Produces a blameless post-incident debrief with timeline, root cause and follow-up actions after an outage, failed release or significant bug, while details are fresh.
$ npx skills add VeryGoodOpenSource/vgv-wingspan --skill debrief -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VeryGoodOpenSource/vgv-wingspan debrief --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/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/debrief .claude/skills/debrief && 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 "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .claude/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debriefType 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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VeryGoodOpenSource/vgv-wingspan debrief --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/debrief .agents/skills/debrief && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .agents/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VeryGoodOpenSource/vgv-wingspan debrief --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/debrief .cursor/skills/debrief && 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 "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .cursor/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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/VeryGoodOpenSource/vgv-wingspan.git --path skills/debrief--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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VeryGoodOpenSource/vgv-wingspan debrief --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/debrief .gemini/skills/debrief && 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 "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .gemini/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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 VeryGoodOpenSource/vgv-wingspan debriefInstalls 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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/debrief .github/skills/debrief && 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 "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .github/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VeryGoodOpenSource/vgv-wingspan debrief --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/debrief .opencode/skills/debrief && 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 "debrief" agent skill from https://github.com/VeryGoodOpenSource/vgv-wingspan/tree/main/skills/debrief into .opencode/skills/debrief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "debrief", 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.
debriefProduces a blameless post-incident debrief with timeline, root cause and follow-up actions after an outage, failed release or significant bug, while details are fresh.
This skill writes a structured, blameless document after a production incident, failed release, flaky deploy or significant bug that deserves more than a fix. It takes the incident description as its argument; if none is given it asks what happened and will not continue until you answer. It then asks about the incident one question at a time, skipping anything already clear.
The questions cover what happened and the user-visible impact, when it started, was detected and was resolved, which platform or environment was affected, severity, how it was discovered, the fix and any temporary workaround, and links to pull requests, commits, CI runs or logs. Questioning stops once a timeline can be reconstructed or you say to proceed, and gaps are noted in the document instead of blocking it.
In parallel the agent collects evidence from the codebase: git log on the affected files over the last two weeks or a range you give, related commits, gh pr view for referenced pull requests, and gh run list and gh run view for failed CI runs, skipping CI when there is no CI context. A template in references/template.md serves as the layout for the final document.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 19e0695. 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:
gitghFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git and gh, 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.
Designed for Claude Code (or similar products with agent support)
From compatibility in the SKILL.md frontmatter.
Post-Incident Debrief loads about 1.9k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 907 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 VeryGoodOpenSource/vgv-wingspan at commit 19e0695, republished under its MIT licence (© VeryGoodOpenSource). 907 words, ~1,858 tokens.
.claude/skills/debrief/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Produce a structured, blameless debrief document after an incident, failed release, or significant bug. Capture what happened, why, and what to change — while the context is still fresh.
Use this when a production incident, failed release, flaky deploy, or significant bug warrants more than just a fix — when the team needs to understand why it happened and prevent recurrence.
<incident_context>$ARGUMENTS</incident_context>
If the incident context above is empty, ask the user: "What incident would you like to debrief? Describe what happened, link to relevant PRs/commits, or paste error logs."
DO NOT proceed until you have a description from the user.
Use the AskUserQuestion tool to fill in gaps one question at a time. Adapt based on what the user already provided — skip questions whose answers are already clear from the incident context.
Key questions to resolve:
| Topic | Example Questions |
|---|---|
| What happened | What was the user-visible impact? What broke? |
| When | When did it start? When was it detected? When was it resolved? |
| Where | What platform, environment, or service? (e.g., prod vs staging, iOS vs Android, specific API) |
| Severity | How many users/systems were affected? Was data lost? |
| Detection | How was it discovered? Alert, user report, or manual observation? |
| Resolution | What was the fix? Is it deployed? Is it a temporary workaround? |
| References | Relevant PRs, commits, CI runs, error logs, or monitoring links? |
Exit condition: Continue until you have enough context to reconstruct a timeline, OR the user says "that's all I have" or "proceed."
The skill must work with partial information. Not every debrief has full CI logs or a complete timeline. Note gaps explicitly in the document rather than blocking on them.
Based on the incident context, automatically collect evidence. Run these in parallel where possible:
Run these in parallel:
git log on affected files (last 2 weeks or user-specified range), git log --all --oneline for related commits, gh pr view for referenced PRsgh run list for recent failures, gh run view <id> for referenced runs. Skip if no CI context — do not block on missing data.git log --oneline <file>). Note files lacking tests or with high churn.Synthesize the evidence to identify the root cause (specific change, gap, or condition — trace to commits or code paths) and contributing factors (missing tests, no monitoring, unclear ownership, insufficient review).
Blameless framing: Focus on systems and processes, not individuals. Ask "what made this possible?" not "who caused this?"
Generate concrete, assignable follow-ups. Each must be specific (not "improve testing"), linked to code where possible, and categorized:
| Type | Purpose | Examples |
|---|---|---|
| Prevent | Would have stopped this incident | Add validation, add test |
| Detect | Would have caught it sooner | Add monitoring, add CI check |
| Respond | Would have made recovery faster | Add runbook, add feature flag |
Action items are recorded in the document only — they become separate tickets.
Before writing the debrief file, ensure the session is not on the base branch:
git rev-parse --abbrev-ref HEAD. If the current branch is a base branch (main, master, or develop), use AskUserQuestion to offer creating a feature branch — git checkout -b <type>/<kebab-topic>, name under 60 characters — before writing. If already on a feature branch, continue without prompting.Write the document to docs/debriefs/YYYY-MM-DD-<kebab-case-topic>-debrief.md.
Ensure docs/debriefs/ directory exists before writing.
Document structure:
Use the debrief template as the document structure. Adapt it to fit the available information — omit sections with no relevant data rather than filling them with "N/A." Add sections if the incident warrants it (e.g., a "Customer Communication" section for user-facing incidents).
Use the AskUserQuestion tool to present next steps:
Question: "Debrief complete! What would you like to do next?"
Options:
If the user selects "Review and refine" → apply the @refine-approach skill to the document. When refinement is complete, present these options again (without the refine option).
If the user selects "Generate issue previews" → read the action items from the written debrief document, then:
Check for issue templates: look for .github/ISSUE_TEMPLATE/ in the project root. Read every .yaml or .yml file found there (skip config.yml).
If templates exist: render one preview block per action item using the most appropriate template. Map each item to a template based on its content (e.g., a missing test or validation gap → bug report; a new monitoring check → feature request; a dependency update or runbook → chore). Populate every required field defined in the template. Include a Template: line naming the chosen template file.
If no templates exist: fall back to the generic format:
---
Title: <specific, actionable title>
Label: prevent | detect | respond
Body:
## Context
Debrief: docs/debriefs/YYYY-MM-DD-<topic>-debrief.md
Root cause: <one-line summary from debrief>
## What happened
<relevant excerpt from the debrief timeline or root cause section>
## What to do
<the action item, specific and linked to code/files where possible>
---Render all previews in a single fenced block so the user can copy them. Do not call gh, glab, or any external CLI — output is display only.
When complete, display:
Debrief complete!
Document: docs/debriefs/YYYY-MM-DD-<kebab-case-topic>-debrief.md
Severity: <severity>
Root cause: [one-line summary]
Action items: <N> prevent, <N> detect, <N> respondDO NOT make code changes. This skill produces a document only. Action items become separate tickets.
© VeryGoodOpenSource, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in skills/debrief of VeryGoodOpenSource/vgv-wingspan.
Open the folder on GitHubat commit 19e0695
Post-Incident Debrief 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 |
|---|---|---|---|---|---|---|
| Post-Incident Debrief this skillVeryGoodOpenSource/vgv-wingspan | 109 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Conducting Post Incident Lessons Learnedmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Incident Postmortemgithub/awesome-copilot | 40k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Incident Triage Harnessmadebyaris/advance-minimax-m3-cursor-rules | 126 | — | ~984 | Automated safety check: Pass | MIT | |
| Incident Response LifecycleLeoYeAI/openclaw-master-skills | 2.2k | — | ~5k | Automated safety check: Pass | Apache-2.0 | |
| Post Mortemhanamizuki/solopreneur | 152 | — | ~1.7k | Automated safety check: Pass | MIT |
mukul975/Anthropic-Cybersecurity-Skills
Facilitate structured post-incident reviews to identify root causes, document what worked and failed, and produce actionable recommendations to improve future incident response.
github/awesome-copilot
A skill your agent uses when an outage, production incident, or significant service degradation has occurred and the team needs to write a structured blameless post-mortem.
madebyaris/advance-minimax-m3-cursor-rules
Walks an agent through an evidence-first incident investigation across logs, metrics, code and screenshots, from first symptom to the smallest safe mitigation.
LeoYeAI/openclaw-master-skills
Incident response process management following the NIST 800-61 lifecycle.
hanamizuki/solopreneur
Trace when a bug was introduced, find the root cause commit, understand why it happened, and produce a structured post-mortem report.
thananon/9arm-skills
Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through.
VeryGoodOpenSource/vgv-wingspan
Runs parallel review agents over a branch, chosen paths or a whole project and merges their findings into one numbered report you can act on by id.
VeryGoodOpenSource/vgv-wingspan
Rebases the current feature branch onto the latest main, master or develop, stashing uncommitted work first and aborting cleanly if conflicts appear.
VeryGoodOpenSource/vgv-wingspan
Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.
VeryGoodOpenSource/vgv-wingspan
Stages, commits, pushes and opens a pull request with a Conventional Commits message, after running the project's checks unless told to skip them.
VeryGoodOpenSource/vgv-wingspan
Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required.
VeryGoodOpenSource/vgv-wingspan
Turns high-level brainstorming and ideas into well-structured, actionable implementation plans.
Categories
Produces a blameless post-incident debrief with timeline, root cause and follow-up actions after an outage, failed release or significant bug, while details are fresh. This skill writes a structured, blameless document after a production incident, failed release, flaky deploy or significant bug that deserves more than a fix. It takes the incident description as its argument; if none is given it asks what happened and will not continue until you answer.
Post-Incident Debrief fits situations like: writing up a production outage after it has been resolved; reviewing a failed release or flaky deploy to find the root cause; turning a significant bug into a timeline with follow-up actions; capturing what happened while the details are still fresh.
Run `npx skills add VeryGoodOpenSource/vgv-wingspan --skill debrief -a claude-code`. Or copy the skill folder (skills/debrief in VeryGoodOpenSource/vgv-wingspan) into .claude/skills/debrief in your project. Claude Code loads it when a task matches its description.
Run `npx skills add VeryGoodOpenSource/vgv-wingspan --skill debrief -a codex`. Or copy the skill folder (skills/debrief in VeryGoodOpenSource/vgv-wingspan) into .agents/skills/debrief 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 VeryGoodOpenSource/vgv-wingspan --skill debrief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debrief, .gemini/skills/debrief, .github/skills/debrief and .opencode/skills/debrief in your project.
Going by SKILL.md and its folder, Post-Incident Debrief needs the command-line tools its instructions call (git and gh). Our summary lists: Git history of the affected project; The GitHub CLI (gh) for pull request and CI lookups when they are relevant. Compatibility (from SKILL.md): Designed for Claude Code (or similar products with agent support).
SKILL.md contains no URLs. Its commands use git and gh, 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.
Post-Incident Debrief is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 436 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Post-Incident Debrief: Conducting Post Incident Lessons Learned (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Incident Postmortem (github/awesome-copilot, 40k stars), Incident Triage Harness (madebyaris/advance-minimax-m3-cursor-rules, 126 stars) and Incident Response Lifecycle (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
VeryGoodOpenSource (a GitHub organization) maintains it in VeryGoodOpenSource/vgv-wingspan, which has 109 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.
Source: VeryGoodOpenSource/vgv-wingspan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
