todoIdealPrompt SKILL.md skillA
todoIdealPrompt from blackorange0506/prompt-todo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add blackorange0506/prompt-todo/todoIdealPrompt@git:20261011.0742d51Pins git:20261011.0742d51 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- blackorange0506/prompt-todo
- Path
template/.claude/skills/todoIdealPrompt/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261011.0742d51, committed Oct 11, 2026
- First version recorded
- Sep 6, 2026
- Size
- 8,451 bytes
- Repository stars
- 4
- License
- MIT
Distill a finished TODO-item dialog into the IDEAL PROMPT — the single SHORT message (a few typeable lines, never a spec) that would have produced the confirmed result on the first try — plus feedback on what the original prompt lacked. Prompt-writing training for the user: Claude reconstructs the whole back-and-forth (original prompt, every correction, the final accepted fix) and writes the prompt it wishes it had received. With --replace, the item's text in the user's todo file…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /todoIdealPrompt
The user works TODO items through long dialogs — the first prompt is short, and the real
requirements surface through corrections ("wrong, text should rotate", "that blocks too much,
only under the icon"). Once the result is confirmed, this skill turns that whole exchange into
the prompt that would have gotten there **in one pass**, so the user can learn to write it that
way next time.
## Argument forms
```
/todoIdealPrompt # the task most recently confirmed fixed in this session
/todoIdealPrompt #16 # a specific item in the user's todo file; its score goes on the item line, its text stays
/todoIdealPrompt #16 --replace # same, and replace the item's text in that file with the ideal prompt
/todoIdealPrompt #16 --score # the default, asked for explicitly — the score is written even while scores are off
/todoIdealPrompt #16 --no-score # print only — the todo file is not touched
```
## What Claude does
1. **Resolve the task.** `#N` names an item in the user's todo file (`TODO.<name>.md`,
`<name>` from `git config user.name` — the rule in `.claude/prompt-todo/RULES.md`); without
…Read the whole file at its exact version.
How to install
mdr add blackorange0506/prompt-todo/todoIdealPrompt@sha256:66bc0fddfe140999The line at the top of this page pins the label git:20261011.0742d51, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_fhgpcgi3mt6rfygt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 6, 2026 and Oct 11, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261011.0742d51 latest | 2026-10-11 | 0742d51 | 8,451 B | A | view · diff |
| git:20260910.bb50adb | 2026-09-10 | bb50adb | 7,828 B | A | view · diff |
| git:20260907.ced06fe | 2026-09-07 | ced06fe | 7,496 B | A | view · diff |
| git:20260906.6689d67 | 2026-09-06 | 6689d67 | 6,418 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8451 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
blackorange0506/prompt-todo · 4 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fhgpcgi3mt6rfygt GET https://markdownregistry.com/api/v1/resolve?ref=blackorange0506/prompt-todo/todoIdealPrompt GET https://markdownregistry.com/api/v1/blob/66bc0fddfe1409996edf5187329d5d3780f30a0f2ecbd6603b41e4022f2ff76b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.