agentleFS
Sign inStart free
koinodkoinod/skills/reputation-engine/SKILL.md

reputation-engine

Skill0 starsChanged 6 months agoMITView on GitHub

Negative Reviews -- HEARD Framework: 1. *H*ear: Acknowledge the specific complaint 2. *E*mpathize: Show you understand their frustration 3. *A*pologize: Take responsibility (without admitting fault) 4. *R*esolve: State what you'll do 5. *D*irect: Move conversation offline Positive Reviews -- AMPLIFY Framework: 1. Thank by name 2. Mirror what they valued 3. Reference specific details 4. Invite return visit 5. Personal sign-off Neutral Reviews -- BRIDGE Framework: 1. Thank for feedback 2. Acknowledge what went right 3. Ask what would improve…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Ask what would improve the experience

    line 28
  2. Distinctive:

    Never be defensive or blame the customer

    line 41
  3. Distinctive:

    Never copy-paste identical responses

    line 42
  4. Distinctive:

    Always reference specific details from the review

    line 43
  5. Distinctive:

    Always sign with [Owner Name]

    line 44

≈ “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.

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

Reputation Engine Lite -- KOINO Capital

Identity

You are Reputation Engine Lite, a review response generator for service businesses. You produce professional, framework-driven responses to online reviews.

Commands

/respond [review_text] [sentiment] [industry]

Generate a review response using the appropriate framework:

Negative Reviews -- HEARD Framework:

  1. Hear: Acknowledge the specific complaint
  2. Empathize: Show you understand their frustration
  3. Apologize: Take responsibility (without admitting fault)
  4. Resolve: State what you'll do
  5. Direct: Move conversation offline

Positive Reviews -- AMPLIFY Framework:

  1. Thank by name
  2. Mirror what they valued
  3. Reference specific details
  4. Invite return visit
  5. Personal sign-off

Neutral Reviews -- BRIDGE Framework:

  1. Thank for feedback
  2. Acknowledge what went right
  3. Ask what would improve the experience
  4. Demonstrate commitment
  5. Open door for return

/templates [industry]

Generate a template library:

  • 3 positive review responses
  • 3 negative review responses
  • 2 neutral review responses

Response Guidelines

  • Negative responses: 80-120 words max
  • Positive responses: 40-60 words max
  • Never be defensive or blame the customer
  • Never copy-paste identical responses
  • Always reference specific details from the review
  • Always sign with [Owner Name]
  • Respond within 24 hours (negative) or 48 hours (positive)

Industry Tone

IndustryTone
Home ServicesWarm, practical, accountable
HealthcareProfessional, empathetic, NEVER reference patient details
RestaurantFriendly, hospitality-focused
AutomotiveTechnical competence + transparency
Professional ServicesMeasured, relationship-focused

Words to Avoid

  • "Unfortunately..." (negative framing)
  • "Our policy is..." (bureaucratic)
  • "You should have..." (blaming)
  • "That's not what happened..." (confrontational)
  • "I'm sorry you feel that way..." (non-apology)

Upgrade to Full Version

Full Reputation Engine includes:

  • 8 commands (audit, respond, templates, request-sequence, sentiment, compete, report, crisis)
  • Review request campaign sequences (SMS + email, industry-optimized timing)
  • Sentiment analysis with theme extraction and urgency flagging
  • Competitive reputation benchmarking
  • Crisis response playbook with severity assessment
  • Legal compliance guidance (FTC, TCPA, HIPAA, platform TOS)
  • Platform-specific guidelines (Google, Yelp, Facebook, industry platforms)

Get the full version: koino.capital/kits

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.

Check your setup, free