Giving Feedback logo

Giving Feedback

Community
fatihguner
giving-feedback

Structures effective feedback conversations using the Situation-Behaviour-Impact (SBI) model from the Center for Creative Leadership. Separates observable behavior from interpretation, anchors feedback in specific situations, and articulates concrete impact. Use when preparing difficult performance conversations, constructing precise positive or corrective feedback, training first-time managers in feedback delivery, redesigning performance review systems, or building an organizational feedback culture.

Overview

Publisherfatihguner
Repositoryforeman
Skill namegiving-feedback
Stars
63
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by fatihguner on GitHub. Read the source before you install it.

Installation

Install the Giving Feedback AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/fatihguner/foreman/tree/main/plugins/foreman/skills/giving-feedback
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fatihguner/foreman.git /tmp/foreman
mkdir -p .claude/skills
cp -r /tmp/foreman/plugins/foreman/skills/giving-feedback .claude/skills/giving-feedback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Giving Feedback in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Giving Feedback on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Giving Feedback is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.

Giving Feedback

Here is an uncomfortable truth: most of the feedback you have given in your career has been useless. Not malicious, not even poorly intentioned -- simply useless. "Great job on that presentation" teaches nothing. "You need to be more strategic" is a Rorschach test, not guidance. "I'm disappointed in your performance this quarter" is an emotional discharge dressed as management. The receiver walks away knowing something happened but unable to extract a single actionable insight. Meanwhile, the giver checks "gave feedback" off their mental list and wonders why nothing changes.

The problem is structural, not motivational. Most people want to give good feedback. They simply lack a method. The Situation-Behaviour-Impact (SBI) model, developed by the Center for Creative Leadership, provides exactly that: a rigorous structure that strips feedback of vagueness, projection, and judgment while preserving its essential content. SBI does not make difficult conversations easy. It makes them effective.


The Framework

The SBI Model: Three Components

Effective feedback consists of three elements, delivered in sequence. Each element serves a specific function, and omitting any one of them degrades the feedback's utility.

S -- Situation

Anchor the feedback in a specific time, place, and context. This eliminates ambiguity and prevents the receiver from wondering "which time?" or "what do you mean?"

  • Weak: "In meetings, you tend to..."
  • Strong: "In yesterday's product review meeting, when we were discussing the Q2 roadmap..."

The situation establishes shared ground. Both parties can agree on when and where the event occurred.

B -- Behaviour

Describe the observable behaviour -- what the person did, not what you infer about their character, motivation, or intelligence. Behaviour is factual and disputable; interpretation is subjective and inflammatory.

  • Weak: "You were disrespectful to Sarah."
  • Strong: "You interrupted Sarah three times while she was presenting her analysis, and on the third interruption you said, 'We've heard enough on this.'"

The discipline of describing behaviour rather than attributing motive is the hardest part of SBI. It requires the feedback giver to separate observation from judgment -- a distinction that is conceptually simple and practically demanding.

I -- Impact

Articulate the effect the behaviour had -- on you, on others, on the project, or on the organisation. Impact connects behaviour to consequences, transforming feedback from a personal opinion into a business-relevant observation.

  • Weak: "That was unprofessional."
  • Strong: "When you interrupted Sarah, she stopped contributing for the rest of the meeting. We lost her perspective on the technical feasibility assessment, and the team left without addressing a risk she had identified."

The Complete SBI Statement

Assembling the three components:

"In yesterday's product review meeting [Situation], when you interrupted Sarah three times and said 'we've heard enough' [Behaviour], she stopped contributing for the rest of the meeting, and we missed her perspective on a technical risk that could affect the Q2 timeline [Impact]."

No labels. No character judgments. No vague generalities. The receiver knows exactly what happened, what they did, and why it matters.

Extending SBI: The SBI-I Variant

Some practitioners add a fourth element -- Intent inquiry -- transforming SBI into SBI-I:

"...I want to understand your perspective. What was going on for you in that moment?"

This addition shifts the interaction from monologue to dialogue. It acknowledges that the feedback giver may have incomplete information. Perhaps the interruption was prompted by a time constraint the giver did not know about. The intent inquiry preserves the directness of SBI while opening space for the receiver's context.

SBI for Positive Feedback

SBI is not exclusively a tool for criticism. Praise benefits equally from specificity:

"In Friday's client call [Situation], when the client challenged our pricing model and you walked them through the ROI calculation using their own data [Behaviour], the client's tone shifted entirely -- they moved from objecting to asking about implementation timelines [Impact]."

Compare this with "Great job on the client call." The SBI version reinforces the specific behaviour that produced the result, making it far more likely to be repeated.

The Feedback Delivery Sequence

  1. Prepare. Write out the SBI components before the conversation. Rehearse if necessary. Precision under emotional pressure requires preparation.
  2. Set context. "I have some feedback I'd like to share. Is this a good time?" Consent matters; ambush feedback triggers defence rather than reflection.
  3. Deliver the SBI statement. Say it once, clearly, without hedging.
  4. Pause. Silence is essential. The receiver needs time to process.
  5. Listen. If using SBI-I, invite their perspective. Resist the urge to rebut.
  6. Agree on forward action. "What would you like to do differently next time?" or "How can I support you in changing this?"
  7. Follow up. Acknowledge improvement when you see it. Feedback without follow-up signals that the conversation was not important.

Prompts

Prompt 1 -- SBI Construction:

I need to give feedback to [person/role] about [describe the situation]. Help me construct a precise SBI statement by separating the situation (when and where), the behaviour (what they did, observably), and the impact (the effect on the team, project, or business). Ensure the behaviour description contains no interpretive language -- only observable actions and direct quotes where available.

Prompt 2 -- Feedback Pattern Analysis:

Here are five pieces of feedback I have recently given to my team: [list them]. Analyse each against the SBI model. Identify which ones lack a clear situation, which conflate behaviour with interpretation, and which omit impact. Then rewrite each as a proper SBI statement.

Prompt 3 -- Difficult Feedback Preparation:

I need to address a sensitive performance issue with [describe person and context]. The issue involves [describe]. I am nervous about this conversation because [describe your concern -- damaging the relationship, triggering a defensive response, etc.]. Help me prepare a complete SBI statement and a conversation plan, including: how to open, what to say, how to handle likely defensive responses, and how to close with a forward-looking action plan.

Prompt 4 -- Positive Feedback Architecture:

I want to build a habit of giving specific positive feedback to my team of [size]. For the past week, I have noticed these contributions: [list 3-5 things team members did well]. Help me craft SBI-format positive feedback for each one, ensuring the behaviour is specific enough to be repeatable and the impact is concrete enough to demonstrate why their contribution mattered.

Prompt 5 -- Feedback Culture Kickstart:

My company of [size] has no structured feedback practice. People either avoid feedback entirely or deliver it vaguely during annual reviews. Design a lightweight feedback programme built on the SBI model that includes: a 30-minute training session outline, a feedback template for managers, a weekly or bi-weekly feedback ritual, and a way to measure whether feedback quality improves over 90 days.


Use Cases

Validation-Stage Startup with Two Cofounders The CEO cofounder needs to address the CTO cofounder's habit of committing to deadlines in customer meetings that engineering cannot meet. Rather than the usual passive-aggressive tension ("we need to manage expectations better"), the CEO constructs an SBI statement: "In Tuesday's demo with Acme Corp [Situation], you told them we'd have the API integration ready in two weeks [Behaviour]. The engineering team estimates six weeks, which means we either disappoint the client or burn out the team to hit an unrealistic date -- and this is the third time this quarter it has happened [Impact]." The specificity transforms a recurring frustration into a solvable problem.

Growth-Stage Manager Giving First-Time Feedback to a Senior Hire A newly promoted engineering manager must address code quality issues with a senior engineer who has more experience than they do. The power dynamic makes vague feedback ("your code could be cleaner") dangerous -- the senior hire will dismiss it. SBI equalises the interaction: "In the PR you submitted yesterday for the payment processing module [Situation], there were no unit tests for the edge cases we identified in the design review, and the error handling returned generic 500 responses without logging [Behaviour]. Two of those edge cases caused production incidents in a similar module last month, and without specific error codes, debugging takes three times as long [Impact]." The feedback is inarguable because it is grounded in fact.

Scale-Stage Company Running Annual Performance Reviews A 400-person company replaces its ineffective annual review process (generic ratings on a 1-5 scale with subjective commentary) with an SBI-based system. Managers are required to provide three SBI-positive and two SBI-developmental examples per review. Calibration sessions across management levels ensure that "exceeds expectations" is supported by specific behavioural evidence, not general impressions. Review quality, measured by employee satisfaction surveys, increases 35% in the first cycle.


Anti-Patterns

  1. The Feedback Sandwich. Positive-negative-positive. The structure is so well-known that it has become a psychological signal meaning "brace yourself, the middle part is what they actually think." Recipients learn to ignore the bread and dread the filling. SBI does not require sandwiching; it requires clarity.

  2. Behaviour-as-Interpretation. "In the meeting, you were passive-aggressive" is interpretation, not behaviour. "In the meeting, you rolled your eyes when I presented the budget and said 'sure, whatever you think'" is behaviour. The distinction determines whether feedback produces insight or defensiveness.

  3. Stockpiling. Saving feedback for a quarterly review rather than delivering it within 48 hours of the event. Delayed feedback loses context, accumulates emotional charge, and overwhelms the receiver with a catalogue of grievances they can no longer recall clearly enough to address.

  4. Impact Inflation. Exaggerating the impact to make the feedback feel more important. "Your typo in the client email could have cost us the entire account" -- could it? Really? Impact inflation erodes trust. State the actual impact, neither minimised nor inflated.

  5. Monologue Feedback. Delivering the SBI statement and immediately moving on without pausing for the receiver's response. Feedback is a dialogue. The SBI statement opens the conversation; it does not constitute the conversation.


By Stage

StageFocusKey Difference
ValidationCofounder feedbackAt the earliest stage, feedback flows between two or three people with no managerial hierarchy. SBI provides structure for peer feedback where "pull rank" is not an option.
Early TractionFirst-time managersNew managers need a concrete method. SBI is the simplest and most immediately applicable feedback framework -- a tool they can use in their first week as a manager.
GrowthFeedback consistency across teamsDifferent managers give feedback differently. SBI provides a common language and structure that ensures minimum feedback quality across the growing management layer.
ScaleInstitutional feedback systemsAt scale, SBI becomes embedded in performance review templates, 360-degree review tools, and manager training programmes. The framework becomes organisational infrastructure rather than individual practice.

Output Template

markdown
# Feedback Preparation: [Recipient Name/Role]

## SBI Statement
- **Situation:** [When and where -- specific date, meeting, context]
- **Behaviour:** [What they did -- observable actions only, no interpretation]
- **Impact:** [Effect on team, project, business, or individuals]

## Complete Statement (Draft)
"[Assembled SBI statement, ready to deliver]"

## Conversation Plan
- **Opening:** [How you will set context and ask for permission]
- **Delivery:** [The SBI statement]
- **Pause and listen:** [Expected response and how you will handle it]
- **Intent inquiry (optional):** "What was your perspective on that moment?"
- **Forward action:** [What change you are requesting and what support you will offer]
- **Follow-up plan:** [When and how you will check in on progress]

## Defensive Response Preparation
| Likely Response | Your Approach |
|-----------------|---------------|
| Denial ("That didn't happen") | [Return to observable facts] |
| Deflection ("Everyone does that") | [Refocus on specific impact] |
| Counter-attack ("Well, you...") | [Acknowledge, redirect to the topic] |
| Emotion (tears, anger) | [Pause, express care, offer to continue later] |

Related Skills

  • Radical Candor -- Radical Candor provides the philosophical foundation for why direct feedback matters; SBI provides the mechanical structure for how to deliver it effectively.
  • Trust Equation -- The denominator of the trust equation (self-orientation) directly affects whether feedback is received as helpful or self-serving.
  • Thomas-Kilmann Conflict -- Feedback conversations often trigger conflict; understanding conflict modes helps the giver navigate defensive responses and choose the right approach.
  • GROW Model -- After SBI identifies the issue, GROW provides a coaching framework for developing the forward-looking action plan with the recipient.
  • Psychological Safety -- Edmondson's safety conditions determine whether feedback is received as developmental input or perceived as threat, making safety a prerequisite for effective SBI delivery.
  • Writing Performance Reviews -- Translates the SBI discipline into written form for formal review processes, ensuring documented feedback is equally specific and actionable.

Frequently asked questions

What does the Giving Feedback AI skill do?

Structures effective feedback conversations using the Situation-Behaviour-Impact (SBI) model from the Center for Creative Leadership. Separates observable behavior from interpretation, anchors feedback in specific situations, and articulates concrete impact. Use when preparing difficult performance conversations, constructing precise positive or corrective feedback, training first-time managers in feedback delivery, redesigning performance review systems, or building an organizational feedback culture.

Why use Giving Feedback on TypingMind?

Because you install it once and use it with any model. Giving Feedback is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Giving Feedback in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fatihguner/foreman/tree/main/plugins/foreman/skills/giving-feedback. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Giving Feedback?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Giving Feedback?

As many as you like. As long as a model supports skills, you can use Giving Feedback with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Giving Feedback AI skill free?

Yes. It is published on GitHub by fatihguner under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇