Create a todo list with each comment, and its category so that its easier for you to track in next steps.

Step 2: Making the necessary changes

For Requires Small/Medium Code Changes, make the necessary changes, push the changes to the PR as commits, and reply to the comment summarizing what changed and the commit id of the change. Do a good research on the comment while making any changes. You can reclassify the comment as Requires Human Intervention if you find something later in the next step or you couldn't push the changes to the PR thus the commit id is not available.
For Requires Human Intervention, respond to the comment with the clarification and ask the human to handle the change.
For Invalid Comment, respond to the comment with the explanation of why it doesn't apply.
For Query, respond to the comment with the answer.

Step 3: Replying to comment

Always respond to the comment as mentioned in the step 2.

Step 4: React to original comment with appropriate emoji from ReactionEmojiMap below

Depending on the category of the comment, react to the original comment with the appropriate emoji from emoji map below. Do not mark the comment thread resolved (this is so that the human can see the reaction and know that the comment status instead of github collapsing the comment thread).

<ReactionEmojiMap>
  "Requires Small/Medium Code Changes": "rocket",
  "Requires Human Intervention": "confused",
  "Invalid Comment": "-1",
  "Query": "rocket"
</ReactionEmojiMap>

Download now (ZIP)

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
clice-io/clice★ 1.4ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-base-directory.mdcCursor rule
- .cursor/rules/orchestrator-guardrails.mdcCursor rule
- .cursor/rules/svelte-migration.mdcCursor rule
- check-component-readinessSkill
- code-reviewSkill
- create-prSkill
- get-agentic-blade-metricsSkill
- heal-prSkill
- migrate-to-rnSkill
- migrate-to-svelteSkill
- perform-task-end-to-endSkill
- review-prSkill
- update-componentSkill
- verify-with-browserSkill
- write-api-decisionSkill
- write-biweekly-announcementSkill
- write-unit-testsSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free