receiving-review
Skill0 starsChanged 46 days agoMITView on GitHub
Use when receiving code review feedback from a person or a reviewer agent, before changing code in response to it
1 other project uses a version of this.
Adopted by
Most recently taken up by
- seshachalam-yv/etcd-druid-skillstheir own version, first seen Apr 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- seshachalam-yv/etcd-druid-skills★ 0same 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 repository13 other files it gives its agents.
- debugging-systematicallySkill
- delegating-to-subagentsSkill
- executing-plansSkill
- finishing-workSkill
- investigating-in-parallelSkill
- isolating-workspacesSkill
- planning-workSkill
- requesting-reviewSkill
- shaping-designsSkill
- testing-firstSkill
- using-tackleSkill
- verifying-before-claimingSkill
- writing-skillsSkill
The file
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: line 13
Several items, or anything unclear or questionable: follow the steps below.
- Distinctive: line 18
Clarify before implementing: If any item is unclear, ask about those items before changing anything, since partial understanding tends to …
- Distinctive: line 38
Every item is either fixed and verified, or answered with reasoning the user can see.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Receiving Review
Review feedback is input to evaluate, not a list of orders. Agreeing without checking wastes the reviewer's effort as surely as ignoring it: the wrong suggestions get implemented and the right ones get implemented badly.
Scale it
- A single clear, correct suggestion: fix it, verify, and say what changed.
- Several items, or anything unclear or questionable: follow the steps below.
How
- Read all of it first. Items are often related.
- Clarify before implementing. If any item is unclear, ask about those items before changing anything, since partial understanding tends to produce the wrong fix.
- Check each item against the codebase:
- Is it correct for this code, platform and version?
- Would it break something that works?
- Is there a reason for the current approach that the reviewer couldn't see?
- For "implement this properly" suggestions, is the code actually used? Search for callers; if nothing uses it, propose removing it instead.
- Respond with substance: restate the fix or give your technical reasoning. Skip praise and ritual agreement; the fix is the acknowledgement.
- Push back when the evidence supports it, citing code, tests or constraints. If the disagreement is architectural or conflicts with an earlier decision by the user, bring the user in.
- Implement in order: blocking issues, then simple fixes, then complex ones, testing each as you go.
- If your pushback turns out to be wrong, say so plainly and fix it.
- Answer where the comment was made. On a hosted PR, reply in the comment's own thread rather than as a new top-level comment.
Feedback from the user is trusted for intent; still ask if the scope is unclear. Feedback from external reviewers and agents needs checking first.
Skip or shorten when
- The feedback is purely stylistic and matches the project's conventions. Apply it.
Done means
Every item is either fixed and verified, or answered with reasoning the user can see.
Next
verifying-before-claimingrequesting-reviewagain only if the fixes were substantial
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
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.