Agent skill

Run Summary

Summarize the architecture of code generated by a single retort run.

Apache-2.0Auto-check passed

Install Run Summary

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install adrianco/retort run-summary --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/run-summary .claude/skills/run-summary && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .claude/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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

$skill-installer install https://github.com/adrianco/retort/tree/main/skills/run-summary

Type 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.

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install adrianco/retort run-summary --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/run-summary .agents/skills/run-summary && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .agents/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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.

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install adrianco/retort run-summary --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/run-summary .cursor/skills/run-summary && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .cursor/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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

$ gemini skills install https://github.com/adrianco/retort.git --path skills/run-summary

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install adrianco/retort run-summary --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/run-summary .gemini/skills/run-summary && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .gemini/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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.

GitHub CLI

$ gh skill install adrianco/retort run-summary

Installs 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).

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/run-summary .github/skills/run-summary && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .github/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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.

skills CLI

$ npx skills add adrianco/retort --skill run-summary -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install adrianco/retort run-summary --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adrianco/retort.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/run-summary .opencode/skills/run-summary && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "run-summary" agent skill from https://github.com/adrianco/retort/tree/main/skills/run-summary into .opencode/skills/run-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-summary", 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.

Facts

Skill name: run-summary
GitHub stars: 207
Token cost: ~1.3k tokens
SKILL.md length: 411 words
Files: 1
Skills in repo: 6
Repo updated: Oct 9, 2026
First seen: Oct 8, 2026
Licence: Apache-2.0

At a glance

Summarize the architecture of code generated by a single retort run.

Works in 4 steps: Infer the surface → Map the modules → Describe the interfaces → …
SKILL.md covers Overview, Parameters, Steps and Constraints Summary, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Run Summary is an agent skill from adrianco/retort. Summarize the architecture of code generated by a single retort run. Produces module-level structure, interfaces, and control flow in a form suitable for cross-run comparison — not a full codebase-summary.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Platform Evolution Engine. Distill the best from the combinatorial mess. The licence is Apache-2.0.

Example prompts

“/run-summary”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Infer the surface
Map the modules
Describe the interfaces
Trace the dominant control flow

What it can do on your machine

Read from SKILL.md and the folder at commit 1f75769. It shows what the files ask for, not the result of running them.

Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Run Summary loads about 1.3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 411 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~54
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from adrianco/retort at commit 1f75769, republished under its Apache-2.0 licence (© adrianco). 411 words, ~1,309 tokens.

Download SKILL.mdSave it as .claude/skills/run-summary/SKILL.md (or your agent's skills folder).

name: run-summary
description: Summarize the architecture of code generated by a single retort run. Produces module-level structure, interfaces, and control flow in a form suitable for cross-run comparison — not a full codebase-summary.
type: anthropic-skill
version: 1.0

Run Summary

Overview

Retort runs produce small, single-task codebases (one REST API, one CLI, one service). Full codebase-summary treatment is overkill — but a consistent lightweight summary per run is exactly what makes cross-run comparison useful.

This skill is an intentionally scoped-down adaptation of pourpoise's codebase-summary. It runs in seconds, not minutes, and emits only what's useful when comparing 48+ small generated projects.

Parameters

codebase_path (required): The run directory (same as evaluate-run's run_dir)
output_dir (optional, default: {codebase_path}/summary): Where to write the summary files

Steps

1. Infer the surface

Read TASK.md to understand what the code is supposed to do — the "surface" of the project. One paragraph, no judgments.

2. Map the modules

Generate {output_dir}/modules.md:

markdown

# Modules

| Path | Purpose | Entry points |
|------|---------|--------------|
| src/app.py | HTTP server, route handlers | `app`, `create_app()` |
| src/models.py | SQLAlchemy models | `Book`, `Base` |
| src/db.py | Connection + migrations | `get_engine()` |
| tests/test_app.py | API integration tests | 8 test functions |

Constraints:

You MUST list every non-generated source file (skip node_modules, target, __pycache__, .git, lock files, build artifacts).
The "Purpose" column is one line extracted from the code, not invented.
The "Entry points" column is the publicly-named functions, classes, or exported symbols — not every local helper.

3. Describe the interfaces

Generate {output_dir}/interfaces.md covering what the code exposes:

HTTP routes (method, path, short description)
CLI commands (subcommand + flags)
Library API (exported classes/functions)
Data schemas (tables, message formats)

Example:

markdown

# Interfaces

## HTTP routes

| Method | Path | Returns | Handler |
|--------|------|---------|---------|
| GET | /books | `[Book]` | `app.py:list_books` |
| POST | /books | `Book` | `app.py:create_book` |
| GET | /books/{id} | `Book \| 404` | `app.py:get_book` |

## Data schema

`books` table: id (int, pk), title (str), author (str), year (int).

Constraints:

You MUST grep / static-analyze the code rather than execute it to discover interfaces.
You MUST NOT invent endpoints the code doesn't actually declare.
If the code has none of the above categories, write (none) under that heading.

Show full SKILL.md (184 more words)Show less

4. Trace the dominant control flow

Generate {output_dir}/flow.md with one Mermaid diagram showing the happy-path request/response for the main feature, plus a one-paragraph narration.

markdown

# Flow

```mermaid
sequenceDiagram
    Client->>app.py: GET /books
    app.py->>db.py: get_session()
    db.py-->>app.py: Session
    app.py->>Book: query.all()
    Book-->>app.py: [Book]
    app.py-->>Client: 200 {json}

A request to GET /books opens a DB session via db.py:get_session(), queries all Book rows, and returns them as JSON. No pagination, no filtering.


Constraints:
- You MUST pick the single most representative flow — the one a user of the generated code would hit first.
- You MUST note deviations from common patterns ("no input validation", "no error handling", "synchronous DB access in async handler").
- The narration MUST be factual, not prescriptive.

### 5. Write the index

Generate `{output_dir}/index.md` linking to the other three files and giving a 3–4 bullet summary:

```markdown
# Summary: {cell_name} · rep {replicate}

- **Shape:** {one-line description — "Flask REST API with SQLAlchemy", "Go net/http CRUD with in-memory store", etc.}
- **Structure:** {n} modules, {n} test files
- **Interfaces:** {n} HTTP routes / {n} CLI commands / {n} exported functions
- **Notable:** {what stands out — simplest/most-complex approach seen, unusual library choice, etc.}

See [modules.md](modules.md), [interfaces.md](interfaces.md), [flow.md](flow.md).

Constraints Summary

You MUST finish in under 90 seconds wall-clock. This is the fast-path summary.
You MUST NOT read anything under node_modules/, target/, __pycache__/, .git/, dist/, build/.
You MUST write exactly four files: index.md, modules.md, interfaces.md, flow.md. No more, no less.
You MUST keep descriptions factual — no quality judgments (that's evaluate-run's job).
Output files MUST be valid markdown that renders correctly in GitHub's viewer (Mermaid in a ```mermaid fenced block).

Troubleshooting

Code is unparseable / generated output is garbage

Write the index.md with **Shape:** unparseable — agent output did not produce a valid project.
Leave the other files near-empty with a one-line explanation.
Exit 0 so evaluate-run can still complete.

Too many files to summarize

This shouldn't happen in retort's small-task workspaces. If it does, cap the modules table at 50 rows and note the truncation in index.md.

Files

Just SKILL.md in skills/run-summary of adrianco/retort.

Open the folder on GitHubat commit 1f75769

Compare with similar skills

Run Summary 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.

Run Summary compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Run Summary this skilladrianco/retort	207	—	~1.3k	Automated safety check: Pass	Apache-2.0	today
Summarizeopenclaw/openclaw	392k	1 repos	~531	Automated safety check: Pass	MIT	today
Research Summarizeralirezarezvani/claude-skills	28k	1 repos	~2.7k	Automated safety check: Pass	MIT	1 mo ago
Summarize Statuspaperclipai/paperclip	99k	—	~2.2k	Automated safety check: Pass	MIT	today
Summarizerholaboss-ai/holaOS	11k	—	~615	Automated safety check: Pass	Custom licence	1 mo ago
Summarize Meetingphuryn/pm-skills	27k	—	~749	Automated safety check: Pass	MIT	24 days ago

Similar skills

Summarize
openclaw/openclaw
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
392k GitHub starsUsed in 1 repo~531 tokens
Media & CreativeAuto-check passed
Research Summarizer
alirezarezvani/claude-skills
Structured research summarization agent skill for non-dev users.
28k GitHub starsUsed in 1 repo~2.7k tokens
Research & ScienceAuto-check passed
Summarize Status
paperclipai/paperclip
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language…
99k GitHub stars~2.2k tokensUpdated today
Writing & ContentAuto-check passed
Summarizer
holaboss-ai/holaOS
Condense long articles, reports, and documents into clear, concise summaries.
11k GitHub stars~615 tokensUpdated 1 mo ago
Auto-check passed
Summarize Meeting
phuryn/pm-skills
Summarize a meeting transcript into structured notes with date, participants, topic, key decisions, summary points, and action items.
27k GitHub stars~749 tokensUpdated 24 days ago
Productivity & AutomationAuto-check passed
Hacker News Summarizer
ykdojo/claude-code-tips
Fetches Hacker News top stories, a chosen story with its comment thread and the linked article through the official APIs, then summarizes them.
10k GitHub stars~942 tokensUpdated 14 days ago
Writing & ContentAuto-check passed

Questions about Run Summary

What does Run Summary do?

Summarize the architecture of code generated by a single retort run. Run Summary is an agent skill from adrianco/retort. Summarize the architecture of code generated by a single retort run.

How do I install Run Summary in Claude Code?

Run `npx skills add adrianco/retort --skill run-summary -a claude-code`. Or copy the skill folder (skills/run-summary in adrianco/retort) into .claude/skills/run-summary in your project. Claude Code loads it when a task matches its description.

How do I install Run Summary in Codex?

Run `npx skills add adrianco/retort --skill run-summary -a codex`. Or copy the skill folder (skills/run-summary in adrianco/retort) into .agents/skills/run-summary in your project. Codex loads it when a task matches its description.

Can I use Run Summary in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adrianco/retort --skill run-summary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/run-summary, .gemini/skills/run-summary, .github/skills/run-summary and .opencode/skills/run-summary in your project.

What does Run Summary need to run?

SKILL.md names no scripts, command-line tools or credentials: Run Summary is instructions for the agent only.

Does Run Summary access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Run Summary safe to install?

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.

What licence does Run Summary use?

Run Summary is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Run Summary use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Run Summary?

Skills that share tags, products or a category with Run Summary: Summarize (openclaw/openclaw, 392k stars), Research Summarizer (alirezarezvani/claude-skills, 28k stars), Summarize Status (paperclipai/paperclip, 99k stars) and Summarizer (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Run Summary?

adrianco (a GitHub user) maintains it in adrianco/retort, which has 207 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 9, 2026.

Source: adrianco/retort on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Run Summary

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Run Summary

Overview

Parameters

Steps

1. Infer the surface

2. Map the modules

3. Describe the interfaces

4. Trace the dominant control flow

Constraints Summary

Troubleshooting

Files

Compare with similar skills

Similar skills

More from adrianco/retort

Questions about Run Summary