PR Walkthrough
kdlbs/kandev
Generate a single-file HTML walkthrough that explains a PR's purpose, user impact, interface changes, compatibility risks, and implementation.
Turns the current session's code changes into a Markdown walkthrough shown in a native Glimpse window, with highlighted code, rendered diffs and review feedback.
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cashew-labs/libretto glimpse-changes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/glimpse-changes .claude/skills/glimpse-changes && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .claude/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cashew-labs/libretto glimpse-changes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/glimpse-changes .agents/skills/glimpse-changes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .agents/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cashew-labs/libretto glimpse-changes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/glimpse-changes .cursor/skills/glimpse-changes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .cursor/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cashew-labs/libretto.git --path .agents/skills/glimpse-changes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cashew-labs/libretto glimpse-changes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/glimpse-changes .gemini/skills/glimpse-changes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .gemini/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cashew-labs/libretto glimpse-changesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/glimpse-changes .github/skills/glimpse-changes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .github/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cashew-labs/libretto --skill glimpse-changes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cashew-labs/libretto glimpse-changes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/glimpse-changes .opencode/skills/glimpse-changes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "glimpse-changes" agent skill from https://github.com/cashew-labs/libretto/tree/main/.agents/skills/glimpse-changes into .opencode/skills/glimpse-changes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "glimpse-changes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
glimpse-changesTurns the current session's code changes into a Markdown walkthrough shown in a native Glimpse window, with highlighted code, rendered diffs and review feedback.
Instead of handing you a plain text diff, the agent writes a short Markdown walkthrough of the changes and displays it in a native Glimpse window through the glimpse-changes command, run with npx. The window shows syntax-highlighted code and rendered diffs, using focused changes or diff blocks placed between paragraphs of explanation.
Most of the skill's text is about how to write the walkthrough: a specific title, a brief summary, an order chosen to explain the work rather than to mirror the diff, and prose about intent, tradeoffs and review risks, written the way one developer talks another through a change. Markdown is best piped over stdin with a quoted heredoc, without escaping backticks or dollar signs, and the command blocks until you close the window. Glimpse can also collect your review feedback.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 41ab782. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
npxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Glimpse Changes Walkthrough loads about 1.5k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 483 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from cashew-labs/libretto at commit 41ab782, republished under its MIT licence (© cashew-labs). 483 words, ~1,476 tokens.
.claude/skills/glimpse-changes/SKILL.md (or your agent's skills folder).Render a Markdown walkthrough in a native Glimpse window with syntax-highlighted code and rich diff rendering.
npx glimpse-changes@1.9.5 --helpUse Glimpse to walk another developer through the code in the clearest order, not necessarily the order files appear in the diff.
Aim for a short, reviewable document:
changes or diff blocks to explain intent, tradeoffs, and review risks.Prefer a narrative that follows the user or developer flow: what someone sees or does, how the request/state/data moves through the system, then any supporting helpers, tests, docs, or cleanup. If another order is clearer, use that instead.
Write like a developer walking another developer through the change. Be direct and specific. Avoid dumping one large diff with a generic explanation. Prefer smaller, focused sections when they help the reader understand the code.
Good explanation style:
Template:
# <Title>
## Summary
- <User-visible or developer-visible effect>
- <Main code path changed>
- <Important review note, risk, or edge case>
## <First thing a reviewer should understand>
Explain the intent and what to look for.
```changes
path/to/relevant-file.ts:20-70
```
## <Next part of the flow>
Explain how this connects to the previous step.
```changes
path/to/another-file.ts:80-130
```
## <Supporting detail, test, or edge case>
Explain why this support code matters.
```changes
path/to/test-file.test.ts:50-100
```Example:
cat <<'EOF' | npx glimpse-changes@1.9.5 -
# Improve review flow messaging
## Summary
- make the default review flow easier for agents to follow
- document when to wait for the user versus using background mode
- keep the walkthrough focused on the interaction reviewers care about
## Open the review and wait for the user
To make review sessions easier to follow, tell agents to open Glimpse, ask the
user to inspect it, and wait until the user says they are done.
```changes
packages/glimpse-changes/skills/glimpse-changes/SKILL.md:120-145
```
EOFExample with an ad-hoc fenced diff block:
cat <<'EOF' | npx glimpse-changes@1.9.5 -
# New utility module
## Summary
- Added a helper for computing hashes
## Hash helper
```diff
+++ src/utils/hash.ts
+import { createHash } from "node:crypto";
+
+export function shortHash(input: string): string {
+ return createHash("sha256")
+ .update("example:" + input)
+ .digest("hex")
+ .slice(0, 12);
+}
```
EOFPrefer piping markdown over stdin. This avoids shell-quoting issues.
cat report.md | npx glimpse-changes@1.9.5
cat report.md | npx glimpse-changes@1.9.5 -
cat <<'EOF' | npx glimpse-changes@1.9.5 -
# Title
Content
EOFImportant: Do NOT escape backticks or dollar signs inside <<'EOF' heredocs.
The single-quoted delimiter already prevents shell expansion. Escaping backticks
will break fence detection and produce garbled output instead of rendered diffs.
You can still pass a single inline markdown argument for simple content:
npx glimpse-changes@1.9.5 "# Title\n\nContent"The CLI opens a Glimpse window and blocks until closed.
Glimpse can also collect review feedback from the user.
Default interactive flow:
Use --background only when an asynchronous workflow is useful. In background
mode, the CLI prints a review file path. That file contains __PENDING__ until
the window is closed, then contains either the user's review text or a no-review
completion message.
npx glimpse-changes@1.9.5 --background "# Title\n\nContent"
# prints: Glimpse window opened. Read /tmp/glimpse-review-<id>.txt for user feedback.Use changes fenced code blocks to show diffs for real files. List paths
relative to the working directory. The renderer resolves old and new contents
from git automatically.
Show full file diffs:
```changes
src/db/queries.ts
src/db/schema.ts
```Focus on a line range:
```changes
src/config.ts:42-50
```Use one block for related files, or separate blocks with prose for a guided walkthrough:
The query layer now batches reads before returning results:
```changes
src/db/queries.ts:30-95
```
The schema adds the index that makes those batched reads efficient:
```changes
src/db/schema.ts:12-28
```The renderer handles new files, deleted files, and modified files. If a file cannot be resolved, it shows an error inline.
For ad-hoc illustrations not tied to real files, use diff fenced blocks with
literal +/-/ prefixed lines:
```diff
-removed line
+added line
context line
```You can also paste full unified diff output:
```diff
diff --git a/foo.txt b/foo.txt
--- a/foo.txt
+++ b/foo.txt
@@ -1,3 +1,3 @@
context
-old
+new
```Fenced code blocks with a language tag are syntax highlighted:
```js
const x = 1;
```© cashew-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/glimpse-changes of cashew-labs/libretto.
Open the folder on GitHubat commit 41ab782
Glimpse Changes Walkthrough next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Glimpse Changes Walkthrough this skillcashew-labs/libretto | 904 | — | ~1.5k | Automated safety check: Pass | MIT | |
| PR Walkthroughkdlbs/kandev | 909 | — | ~6.2k | Automated safety check: Pass | AGPL-3.0 | |
| PRP Companion PageWirasm/prp | 2.3k | — | ~990 | Automated safety check: Pass | MIT | |
| @pierre/diffs Code Renderingpierrecomputer/pierre | 6.2k | 2 repos | ~803 | Automated safety check: Pass | Apache-2.0 | |
| Frontend Code Reviewlanggenius/dify | 158k | — | ~938 | Automated safety check: Pass | Custom licence | |
| Archify Diagram BuilderUnclecheng-li/AI_Animation | 1.5k | 2 repos | ~4.1k | Automated safety check: Pass | MIT |
kdlbs/kandev
Generate a single-file HTML walkthrough that explains a PR's purpose, user impact, interface changes, compatibility risks, and implementation.
Wirasm/prp
Writes a self-contained HTML page beside a PRP plan or review that shows the diagram, steps, risks or findings, with a stable id on every item.
pierrecomputer/pierre
Guides an agent through using @pierre/diffs to render syntax-highlighted files and diffs, and to build editing and review surfaces in React or plain JavaScript.
langgenius/dify
Reviews frontend changes under `web/` or `packages/dify-ui/` for concrete defects and broken project contracts, using routed rule packs and a severity scale for findings.
Unclecheng-li/AI_Animation
Builds validated architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone interactive HTML from a small JSON spec, with optional motion and image export.
backnotprop/plannotator
Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.
cashew-labs/libretto
Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex.
cashew-labs/libretto
Works through the review comments on a pull request one by one: fetches the threads, makes the fixes, runs type-check, build and lint, pushes, and resolves the threads.
cashew-labs/libretto
Design rules for command-line tools: subcommand-scoped help, actionable success output, debuggable failures, stable output, meaningful exit codes and a --json mode.
cashew-labs/libretto
Drives desktop Electron apps already installed on your machine, such as Slack, Discord or VS Code, by relaunching them with a debugging port and using the Libretto CLI.
cashew-labs/libretto
Resolves Git merge, rebase and cherry-pick conflicts by reading the PRs behind each side, keeping both intents and asking you when they truly clash.
cashew-labs/libretto
Researches the codebase and relevant docs, asks clarifying questions, then writes a spec sheet in specs/ for a significant feature or complex fix.
Categories
Turns the current session's code changes into a Markdown walkthrough shown in a native Glimpse window, with highlighted code, rendered diffs and review feedback. Instead of handing you a plain text diff, the agent writes a short Markdown walkthrough of the changes and displays it in a native Glimpse window through the glimpse-changes command, run with npx. The window shows syntax-highlighted code and rendered diffs, using focused changes or diff blocks placed between paragraphs of explanation.
Glimpse Changes Walkthrough fits situations like: getting a visual walkthrough of local code changes before committing; reviewing an agent's session diff in a window instead of raw patch text; explaining a change to another developer in a readable order.
Run `npx skills add cashew-labs/libretto --skill glimpse-changes -a claude-code`. Or copy the skill folder (.agents/skills/glimpse-changes in cashew-labs/libretto) into .claude/skills/glimpse-changes in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cashew-labs/libretto --skill glimpse-changes -a codex`. Or copy the skill folder (.agents/skills/glimpse-changes in cashew-labs/libretto) into .agents/skills/glimpse-changes in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cashew-labs/libretto --skill glimpse-changes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/glimpse-changes, .gemini/skills/glimpse-changes, .github/skills/glimpse-changes and .opencode/skills/glimpse-changes in your project.
Going by SKILL.md and its folder, Glimpse Changes Walkthrough needs the command-line tools its instructions call (npx). Our summary lists: Node.js with npx to run glimpse-changes; A desktop session that can open a native window.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Glimpse Changes Walkthrough is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Glimpse Changes Walkthrough: PR Walkthrough (kdlbs/kandev, 909 stars), PRP Companion Page (Wirasm/prp, 2.3k stars), @pierre/diffs Code Rendering (pierrecomputer/pierre, 6.2k stars) and Frontend Code Review (langgenius/dify, 158k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cashew-labs (a GitHub organization) maintains it in cashew-labs/libretto, which has 904 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on August 21, 2026.
Source: cashew-labs/libretto on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.