explain-pr
Explain large or complex pull requests as a navigable HTML guide, tracing user journeys from entrypoints through changed code.
Skill by BetoFrega
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/betofrega-explain-pr
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/explain-pr
What's inside
- Skill name
explain-pr- Description
- Explain large or complex pull requests as a navigable HTML guide, tracing user journeys from entrypoints through changed code. Use when asked to understand a PR or build a guided walkthrough of its changes.
- License
- MIT
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- pr-explanation.html · assets/
SKILL.md (first lines)
# Explain a PR Deliver a portable HTML guide by journeys, weighted by significance, not line count; no size prerequisite. ## 1. Establish evidence Apply [simple-language](../simple-language/SKILL.md), including its self-check; if unavailable, ask its location before drafting. Identify reader/question, PR, base/head commits; default reader: product-familiar engineer unfamiliar with this change. Read linked issue/spec, description, complete file inventory/diff, and description screenshots with surrounding before/after/journey context. Match local sources to commits; distinguish diff baseline from target tip. Require reproducible comparison and sourced or explicitly unknown user need. Separate documented intent, observed implementation, inference. Inaccessible/truncated evidence requires named coverage gaps and a labeled partial explanation. ## 2. Trace journeys For every distinct behavior, trace scenario, entrypoint, decisions, transformations, side effects, visible outcome; verify connections through unchanged callers/dependencies. Trace lifecycle triggers for migrations/tooling/configuration. Follow authorization, validation, failure, retry, asynchronous branches. Show event/queue producer, payload, consumer, completion/failure signal as handoffs. Map every changed file to journey, cross-cutting change, tests, mechanical/generated changes, or unresolved evidence; group repetition. Finish with all files accounted for, sourced connections, and explicit uncertain edges. ## 3. Explain Lead with user need and concrete before/after; follow with main/independent journeys and cross-cutting changes. Explain responsibility, change, consequence; label existing/changed/added/removed behavior textually and visually. Use small clarifying excerpts; cite verified symbols/lines, preferably immutable base/head links. Validate URL schemes; HTML-escape source text. Place every description screenshot beside its demonstrated state/comparison/journey, preserving meaning/order. Provide alt text and captions separating visible evidence from PR claims; link the original description when possible. Screenshots support, not prove, implementation. Name inaccessible/redundant/sensitive/unrelated omissions. Use Mermaid sequences for calls/handoffs, flowcharts for decisions when useful: one question per diagram, verified arrows, textual equivalent. Source rationale or label inference. Close with tests (inspected, CI-reported, task-run distinguished), uncertainty, source reading route. Keep explanation/review separate; report concerns with evidence, without merge approval. Finish when readers can explain behavior, follow causes, locate code without reading the full diff. ## 4. Build and verify Copy [HTML template](assets/pr-explanation.html) as bundle-root `index.html`; replace examples, adapt journeys, language/title, synchronize navigation/IDs. Preserve inline CSS/narrative, pinned CDN renderer, accessible Mermaid source/textual fallback, adjacent citations, visible required narrative, expandable supporting evidence, responsive navigation, keyboard focus, diagram overflow, print styles. Use chosen destination or writable artifacts outside reviewed repository. Name directory for PR. Save screenshots under `assets/screenshots/` with stable descriptive names, source bytes/useful extensions where possible, relative HTML paths. No remote-image/absolute-path dependency; external caption citations are allowed. Check example residue, anchors, escaping, citations, screenshot coverage/distortion. Copy/move whole directory temporarily and open when possible: verify portable screenshots, desktop/mobile, details, diagrams/textual fallback with CDN unavailable. Check print before claiming PDF readiness; report unavailable checks. Apply [local document delivery](../consolidate/references/local-document-delivery.md) to actual destination. Deliver clickable `index.html`, directory, coverage statement. Zip/publish/post only when requested.
From BetoFrega/skills, MIT.
More from BetoFrega/skills
- 0.567score
grilling
BetoFrega
Clarify and stress-test a selected plan, decision, idea, or product increment through scoped interview rounds.
SkillAFreshness: AClaude Code +9 - 0.567score
code-review
BetoFrega
Review branch, PR, or in-progress changes from a commit, branch, tag, or merge-base across standards, spec, performance, observability, and accessibility.
SkillAFreshness: AClaude Code +9 - 0.567score
consolidate
BetoFrega
Consolidate canonical product knowledge, ideas, behavior, decisions, increments, and evidence; route technical decisions and reconcile delivery, exposure, and…
SkillAFreshness: AClaude Code +9 - 0.564score
diagnosing-bugs
BetoFrega
Diagnose hard bugs and performance regressions.
SkillAFreshness: AClaude Code +9 - 0.564score
autonomous-decisions
BetoFrega
Resolve a specified set of decisions through independent deliberation and evidence-based judgment.
SkillAFreshness: AClaude Code +9 - 0.561score
beto-mode
BetoFrega
Read first for multi-step, design, implementation, debugging, planning, or review work.
SkillAFreshness: AClaude Code +9 - 0.561score
esds-decompress
BetoFrega
Decompress ESDS payloads into compact human-readable text.
SkillAFreshness: AClaude Code +9 - 0.561score
advisory
BetoFrega
Consult for stalls, repeated errors, complex algorithms, unresolved cross-layer interactions, or consequential decisions, diagnoses, plans, and reviews.
SkillAFreshness: AClaude Code +9 - 0.561score
esds-compress
BetoFrega
Compress input using Exponential Semantic Density Scaling (ESDS).
SkillAFreshness: AClaude Code +9 - 0.561score
domain-modeling
BetoFrega
Build and sharpen domain terms and relationships, or write/edit the domain glossary in CONTEXT.md.
SkillAFreshness: AClaude Code +9 - 0.558score
implement-spec
BetoFrega
Implement an entire specification and its ticket graph as one PR.
SkillAFreshness: AClaude Code +9 - 0.556score
host-network
BetoFrega
Request host execution when sandbox network restrictions cause connection failures or misleading CLI authentication errors, including gh.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 10, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/BetoFrega/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from BetoFrega
- 0.567score
consolidate
BetoFrega
Consolidate canonical product knowledge, ideas, behavior, decisions, increments, and evidence; route technical decisions and reconcile delivery, exposure, and…
SkillAFreshness: AClaude Code +9 - 0.567score
grilling
BetoFrega
Clarify and stress-test a selected plan, decision, idea, or product increment through scoped interview rounds.
SkillAFreshness: AClaude Code +9 - 0.567score
code-review
BetoFrega
Review branch, PR, or in-progress changes from a commit, branch, tag, or merge-base across standards, spec, performance, observability, and accessibility.
SkillAFreshness: AClaude Code +9 - 0.564score
autonomous-decisions
BetoFrega
Resolve a specified set of decisions through independent deliberation and evidence-based judgment.
SkillAFreshness: AClaude Code +9 - 0.564score
diagnosing-bugs
BetoFrega
Diagnose hard bugs and performance regressions.
SkillAFreshness: AClaude Code +9 - 0.561score
advisory
BetoFrega
Consult for stalls, repeated errors, complex algorithms, unresolved cross-layer interactions, or consequential decisions, diagnoses, plans, and reviews.
SkillAFreshness: AClaude Code +9
Cite this page
explain-pr skill. Agent Mart. https://agentmart.dev/skills/betofrega-explain-pr (last updated 2026-10-24)