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

Retro

by bitsocialnet in bitsocialnet/5chan

Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance.

GPL-3.0Auto-check passedDevelopment

Install Retro

skills CLI
$ npx skills add bitsocialnet/5chan --skill retro -a claude-code

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

GitHub CLI
$ gh skill install bitsocialnet/5chan retro --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/bitsocialnet/5chan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/retro .claude/skills/retro && 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
retro
GitHub stars
135
Token cost
~865 tokens
SKILL.md length
467 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
GPL-3.0

At a glance

Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance.

  • Tasks that involve Debugging
  • SKILL.md covers Establish the evidence, Choose useful prevention and Complete within scope
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Retrospectives

What it does

Retro is an agent skill from bitsocialnet/5chan. Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging and Retrospectives. The repository describes itself as: A peer-to-peer 4chan alternative. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Debugging
  • Tasks that involve Retrospectives

Example prompts

  • “/retro”

What it can do on your machine

Read from SKILL.md and the folder at commit a31f565. 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.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Retro loads about 865 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~865

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 bitsocialnet/5chan at commit a31f565, republished under its GPL-3.0 licence (© bitsocialnet). 467 words, ~865 tokens.

Download SKILL.mdSave it as .claude/skills/retro/SKILL.md (or your agent's skills folder).
name
retro
description
Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance.

Retro

Turn a demonstrated mistake or repeated obstacle into the smallest useful improvement to this repository's development workflow. A finding that existing checks already cover, or that needs no additional prevention, is a valid outcome.

Establish the evidence

Use the current task's conversation, diff, review feedback, and available failure output. For another session or PR, use the evidence the user identifies; state missing context rather than inventing a history or searching unrelated sessions. Routine successful edits do not need a retrospective.

Read applicable AGENTS.md guidance and the relevant package/build scripts, check configuration, hooks, and CI jobs before proposing a check. Distinguish a missing check from one that exists but is unwired, skipped, or unable to fail its caller. During an explicit repository-wide retrospective, absent automated lint, type, or test enforcement is itself worth reporting. Inspect configuration first; do not launch a full build or test suite just to inventory it.

Choose useful prevention

  • For a mechanical issue, prefer a deterministic check over another prose rule: an existing linter option, a focused regression test, or a small extension to the repository's checker. Reuse the normal check commands and CI; use a commit hook only for checks that are fast and suitable for staged changes.
  • For behavior bugs, cover the failing behavior or invariant. For syntax, imports, or module placement, prefer the existing parser/linter or architecture checker. Avoid broad text matches that confuse valid code with the defect.
  • For a judgment call that cannot be checked reliably, clarify the relevant existing review guidance or playbook. Do not create a new standards document merely to restate existing instructions.
  • For repeated navigation or information gaps, add a focused pointer or repair the existing tool/documentation path when the session demonstrates why it is needed.

Weigh impact and recurrence against maintenance cost and false positives. Do not invent a rule from a one-off preference, duplicate existing coverage, weaken checks to make a run pass, or expand into unrelated cleanup. Keep repository policy in committed repository files; do not modify global instructions or other repositories.

Show full SKILL.md (129 more words)Show less

Complete within scope

A review-only or ideas-only request returns recommendations without edits. During authorized implementation, apply the smallest relevant prevention within the task's scope; report broader workflow or policy changes as follow-ups. Existing authorization continues to apply, and this skill adds no approval gate or publishing permission.

When adding a check, verify that it detects the demonstrated failure and accepts the corrected behavior, using the repository's affected-check guidance. Reuse valid verification evidence; do not repeat unrelated checks. Keep retrospective reasoning in the agent workflow rather than adding an AI call to every commit or a new scheduled job.

Report only worthwhile findings, with the evidence, the prevention applied or proposed, and any verification limits. If no additional prevention is justified, say so briefly.

Inspired by mattpocock/skills retro PR #1083.

© bitsocialnet, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/retro of bitsocialnet/5chan.

Open the folder on GitHubat commit a31f565

Compare with similar skills

Retro 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.

Retro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retro this skillbitsocialnet/5chan135—~865Automated safety check: PassGPL-3.0
Retroapmantza/pi-lens463—~531Automated safety check: PassMIT
Experiment CraftEvoScientist/EvoSkills4753 repos~2kAutomated safety check: PassApache-2.0
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence

Similar skills

  • Retro

    apmantza/pi-lens

    Run the pi-lens retrospective — turn a session, an incident, or a merged bug fix into environment changes (checks, hooks, contract lines, deletions), classified mechanical-vs-judgement, each with…

    463 GitHub stars~531 tokensUpdated today
    DevelopmentAuto-check passed

  • Experiment Craft

    EvoScientist/EvoSkills

    A skill your agent uses when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs…

    475 GitHub starsUsed in 3 repos~2k tokens
    DevelopmentAuto-check passed

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes

  • Debugging Executions

    n8n-io/n8n

    Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed

More from bitsocialnet/5chan

All 12 skills in this repo

  • Playwright CLI

    bitsocialnet/5chan

    Verify browser behavior or reproduce a web UI issue with the installed Playwright CLI.

    135 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

  • Inspect Elements

    bitsocialnet/5chan

    Map a visible 5chan DOM node to its React source when file or component attribution is needed.

    135 GitHub stars~727 tokensUpdated today
    Auto-check passed

  • Translate

    bitsocialnet/5chan

    Add, update, or remove 5chan i18next translations when locale changes are requested.

    135 GitHub stars~692 tokensUpdated today
    Auto-check: notes

  • You Might Not Need An Effect

    bitsocialnet/5chan

    Review React effects and memoization when the user requests an effect audit or a change has unclear synchronization needs.

    135 GitHub stars~474 tokensUpdated today
    Auto-check passed

  • Debug Agent

    bitsocialnet/5chan

    Investigate a reported bug using source, tests, or runtime evidence to establish its cause.

    135 GitHub stars~663 tokensUpdated today
    Auto-check passed

  • Profile Browsing

    bitsocialnet/5chan

    Measure 5chan loading, navigation, interaction timing, and committed React updates using repeatable scenarios.

    135 GitHub stars~507 tokensUpdated today
    Auto-check passed

Categories

Questions about Retro

What does Retro do?

Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance. Retro is an agent skill from bitsocialnet/5chan. Review a coding session, bug fix, or substantive review correction for evidence-backed ways to prevent recurrence, using existing checks and focused guidance.

When should I use Retro?

Retro fits situations like: tasks that involve Debugging; tasks that involve Retrospectives.

How do I install Retro in Claude Code?

Run `npx skills add bitsocialnet/5chan --skill retro -a claude-code`. Or copy the skill folder (.agents/skills/retro in bitsocialnet/5chan) into .claude/skills/retro in your project. Claude Code loads it when a task matches its description.

How do I install Retro in Codex?

Run `npx skills add bitsocialnet/5chan --skill retro -a codex`. Or copy the skill folder (.agents/skills/retro in bitsocialnet/5chan) into .agents/skills/retro in your project. Codex loads it when a task matches its description.

Can I use Retro 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 bitsocialnet/5chan --skill retro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retro, .gemini/skills/retro, .github/skills/retro and .opencode/skills/retro in your project.

What does Retro need to run?

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

Does Retro access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Retro 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 Retro use?

Retro is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Retro use?

About 865 tokens (SKILL.md is roughly 3.5k 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 Retro?

Skills that share tags, products or a category with Retro: Retro (apmantza/pi-lens, 463 stars), Experiment Craft (EvoScientist/EvoSkills, 475 stars), Trellis Session Insight (mindfold-ai/Trellis, 15k stars) and Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retro?

bitsocialnet (a GitHub organization) maintains it in bitsocialnet/5chan, which has 135 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: bitsocialnet/5chan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.