How do I install the Retro Create skill?

Run npx get-skill add tomevault-io/retro-create in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Retro Create safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Retro Create?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Retro Create free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Retro Create?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Retro Create by tomevault-io — Agent Skill

Name: Retro Create
Author: tomevault-io

File contents

Purpose

After any skill completes, review the session for issues and improve the skill to prevent recurrence.

Trigger

Run automatically after every skill invocation completes (success or failure).

What to look for

Failed commands — commands that errored and required retrying or workarounds
User corrections — the user stepped in to redirect, correct, or override
Wrong assumptions — the skill assumed something that was not true (versions, paths, flags)
Missing steps — manual steps the user had to perform that the skill should have handled
Outdated instructions — references to APIs, flags, or behaviors that have changed

Protocol

For each issue found:

Log — append an entry to <skill-dir>/retro.md (create the file if it does not exist)
Root-cause — identify which file (SKILL.md, reference, template) contains the gap
Fix immediately — edit the skill file directly to prevent recurrence. This is the default action.
Log only if unsafe — record the issue with status: open only when the fix would change skill behavior in ways that cannot be verified in the current session. Require a resolution-hint on every open entry.

After logging any status: open entry, append:

Open issues remain. Run /retro-resolve to process them.

retro.md entry format

## YYYY-MM-DD — <brief title>

- **type**: failed-command | user-correction | wrong-assumption | missing-step | outdated-instruction
- **skill**: <skill-name>
- **context**: <what happened>
- **root-cause**: <why it happened>
- **fix**: <what was changed> | `status: open` if not yet fixed
- **resolution-hint**: <what the fix should look like> (required for open entries)
- **files-changed**: <list of files edited, or "none">

Constraints

Do not modify skill behavior or semantics — only fix gaps, errors, and omissions
Keep entries concise (3-5 lines per field max)
Do not duplicate fixes already present in skill files
If a fix would change skill behavior significantly, log as status: open and note the concern
Prefer fixing over logging. If you can describe the fix in resolution-hint, you can probably just apply it.
Never log as status: open simply because the session is long or context is low.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: retro-createdescription: Post-invocation retrospective. Tracks skill issues and applies fixes automatically. Use when this capability is needed.---## PurposeAfter any skill completes, review the session for issues and improve the skill to prevent recurrence.## TriggerRun automatically after every skill invocation completes (success or failure).## What to look for1. **Failed commands** — commands that errored and required retrying or workarounds2. **User corrections** — the user stepped in to redirect, correct, or override3. **Wrong assumptions** — the skill assumed something that was not true (versions, paths, flags)4. **Missing steps** — manual steps the user had to perform that the skill should have handled5. **Outdated instructions** — references to APIs, flags, or behaviors that have changed## ProtocolFor each issue found:1. **Log** — append an entry to `<skill-dir>/retro.md` (create the file if it does not exist)2. **Root-cause** — identify which file (SKILL.md, reference, template) contains the gap3. **Fix immediately** — edit the skill file directly to prevent recurrence. This is the default action.4. **Log only if unsafe** — record the issue with `status: open` only when the fix would change skill behavior in ways that cannot be verified in the current session. Require a `resolution-hint` on every open entry.After logging any `status: open` entry, append:> **Open issues remain.** Run /retro-resolve to process them.## retro.md entry format```## YYYY-MM-DD — <brief title>- **type**: failed-command | user-correction | wrong-assumption | missing-step | outdated-instruction- **skill**: <skill-name>- **context**: <what happened>- **root-cause**: <why it happened>- **fix**: <what was changed> | `status: open` if not yet fixed- **resolution-hint**: <what the fix should look like> (required for open entries)- **files-changed**: <list of files edited, or "none">```## Constraints- Do not modify skill behavior or semantics — only fix gaps, errors, and omissions- Keep entries concise (3-5 lines per field max)- Do not duplicate fixes already present in skill files- If a fix would change skill behavior significantly, log as `status: open` and note the concern- Prefer fixing over logging. If you can describe the fix in `resolution-hint`, you can probably just apply it.- Never log as `status: open` simply because the session is long or context is low.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/edfenton) — claim your Tome and manage your conversions.

Frequently asked questions

Retro Create