feedback-pedagogy

Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.

Best use case

feedback-pedagogy is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.

Teams using feedback-pedagogy should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/feedback-pedagogy/SKILL.md --create-dirs "https://raw.githubusercontent.com/organvm-iv-taxis/a-i--skills/main/distributions/claude/skills/feedback-pedagogy/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/feedback-pedagogy/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How feedback-pedagogy Compares

Feature / Agentfeedback-pedagogyStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Feedback Pedagogy

Transform feedback from judgment to learning opportunity.

## Feedback Philosophy

### Feedback vs Evaluation

| Evaluation | Feedback |
|------------|----------|
| Judges quality | Improves quality |
| Backward-looking | Forward-looking |
| "This is wrong" | "Here's how to improve" |
| Grade | Growth |

### Effective Feedback Is...

- **Specific**: Points to exact moments, not vague impressions
- **Actionable**: Gives clear next steps
- **Timely**: Close enough to remember context
- **Balanced**: Acknowledges strengths and growth areas
- **Goal-referenced**: Tied to learning objectives

---

## Written Feedback Framework

### The Feedback Sandwich (Use Sparingly)

```
Strength → Growth Area → Encouragement
```

Better: **Targeted feedback** that addresses what matters most.

### The 3-2-1 Model

```
3 things done well (specific examples)
2 areas for development (with suggestions)
1 question to consider (promotes reflection)
```

### Feedback Comment Types

| Type | Purpose | Example |
|------|---------|---------|
| **Praise** | Reinforce effective choices | "Your thesis clearly states your argument and previews your main points" |
| **Explanation** | Clarify why something matters | "Topic sentences help readers follow your logic" |
| **Suggestion** | Offer concrete improvement | "Try adding a transition here to connect these ideas" |
| **Question** | Prompt deeper thinking | "What evidence would strengthen this claim?" |
| **Reader response** | Share authentic reaction | "I got lost here—what's the main point?" |

### Prioritization

Don't mark everything. Focus on:

1. **Higher-order concerns first**
   - Thesis/argument
   - Organization/structure
   - Evidence/support
   - Analysis/development

2. **Then lower-order concerns**
   - Sentence clarity
   - Word choice
   - Grammar/mechanics
   - Formatting

### Comment Placement

| Location | Use For |
|----------|---------|
| Marginal | Specific, local issues |
| End note | Big-picture patterns, priorities |
| Rubric | Systematic criteria assessment |

---

## Rubric Design

### Rubric Types

| Type | Description | Best For |
|------|-------------|----------|
| **Holistic** | Single score, overall quality | Quick assessment, writing portfolios |
| **Analytic** | Separate scores per criterion | Detailed feedback, skill isolation |
| **Single-point** | Criteria list, no levels | Flexibility, avoiding "teaching to rubric" |

### Analytic Rubric Template

```markdown
## [Assignment Name] Rubric

| Criterion | Excellent (4) | Good (3) | Developing (2) | Beginning (1) |
|-----------|---------------|----------|----------------|---------------|
| Thesis | Clear, arguable, specific thesis that addresses prompt | Thesis present and mostly clear | Thesis unclear or too broad | No identifiable thesis |
| Evidence | Multiple relevant, well-integrated sources | Adequate evidence with some integration issues | Limited or poorly integrated evidence | Little to no evidence |
| Analysis | Sophisticated analysis connecting evidence to argument | Analysis present but could be deeper | Summary more than analysis | Minimal analysis |
| Organization | Clear structure with effective transitions | Mostly organized with some rough transitions | Disorganized or hard to follow | No discernible structure |
| Mechanics | Nearly error-free | Few errors that don't impede meaning | Errors sometimes impede meaning | Errors significantly impede meaning |

**Total: ___/20**
```

### Single-Point Rubric Template

```markdown
## [Assignment Name] Single-Point Rubric

| Areas for Growth | Criterion (Proficient) | Areas of Strength |
|------------------|------------------------|-------------------|
| [Space for feedback] | Clear thesis that takes a position | [Space for feedback] |
| [Space for feedback] | Evidence supports all major claims | [Space for feedback] |
| [Space for feedback] | Analysis explains how evidence proves thesis | [Space for feedback] |
| [Space for feedback] | Logical organization with transitions | [Space for feedback] |
| [Space for feedback] | Appropriate academic style | [Space for feedback] |
```

### Rubric Design Principles

- Align criteria with learning objectives
- Use observable, measurable language
- Avoid vague terms ("good," "adequate")
- Include descriptors at each level
- Share rubric with students BEFORE assignment

---

## Peer Review Facilitation

### Preparing Students

1. Model feedback using examples
2. Practice on anonymous samples
3. Provide structured protocols
4. Establish community norms

### Peer Review Protocol

```markdown
## Peer Review Guide

**Reader**: [Name]
**Writer**: [Name]

### First Read (Big Picture)
Read the whole piece without stopping. Note your overall impression.

- What is the main argument?
- What worked well?
- What confused you?

### Second Read (Detailed)
Answer these questions with specific examples:

1. **Thesis**: Can you identify the thesis? Is it arguable?
2. **Structure**: Does the organization make sense? Where did you get lost?
3. **Evidence**: Which evidence is most convincing? Where do you need more?
4. **Analysis**: Where could the writer dig deeper?

### Feedback Summary
- One thing that's working well:
- One thing to prioritize in revision:
- One question for the writer:
```

### Peer Review Norms

**Readers should**:
- Be specific (cite examples)
- Ask questions
- Suggest, don't command
- Focus on the writing, not the writer

**Writers should**:
- Listen without defending
- Ask clarifying questions
- Take notes
- Decide what feedback to use

---

## Verbal Feedback (Conferences)

### Conference Structure

```
1. Open: "What do you want me to focus on?"
2. Listen: Let student identify concerns
3. Prioritize: "Let's focus on X because..."
4. Demonstrate: Model revision strategy
5. Apply: Have student try it
6. Close: "What's your next step?"
```

### Questioning Techniques

| Instead of... | Try... |
|---------------|--------|
| "This is unclear" | "What do you mean here?" |
| "Add more detail" | "What else could you tell me about this?" |
| "This doesn't make sense" | "Walk me through your thinking here" |
| "You need a thesis" | "What's the main point you want readers to take away?" |

---

## Efficiency Strategies

### For Large Classes

- Use rubrics consistently
- Create comment banks for common issues
- Audio/video feedback (often faster than writing)
- Peer review for formative feedback
- Focus grading on selected criteria
- Grade samples, not everything

### Comment Bank Examples

```
THESIS ISSUES:
- "Your thesis tells me what the paper is about but doesn't take a position. 
   Try: 'Although X, Y because Z.'"
- "This thesis is too broad. Can you narrow to a specific aspect?"

EVIDENCE ISSUES:
- "Good evidence, but I need your analysis. What does this quote prove?"
- "This claim needs support. What source could back this up?"

ORGANIZATION:
- "Nice paragraph, but it might fit better after [section]. See what you think."
- "I need a transition here to understand how we got from A to B."
```

### Audio/Video Feedback

Benefits:
- Faster than writing (often 2-3x)
- Conveys tone better
- Feels more personal
- Can screencast while scrolling

Tips:
- Keep under 5 minutes
- Start with overview, then specifics
- Reference specific locations
- End with priorities

---

## Growth Mindset Language

| Fixed Mindset | Growth Mindset |
|---------------|----------------|
| "You're not good at this" | "This skill takes practice" |
| "This is wrong" | "This doesn't quite work yet" |
| "You don't understand" | "Let's work on understanding" |
| "Smart students get this" | "This is challenging for everyone" |

---

## References

- `references/rubric-templates.md` - Ready-to-use rubrics
- `references/comment-bank.md` - Reusable feedback comments
- `references/peer-review-protocols.md` - Peer review activities

Related Skills

taxonomy-modeling-design

5
from organvm-iv-taxis/a-i--skills

Phase 2 of the pentaphase structural-overhaul protocol. Classifies entities, standardizes attributes, establishes relationships, and designs the access framework. Use when the user invokes phase 2 of an overhaul, asks to "design the taxonomy" or "model the structure", or has completed a landscape audit and is ready to redesign. Consumes phase-1-landscape-report.md; produces phase-2-taxonomy-model.md.

systemic-ingestion-normalization

5
from organvm-iv-taxis/a-i--skills

Phase 4 of the pentaphase structural-overhaul protocol. Purges redundancies, enriches and aligns legacy entities to the new schema, executes phased ingestion into the new environment, and audits integrity. Use when the user invokes phase 4 of an overhaul, asks to "migrate the data" or "ingest into the new system", or has a configured environment ready to accept legacy entities. Consumes phase-3-environment-spec.md; produces phase-4-ingestion-report.md.

system-environment-configuration

5
from organvm-iv-taxis/a-i--skills

Phase 3 of the pentaphase structural-overhaul protocol. Translates the taxonomy model into objective technical criteria, evaluates candidate mechanisms or frameworks, instantiates the chosen architecture, and programs validation rules. Use when the user invokes phase 3 of an overhaul, asks to "select a system" or "configure the environment", or has a taxonomy model and is ready to choose technology. Consumes phase-2-taxonomy-model.md; produces phase-3-environment-spec.md.

pentaphase-orchestrator

5
from organvm-iv-taxis/a-i--skills

Threads the full five-phase structural-overhaul protocol — landscape discovery, taxonomy design, environment configuration, systemic ingestion, governance evolution — for any substrate the user names. Use when the user requests a structural overhaul, system redesign, or end-to-end restructuring of a documentation system, asset registry, code monorepo, knowledge base, or operational workflow; or when they explicitly invoke the pentaphase methodology. Coordinates handoffs between phase-skills and seats validation gates between phases.

landscape-discovery-audit

5
from organvm-iv-taxis/a-i--skills

Phase 1 of the pentaphase structural-overhaul protocol. Inventories assets, maps current flow, identifies friction, and defines value metrics for any substrate. Use when the user invokes phase 1 of an overhaul, requests a baseline audit, asks to "discover the landscape" of a system, or wants to understand current state before redesigning. Produces phase-1-landscape-report.md.

governance-evolution-protocol

5
from organvm-iv-taxis/a-i--skills

Phase 5 of the pentaphase structural-overhaul protocol. Codifies operational protocols, onboards the ecosystem of participants, programs behavior monitoring, and establishes an iteration cadence so the substrate evolves rather than calcifies. Use when the user invokes phase 5 of an overhaul, asks to "establish governance" or "lock in the protocols", or has completed ingestion and is ready to declare the substrate operational. Consumes phase-4-ingestion-report.md; produces phase-5-governance-charter.md, which closes the protocol.

dimension-surfacing

5
from organvm-iv-taxis/a-i--skills

Surfaces the parallel domain dimensions implicit in a dense or minimal prompt. Use when a user prompt is small on the surface but plainly implies multiple independent domains needing different expertise; when explicitly invoked by the coliseum-orchestrator skill as Phase 1; or when the user asks "what dimensions does this prompt encode" or "what axes does this break into." Produces a named dimension set where each dimension is independently executable and not a paraphrase of another.

coliseum-dispatch

5
from organvm-iv-taxis/a-i--skills

Dispatches a composed set of assignment envelopes to domain-expert subagents in parallel, in a single message with multiple Agent tool calls. Enforces the no-pingpong gate via the pingpong-detector agent before any dispatch fires. Use when invoked by the coliseum-orchestrator as Phase 3; when envelopes are already composed and the next step is parallel execution; or when the user asks to "fan out" or "dispatch in parallel." Produces a dispatch log capturing what was sent, when, and where returns land.

assignment-composition

5
from organvm-iv-taxis/a-i--skills

Wraps each surfaced dimension as a self-contained 9-section autonomous-work-assignment envelope — scope, context, success criteria, allowed tools, return format, handoff — all the recipient subagent needs to execute without coming back. Use when invoked by coliseum-orchestrator as Phase 2; when dimensions are named and the next step is to make each independently dispatchable; or when the user asks "compose this as an assignment." The no-pingpong gate validates each envelope before dispatch.

workspace-autopsy-governance

5
from organvm-iv-taxis/a-i--skills

Conducts a full automated autopsy of the current workspace directory to map files, identifies structural issues, proposes a restructuring plan (the signal), and establishes unified governance using templates. Use this skill when a user asks to map, restructure, reorganize, or apply new governance to an existing messy repository.

workshop-presentation-design

5
from organvm-iv-taxis/a-i--skills

Design engaging workshops, conference talks, and educational presentations. Covers learning objectives, activity design, slide craft, and facilitation techniques. Triggers on workshop design, presentation prep, talk structure, or training session requests.

webhook-integration-patterns

5
from organvm-iv-taxis/a-i--skills

Designs reliable webhook systems with proper delivery guarantees, retry logic, signature verification, and idempotent processing for event-driven integrations.