agentleFS
fightZyfightZy/simple-skills/.agents/skills/receiving-feedback/SKILL.md

receiving-feedback

Skill1 starsChanged 12 days agoMITView on GitHub

Use when receiving feedback, suggestions, criticism, or review on any work — before acting on it. Especially when feedback seems unclear, questionable, conflicts with prior decisions, or asks for "professional" expansion.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Distinctive:

    If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

    line 49
  2. Distinctive:

    Still ask: if scope unclear

    line 87
  3. Distinctive:

    If we don't need this, don't add it.

    line 121
  4. Distinctive:

    Use reasoning, not defensiveness

    line 147
  5. Distinctive:

    If you're uncomfortable pushing back: name the tension to yourself, then raise the issue with your partner.

    line 152
  6. Distinctive:

    If you pushed back and were wrong:

    line 156
  7. Distinctive:

    Verify. Question. Then act.

    line 196

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Receiving Feedback

Overview

Receiving feedback requires genuine evaluation, not emotional performance.

Core principle: Verify before acting. Ask before assuming. Correctness over social comfort.

When to Use

  • Receiving feedback, suggestions, criticism, or review on any work
  • Feedback seems unclear, questionable, or conflicts with prior decisions
  • Reviewer asks to "do it properly / more comprehensively"
  • Feedback from external sources you don't fully trust

When NOT to use: Purely factual corrections with no ambiguity (just apply them).

The Response Pattern

WHEN receiving feedback:

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against reality of the work
4. EVALUATE: Sound for THIS context?
5. RESPOND: Factual acknowledgment or reasoned pushback
6. ACT: One item at a time, verify each

Forbidden Responses

NEVER:

  • "You're absolutely right!" / "Great point!" / "Excellent feedback!" (performative)
  • "Let me do that now" (before verification)
  • ANY gratitude expression ("Thanks for...")

INSTEAD:

  • Restate the actual requirement
  • Ask clarifying questions
  • Push back with reasoning if wrong
  • State the fix factually once acting — no preamble, no thanks

If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

Red Flags - STOP

  • About to say "You're right" / "Great point" / "Thanks"
  • About to act on feedback before verifying it
  • About to implement some items while deferring unclear ones
  • Assuming an external reviewer is correct
  • Tempted to skip pushback to avoid discomfort

All of these mean: Pause. Verify. Then act or push back with reasoning.

Rationalization Table

ExcuseReality
"Thanks is just polite"Actions speak. The fix shows you heard it.
"External reviewer knows better"External feedback = suggestions to evaluate, not orders. Verify.
"Implement the clear ones now, ask later"Items may be related. Partial understanding = wrong result. Clarify all first.
"Can't verify, proceed anyway"State the limitation, ask for direction.
"Pushing back is rude"Correctness > comfort. Use reasoning, not defensiveness.
"They said 'do it properly', so I must"Check actual need first. Don't expand scope without justification.

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not act on anything yet
  ASK for clarification on unclear items

WHY: Items may be related. Partial understanding = wrong result.

Source-Specific Handling

From your partner

  • Trusted - act after understanding
  • Still ask if scope unclear
  • Skip ceremony — act or acknowledge factually

From External Reviewers

BEFORE acting:
  1. Correct for THIS context?
  2. Breaks existing work?
  3. Reason for current state?
  4. Does reviewer understand full context?

IF suggestion seems wrong:
  Push back with reasoning

IF can't easily verify:
  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

IF conflicts with prior decisions:
  Stop and discuss with your partner first

External feedback = suggestions to evaluate, not orders to follow. Be skeptical, but check carefully.

Need Check for "Professional" / "Comprehensive" Suggestions

IF reviewer suggests "doing it properly / more comprehensively":
  Check whether the expanded scope is actually needed

  IF not needed: "This isn't actually used/required. Remove it? Or keep minimal?"
  IF needed: Then implement properly

If we don't need this, don't add it. Don't let "professional" framing expand scope without justification.

Action Order

FOR multi-item feedback:
  1. Clarify anything unclear FIRST
  2. Then act in this order:
     - Blocking issues (breaks things, wrong outcomes)
     - Simple fixes (typos, labels, small corrections)
     - Complex fixes (restructuring, significant changes)
  3. Verify each fix individually
  4. Confirm no regressions

When To Push Back

Push back when:

  • Suggestion breaks existing work
  • Reviewer lacks full context
  • Violates actual need (unnecessary expansion)
  • Incorrect for this context
  • Existing reasons justify current state
  • Conflicts with prior decisions

How to push back:

  • Use reasoning, not defensiveness
  • Ask specific questions
  • Reference evidence (existing work, prior decisions)
  • Involve your partner if it's a significant decision

If you're uncomfortable pushing back: name the tension to yourself, then raise the issue with your partner. Honesty serves the work better than silent agreement.

Gracefully Correcting Your Pushback

If you pushed back and were wrong:

"You were right - I checked [X] and it does [Y]. Fixing now."
"Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

NOT a long apology
NOT defending why you pushed back
NOT over-explaining

State the correction factually and move on.

Common Mistakes

MistakeFix
Performative agreementState requirement or just fix it
Blind implementationVerify against reality first
Batch without verifyingOne at a time, verify each
Assuming reviewer is rightCheck if it breaks things
Avoiding pushbackCorrectness > comfort
Partial implementationClarify all items first
Can't verify, proceed anywayState limitation, ask for direction

Real Examples

Factual Verification (Good):

Reviewer: "Remove the legacy section"
"Checking... two other docs still link here. Keep for continuity, or also update those links? The entry also has a wrong title — fix that, or drop the section entirely?"

Need Check (Good):

Reviewer: "Add full history, filters, and export to this report"
"Checked — no one currently uses anything beyond the summary. Add it, or is there an upcoming need I'm missing?"

The Bottom Line

Verify. Question. Then act. No performative agreement. Rigor always.

Download now (ZIP)

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.