Shape User Idea
SkillSearchLets your agent turn an idea you have into a confirmed written idea file for your project journal.
Use Shape User Idea in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Shape User Idea and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Shape User Idea skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Shape an idea the user already has, or answer a project question, and write one idea file after they confirm. A topic with no artifact belongs to search-ml-literature. Do not write JOURNAL.md or a design note. Do not pick a backlog row.
What this skill tells your AI
The instructions your AI receives, as published by probabl-ai/skills in skills/shape-user-idea/SKILL.md and read by Ahel’s review.
Comes after review, beside the backlog. The user already has an
idea, a question, or an artifact. This skill writes
journal/ideas/<slug>.md only after they confirm. The backlog
triages that file later.
Human-facing prose
Details: setup-workspace references/human_facing_prose.md.
Questions and the confirmation paragraph describe this idea in
data-science terms — not skill ids or the wrapper CLI.
Procedure
- Run
python -m skore_skills status. Readjournal/JOURNAL.mdStatus and History, anddata_analysis/data_analysis.mdwhen it exists. - If the entry is not already a concrete idea, question, or artifact, AskUserQuestion: free-text or artifact. A URL, issue, path, or stated idea skips that menu.
- A question about this project is answered from those files.
Leave an unknown metric as
n/a. Write no idea file and return to the caller. - A topic with no artifact ("what do people do for …") loads
search-ml-literatureonly ifstatus.skills.search-ml-literatureis true. Otherwise one-line skip. Do notWebSearchfor a paper from here. - An artifact is read, not reconstructed. Paper or doc URL:
WebFetchthe page. GitHub issue:gh auth statusfirst; if unauthenticated, ask the user to rungh auth loginor paste the body. Thengh issue view. Resolution: explicit URL, thenorg/repo#N, then bare#Nonly in the currentghrepo — otherwise ask. Spec or notes file: read that file only. - Walk three questions. Do not fabricate a missing answer.
- What are we trying to learn?
- Why now? Quote the user or the artifact.
- What changes versus the last experiment, in prose?
- If the idea changes the project goal in
journal/JOURNAL.mdStatus, ask before writing the file. A library the source names and the user has not agreed to add stays in Open gaps. A domain claim this dataset does not establish stays in Open gaps. - Restate the idea in one short paragraph and wait for an explicit yes. "Maybe" is not yes. No or stop writes nothing.
- On yes, the only file this skill writes is
journal/ideas/<slug>.md. Do not create or editjournal/JOURNAL.mdor a design note. Writejournal/ideas/<slug>.md:
# <slug>
- Experiment: <last History stem, or n/a>
- Source: user
- Triage: open
- Question:
- Why now:
- What changes:
- Open gaps:
Why now carries the quote, URL, or path. No acceptance
criteria. Return the path to the caller (manage-ml-backlog
or triage-ml-task).
Stop conditions
- Do not write
JOURNAL.mdor a design note. - Do not append a
B<N>row. The backlog triages the file. - Do not invent source content from a title.
- Do not
WebSearchfor a topic with no artifact. - The entry question and the confirmation paragraph are required gates.
- If the user already asked to add a named library, put it in
What changes and load
add-python-packagewhen that skill is installed. Do notpixi addfrom here.
Signals
- GitHub stars
- 137
- Forks
- 9
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
shape-user-idea- Source
- github.com/probabl-ai/skills