learn-from-pr

learn-from-pr is a skill for Claude Code, Codex from dotnet/maui. It costs 58 tokens per session (2,173 once invoked), scanned A, original, MIT.

A post-PR review that examines how a coding agent worked during a completed pull request, or PR—a proposed set of code changes. It produces lessons about what happened and recommendations for instructions, skills, and documentation.

In plain words
What is it for?
Use it after an agent-involved PR to compare the attempted fix with the actual fix, identify failure patterns, and record concrete improvements.
Why use it?
It helps explain failed attempts, slow progress, or successful patterns that are otherwise easy to overlook after a PR is merged or finished.

Skill for Claude CodeCodex

About the project

.NET MAUI is a C# and XAML framework for building native mobile and desktop applications from one shared codebase. Developers use it to create apps for Android, iOS, iPadOS, macOS, and Windows. The catalogue entries provide skills, instructions, and agents for working with .NET MAUI.

dotnet/maui · 23,317 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dotnet/maui/learn-from-pr
Any agent
npx skills add dotnet/maui --skill learn-from-pr
Clone the repo
git clone --depth 1 https://github.com/dotnet/maui

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for learn-from-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/dotnet/maui/learn-from-pr.svg)](https://agentmods.dev/skills/dotnet/maui/learn-from-pr)
Your own site
<a href="https://agentmods.dev/skills/dotnet/maui/learn-from-pr"><img src="https://agentmods.dev/badge/skills/dotnet/maui/learn-from-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.02173
Opus 5 $0.00029 $0.01086
Sonnet 5 $0.00012 $0.00435
Haiku 4.5 $0.00006 $0.00217

Measured 5d ago against content hash a469a3c25050, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-from-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/learn-from-pr/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn From PR

Extracts lessons learned from a completed PR to improve repository documentation and agent capabilities.

Inputs

Input Required Source
PR number or Issue number Yes User provides (e.g., "PR #33352" or "issue 33352")

Outputs

  1. Learning Analysis - Structured markdown with:

    • What happened (problem, attempts, solution)
    • Fix location analysis (attempted vs actual)
    • Failure modes identified
    • Prioritized recommendations
  2. Actionable Recommendations - Each with:

    • Category, Priority, Location, Specific Change, Why It Helps

Completion Criteria

The skill is complete when you have:

  • Gathered PR diff and metadata
  • Analyzed fix location (attempted vs actual)
  • Identified failure modes
  • Generated at least one concrete recommendation
  • Presented findings to user

When to Use

  • After agent failed to find the right fix
  • After agent succeeded but took many attempts
  • After agent succeeded quickly (to understand what worked)
  • When asked "what can we learn from PR #XXXXX?"

When NOT to Use

  • Before PR is finalized (use pr-finalize first)
  • For trivial PRs (typo fixes, simple changes)
  • When no agent was involved (nothing to analyze)

Workflow

Step 1: Gather Data

# Required: Get PR info
gh pr view XXXXX --json title,body,files
gh pr diff XXXXX

Analyze the PR to extract learning:

  1. PR discussion - Comments reveal what was tried
  2. Commit history - Multiple commits may show iteration
  3. Code complexity - Non-obvious fixes suggest learning opportunities
  4. Similar past issues - Search for related bugs

Focus on: "What would have helped an agent find this fix faster?"

Step 2: Fix Location Analysis

Critical question: Did agent attempts target the same files as the final fix?

# Where did final fix go?
gh pr view XXXXX --json files --jq '.files[].path' | grep -v test
Scenario Implication
Same files Agent found right location
Different files Major learning opportunity - document why

Read the full file on GitHub · 277 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 277 lines · 58 tokens per session scan A a469a3c25050

Subscribe to this mod's changes

learn-from-pr is a skill published in the GitHub repository dotnet/maui (23,317 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 2,173 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dpg-migration

Migration logic for Azure SDK for .NET data-plane libraries migrating from AutoRest/Swagger to TypeSpec-based generation. Uses MCP tools from the generator-agent server for automated deterministic fixes.

Azure/azure-sdk-for-net · 41 tokens

csharp-azure-spector-coverage-gaps

Discovers and implements gaps in Spector test coverage for the Azure C# HTTP client emitter. Use when asked to find missing Spector scenarios, add Spector test coverage, or implement a specific Spector spec for the Azure C# emitter. Can also compare coverage between the Azure dashboard and the Standard (TypeSpec core)…

Azure/azure-sdk-for-net · 78 tokens

auto-build-repair

Headless, bounded repair of custom-code build failures in an already-generated Azure SDK PR. Thin wrapper over the shared azure-sdk-mcp:azsdkcustomizedcodeupdate engine in custom-code-only scope (editScope: CustomCode); the skill owns the iterate-until-green loop, capped by a per-language maxIterations read from…

Azure/azure-sdk-for-net · 149 tokens

azure-sdk-mgmt-pr-review

Review Azure SDK management-plane pull requests, check naming conventions, API compatibility, and code quality.

Azure/azure-sdk-for-net · 26 tokens

mgmt-review-comment-resolution

Resolve review comments on Azure management-plane .NET SDK PRs. Handles renaming types/properties, changing property types, and other API surface adjustments by updating TypeSpec client.tsp and regenerating.

Azure/azure-sdk-for-net · 46 tokens

mitigate-breaking-changes

Patterns and techniques for mitigating breaking changes in Azure management-plane SDKs. Covers SDK-side customizations (partial classes, CodeGenType, CodeGenSuppress) and TypeSpec decorator customizations (clientName, access, markAsPageable, alternateType, hierarchyBuilding).

Azure/azure-sdk-for-net · 60 tokens