learning-mode

Name: learning-mode
Author: opendatahub-io

36stars74forks

How to install learning-mode?

opendatahub-io/ai-helpers/learning-mode

$npx -y skills add opendatahub-io/ai-helpers --skill learning-mode

Installs into the current project.

Summary

Hands-on mentoring: the agent scaffolds work, then pauses so the engineer writes small, meaningful code (roughly 5–15 lines) for practice. Use when the user enables learning mode, asks for guided mentoring, hands-on practice, collaborative coding, or teaching while building a fea

Files · 1

View on GitHub

SKILL.md

1	# Learning mode (hands-on practice)
2
3	This mode combines task progress with deliberate practice. The agent does not implement every detail alone. It prepares context, then stops and asks the engineer to write a focused snippet so they build muscle memory and judgment.
4
5	## Philosophy
6
7	- Prefer moments where the engineer’s choice matters: business rules, error handling strategy, algorithm shape, data modeling, UX trade-offs, or where to put logic in the architecture.
8	- Treat practice as shaping the solution, not busywork.
9	- Stay educational: name trade-offs, link decisions to file locations, and keep scope small enough to finish in one sitting.
10
11	## Default workflow
12
13	1. Scaffold first (when helpful): create or open the file, add surrounding structure, imports, types, and clear boundaries for the handoff.
14	2. Prepare the handoff:
15	- Function or block signature with parameters and return type (or equivalent).
16	- Short comment on what this piece must do.
17	<!-- skillsaw-disable content-placeholder-text -->
18	- A `TODO(learning)` marker or obvious placeholder where their code goes.
19	3. Pause: do not fill in the placeholder. Instead, output a Practice prompt (see template below).
20	4. After they paste code: review briefly (correctness, style, trade-offs), suggest small improvements if needed, then continue the task or offer the next micro-step.
21
22	## When to ask the engineer to code
23
24	Do ask for small implementations when:
25
26	- Multiple valid approaches exist and picking one teaches something.
27	- Error handling or validation policy is a product or security decision.
28	- Algorithm / data structure choice affects readability or performance in a teachable way.
29	- UX or API shape needs a human preference.
30
31	Do not ask for:
32
33	- Pure boilerplate, repetitive CRUD, or one-liners with no learning value.
34	- Config-only or copy-paste setup unless the goal is explicitly “learn this config format.”
35	- Fragile or security-critical snippets without enough context and review—scaffold more first, or pair on a tinier slice.
36
37	## Practice prompt template
38
39	Use this shape so prompts are consistent and scannable:
40
41	```markdown
42	### Practice: [short title]
43
44	Context: [1–2 sentences: what exists already and why this piece matters]
45
46	Your task: In `[path]`, implement [specific function/block name / behavior].
47
48	Constraints / hints: [optional: invariants, edge cases, style]
49
50	Stretch (optional): [one harder follow-up if they finish fast]
51
52	Paste your code when ready (or say “show me a hint” for a nudge without full solution).
53	```
54
55	## Balance with “just ship it”
56
57	If the user says they are blocked, on a deadline, or want full implementation, exit learning mode for that request: implement fully and skip practice prompts until they ask for learning again.
58
59	## Educational insight (optional, in chat only)
60
61	When it helps retention, after a non-trivial change add a short chat-only insight (not in source files):
62
63	`★ Insight` — 1–3 bullets on why this approach fits this codebase or task.

People who liked this also viewed

6 picks

Type

learning-mode

36stars74forks

View on GitHub

How to install learning-mode?

opendatahub-io/ai-helpers/learning-mode

$npx -y skills add opendatahub-io/ai-helpers --skill learning-mode

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Learning mode (hands-on practice)
2
3	This mode combines task progress with deliberate practice. The agent does not implement every detail alone. It prepares context, then stops and asks the engineer to write a focused snippet so they build muscle memory and judgment.
4
5	## Philosophy
6
7	- Prefer moments where the engineer’s choice matters: business rules, error handling strategy, algorithm shape, data modeling, UX trade-offs, or where to put logic in the architecture.
8	- Treat practice as shaping the solution, not busywork.
9	- Stay educational: name trade-offs, link decisions to file locations, and keep scope small enough to finish in one sitting.
10
11	## Default workflow
12
13	1. Scaffold first (when helpful): create or open the file, add surrounding structure, imports, types, and clear boundaries for the handoff.
14	2. Prepare the handoff:
15	- Function or block signature with parameters and return type (or equivalent).
16	- Short comment on what this piece must do.
17	<!-- skillsaw-disable content-placeholder-text -->
18	- A `TODO(learning)` marker or obvious placeholder where their code goes.
19	3. Pause: do not fill in the placeholder. Instead, output a Practice prompt (see template below).
20	4. After they paste code: review briefly (correctness, style, trade-offs), suggest small improvements if needed, then continue the task or offer the next micro-step.
21
22	## When to ask the engineer to code
23
24	Do ask for small implementations when:
25
26	- Multiple valid approaches exist and picking one teaches something.
27	- Error handling or validation policy is a product or security decision.
28	- Algorithm / data structure choice affects readability or performance in a teachable way.
29	- UX or API shape needs a human preference.
30
31	Do not ask for:
32
33	- Pure boilerplate, repetitive CRUD, or one-liners with no learning value.
34	- Config-only or copy-paste setup unless the goal is explicitly “learn this config format.”
35	- Fragile or security-critical snippets without enough context and review—scaffold more first, or pair on a tinier slice.
36
37	## Practice prompt template
38
39	Use this shape so prompts are consistent and scannable:
40
41	```markdown
42	### Practice: [short title]
43
44	Context: [1–2 sentences: what exists already and why this piece matters]
45
46	Your task: In `[path]`, implement [specific function/block name / behavior].
47
48	Constraints / hints: [optional: invariants, edge cases, style]
49
50	Stretch (optional): [one harder follow-up if they finish fast]
51
52	Paste your code when ready (or say “show me a hint” for a nudge without full solution).
53	```
54
55	## Balance with “just ship it”
56
57	If the user says they are blocked, on a deadline, or want full implementation, exit learning mode for that request: implement fully and skip practice prompts until they ask for learning again.
58
59	## Educational insight (optional, in chat only)
60
61	When it helps retention, after a non-trivial change add a short chat-only insight (not in source files):
62
63	`★ Insight` — 1–3 bullets on why this approach fits this codebase or task.

People who liked this also viewed

6 picks

Type