New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Recovery Runbook

by MAGA2010 in MAGA2010/hackathon-run

Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage.

MITAuto-check passedDevOps & Cloud

Install Recovery Runbook

skills CLI
$ npx skills add MAGA2010/hackathon-run --skill recovery-runbook -a claude-code

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

GitHub CLI
$ gh skill install MAGA2010/hackathon-run recovery-runbook --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/MAGA2010/hackathon-run.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recovery-runbook .claude/skills/recovery-runbook && 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/

Facts

Skill name
recovery-runbook
GitHub stars
411
Token cost
~967 tokens
SKILL.md length
323 words
Files
4 (incl. scripts)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage.

  • Works in 5 steps: Classify severity → Pick a fallback strategy → Write the 30-second script → …
  • Tasks that involve Runbooks and postmortems
  • SKILL.md covers Input contract, Execution, Output contract and Acceptance criteria, plus 2 more sections
  • Runs Python and Shell scripts from its folder

What it does

Recovery Runbook is an agent skill from MAGA2010/hackathon-run. Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage. Use the moment a failure occurs: P0 if the demo is dead, P3 if only copy is wrong.

Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `scripts/build_recovery.py`, `scripts/fallback.py` and `tests/test_build_recovery.sh`).

It sits in DevOps & Cloud, covering Runbooks and postmortems. The licence is MIT.

When your agent uses it

  • Tasks that involve Runbooks and postmortems

Example prompts

  • “Use the recovery-runbook skill to generate an emergency 30-second demo script and a fallback plan when a live demo breaks on stage”
  • “/recovery-runbook”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

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

  1. Classify severity
  2. Pick a fallback strategy
  3. Write the 30-second script
  4. Provide recovery steps
  5. Write artifacts

What it can do on your machine

Read from SKILL.md and the folder at commit de3bcfb. 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

    Ships 2 files in scripts/ (Python and Shell), which the agent can run.

    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

Recovery Runbook loads about 967 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~967

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); the scripts in this folder are not scanned.

SKILL.md

The full file from MAGA2010/hackathon-run at commit de3bcfb, republished under its MIT licence (© MAGA2010). 323 words, ~967 tokens.

Download SKILL.mdSave it as .claude/skills/recovery-runbook/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
recovery-runbook
description
Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage. Use the moment a failure occurs: P0 if the demo is dead, P3 if only copy is wrong.
when_to_use
Trigger when the demo fails on stage, the dev server is down, the API times out, or any skill invocation surfaces a P0/P1 failure. Do not invoke preemptively…
version
1.0
category
recovering
tags
["fallback", "decision-tree", "30-second"]
dependencies
["fast-verify", "demo-coach"]
side_effects
["recovery"]
triggers
["demo is broken", "fallback", "recovery", "what do we do if X fails", "30-second fallback"]
capabilities
[fs_read, fs_write, env]

recovery-runbook

Input contract

Required:

  • failure_description: one-sentence description of what broke
  • severity: P0 | P1 | P2 | P3
  • demo_path (from .hackathon/state/plan.json or user-supplied)

Optional:

  • .hackathon/state/verify.json (last failure signatures)
  • .hackathon/state/rehearsal.json (timed rehearsal risks)

Execution

1. Classify severity
SeverityMeaningDefault fallback
P0Demo entirely brokenVideo recording + verbal narrative
P1Core feature crashesStatic screenshots + verbal walkthrough
P2Peripheral feature failsSkip the failing step, narrate the rest
P3UI / copy issueAcknowledge, continue
2. Pick a fallback strategy

For each severity, the skill produces:

  1. The thing to do next (action verb)
  2. The thing to say (one sentence)
  3. The thing NOT to do (anti-pattern to avoid)
3. Write the 30-second script

Mandatory content:

  • Acknowledge the failure in < 5 seconds ("the live demo hiccuped, here's what we built").
  • Switch to the fallback in < 10 seconds.
  • Show value in the next 10 seconds.
  • End with a confident close in < 5 seconds.
4. Provide recovery steps

For the engineer, off-stage:

  • Check the dev server (lsof, ps).
  • Check the most recent log lines.
  • Check environment variables.
  • Check external service status.
5. Write artifacts
  • .hackathon/artifacts/recovery-runbook.md (printable card)
  • .hackathon/state/recovery.json (machine-readable for downstream tools)

Output contract

Files written:

  • .hackathon/artifacts/recovery-runbook.md (the 30-second script + fallback plan)
  • .hackathon/state/recovery.json (matches src/state/schemas/recovery.schema.json; severity + steps + fallback + evidence)

scripts/fallback.py automatically reads verify and rehearsal evidence from --out-dir, then prepends the recorded fixes to the off-stage recovery steps.

Acceptance criteria

  • Provides a fallback plan for the given severity.
  • Provides presentation talking points.
  • Avoids prolonged live debugging.
  • Prioritizes demo continuity over technical depth.
  • Outputs a 30-second script that fits within 30 seconds when read aloud.

Failure modes

ModeBehavior
symptom is emptyAsk once; do not invent a symptom
Demo is already overRefuse; recovery-runbook is for the live demo
time_to_present <= 0Refuse; emit "too late, post-mortem instead"
Multiple symptoms detectedAsk the human to pick the dominant one before proceeding

Trigger phrases

  • "the demo just died"
  • "the screen is frozen"
  • "API is down"
  • "what do I do"
  • "fallback plan"

© MAGA2010, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/recovery-runbook of MAGA2010/hackathon-run.

  • SKILL.md
  • scripts/build_recovery.py
  • scripts/fallback.py
  • tests/test_build_recovery.sh

Open the folder on GitHubat commit de3bcfb

Compare with similar skills

Recovery Runbook 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.

Recovery Runbook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recovery Runbook this skillMAGA2010/hackathon-run411—~967Automated safety check: PassMIT
Trader Memory Coretradermonty/claude-trading-skills3k2 repos~4.3kAutomated safety check: PassMIT
Author Migrationnrwl/nx29k—~12kAutomated safety check: NotesMIT
Write Notes Like Deepseekczm15053/write-notes-like-deepseek508—~2kAutomated safety check: PassNone
OpenRig Upgrade Proceduremvschwarz/openrig6.8k—~2.9kAutomated safety check: PassApache-2.0
GreptimeDB Release RunbookGreptimeTeam/greptimedb6.7k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Trader Memory Core

    tradermonty/claude-trading-skills

    Track investment theses across their lifecycle — from screening idea to closed position with postmortem.

    3k GitHub starsUsed in 2 repos~4.3k tokens
    DevOps & CloudAuto-check passed

  • Author Migration

    nrwl/nx

    Author or scope a first-party Nx migration. An agent skill from nrwl/nx.

    29k GitHub stars~12k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

  • Write Notes Like Deepseek

    czm15053/write-notes-like-deepseek

    A skill your agent uses when a change is non-trivial by DSH standards (behavior, architecture, cross-file contracts, process/tooling, testing strategy, or on-disk/wire/config formats), when choosing…

    508 GitHub stars~2k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed

  • OpenRig Upgrade Procedure

    mvschwarz/openrig

    Walks an agent through upgrading the OpenRig CLI and daemon one observed step at a time, keeping live seats alive and reconciling managed plugin files.

    6.8k GitHub stars~2.9k tokensUpdated today
    DevOps & CloudAuto-check passed

  • GreptimeDB Release Runbook

    GreptimeTeam/greptimedb

    Runbook for publishing a GreptimeDB version: pick the release branch, verify the Cargo version, then tag, create the GitHub release and open the docs note PR.

    6.7k GitHub stars~1.4k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Statem

    henryqin1997/statem

    A skill your agent uses when a long coding or research task should be managed with statem state-machine runbooks, including creating specs, starting or resuming runs, checking current state…

    1.3k GitHub stars~1.2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

More from MAGA2010/hackathon-run

All 15 skills in this repo

  • Decision Log

    MAGA2010/hackathon-run

    Writes every KEEP/CUT/DEFER/PIVOT scope decision into an append-only team log with rationale, author, and timestamp.

    411 GitHub stars~847 tokensUpdated 3 days ago
    Auto-check passed

  • Demo Coach

    MAGA2010/hackathon-run

    Drafts a 30, 60, or 90-second pitch script for the demo, structured as opening, pain, product, action, result, close.

    411 GitHub stars~895 tokensUpdated 3 days ago
    Auto-check passed

  • Judge Sim

    MAGA2010/hackathon-run

    Scores a hackathon project 0 to 5 across seven judging dimensions and produces a prioritized fix list for the last hour.

    411 GitHub stars~970 tokensUpdated 3 days ago
    Auto-check passed

  • Scope Knife

    MAGA2010/hackathon-run

    Forces a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is running out.

    411 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Time Box

    MAGA2010/hackathon-run

    Allocates time across the hackathon lifecycle (idea - scope - build - verify - demo - ship) and warns before each deadline slips.

    411 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Fast Verify

    MAGA2010/hackathon-run

    Verifies the demo path runs end-to-end by executing each step in order, recording the actual outcome, and stopping at the first failure with a diagnostic.

    411 GitHub stars~893 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Recovery Runbook

What does Recovery Runbook do?

Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage. Recovery Runbook is an agent skill from MAGA2010/hackathon-run. Generates an emergency 30-second demo script and a fallback plan when a live demo breaks on stage.

When should I use Recovery Runbook?

Recovery Runbook fits situations like: tasks that involve Runbooks and postmortems.

How do I install Recovery Runbook in Claude Code?

Run `npx skills add MAGA2010/hackathon-run --skill recovery-runbook -a claude-code`. Or copy the skill folder (skills/recovery-runbook in MAGA2010/hackathon-run) into .claude/skills/recovery-runbook in your project. Claude Code loads it when a task matches its description.

How do I install Recovery Runbook in Codex?

Run `npx skills add MAGA2010/hackathon-run --skill recovery-runbook -a codex`. Or copy the skill folder (skills/recovery-runbook in MAGA2010/hackathon-run) into .agents/skills/recovery-runbook in your project. Codex loads it when a task matches its description.

Can I use Recovery Runbook 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 MAGA2010/hackathon-run --skill recovery-runbook -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recovery-runbook, .gemini/skills/recovery-runbook, .github/skills/recovery-runbook and .opencode/skills/recovery-runbook in your project.

What does Recovery Runbook need to run?

Going by SKILL.md and its folder, Recovery Runbook needs Python and a shell for the scripts in its folder. Our summary lists: Python 3; A Bash shell.

Does Recovery Runbook 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 Recovery Runbook 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Recovery Runbook use?

Recovery Runbook is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recovery Runbook use?

About 967 tokens (SKILL.md is roughly 3.9k 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 Recovery Runbook?

Skills that share tags, products or a category with Recovery Runbook: Trader Memory Core (tradermonty/claude-trading-skills, 3k stars), Author Migration (nrwl/nx, 29k stars), Write Notes Like Deepseek (czm15053/write-notes-like-deepseek, 508 stars) and OpenRig Upgrade Procedure (mvschwarz/openrig, 6.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recovery Runbook?

MAGA2010 (a GitHub user) maintains it in MAGA2010/hackathon-run, which has 411 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: MAGA2010/hackathon-run on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.