graft

Name: graft
Author: Rune-kit

80stars21forks

How to install graft?

rune-kit/rune/graft

$npx -y skills add Rune-kit/rune --skill graft

Installs into the current project.

Summary

Clone, port, or convert features from any GitHub repo into your project. Use when stealing patterns from external repos or porting proven code. Understand before copy, challenge before implement. 4 modes: port (rewrite), compare (analysis), copy (transplant), improve (copy + opti

Files · 1

View on GitHub

SKILL.md

1	# graft
2
3	## Purpose
4
5	External code intelligence — structured workflow for learning from, adapting, and integrating features from any public repository into your project. Graft is NOT a copy-paste tool. It enforces understanding before adoption through a mandatory challenge gate that evaluates license compatibility, stack fit, scope, quality, and maintenance health before any code touches your codebase.
6
7	## Core Rule: The Tree is a Menu, Not the Meal
8
9	When you clone a repo you see hundreds of files. That tree is a menu — options to order from, not a meal to eat. Grafting the whole tree is how context windows die and foreign patterns leak into your codebase.
10
11	- Read the README + the 2-5 files that implement the target feature. Skip the rest.
12	- If you cannot name the specific files you need before reading, you do not know what you want yet — go back to Step 0 and narrow scope.
13	- `WebFetch` on raw GitHub URLs beats `git clone` whenever you know the exact files. Use clone only when discovery is genuinely needed.
14
15	Reading to understand is not grafting. The discipline above caps the graft scope — the files you actually transplant, port, or improve into your codebase (2-5, hard-cap 10). It does NOT cap how many files you may read to learn a pattern. Studying a 24-skill library to extract one convention legitimately reads dozens of files but grafts almost none. Keep the two counts separate: a wide read with a narrow graft is thorough; a wide graft is the failure mode.
16
17	This menu discipline applies to the transplant modes (port, copy, improve). Copy mode is not an excuse to import a directory wholesale — you still select files deliberately. Compare mode and survey scope (`--deep`) are exempt from the read cap by design: their job is breadth of understanding, not transplant. They still must NOT import code wholesale — wide reading, narrow (or zero) graft.
18
19	<HARD-GATE>
20	Challenge gate (Step 4) MUST complete before adaptation planning (Step 5).
21	No implementation without confronting trade-offs. This applies to ALL modes except compare.
22	Skip only with --fast flag (user accepts full responsibility).
23	</HARD-GATE>
24
25	## Modes
26
27	### Port (default)
28	Rewrite the target feature using YOUR stack and patterns. Source code is a reference, not a template. Output is idiomatic to your codebase.
29
30	When: Different tech stack (Vue→React, Django→FastAPI), or source patterns conflict with your conventions.
31
32	### Compare
33	Side-by-side analysis only. No code changes. Outputs a structured comparison report.
34
35	When: Evaluating whether to adopt a feature, benchmarking your implementation against another, or learning patterns without importing code.
36
37	### Copy
38	Pure transplant with minimal adaptation. Stays as close to the original as possible — only changes imports, paths, and config to fit your project structure.
39
40	When: Same tech stack, source code is high quality, you want the exact implementation.
41
42	### Improve
43	Copy the feature, then refactor and optimize. Fix anti-patterns, add missing tests, adapt to your codebase conventions, upgrade deprecated APIs.
44
45	When: Same stack but source has quality issues, or you want the feature but better.
46
47	## Speed Options
48
49	\| Flag \| Research \| Challenge Gate \| User Approval \|
50	\|------\|----------\|---------------\|---------------\|
51	\| (default) \| ✅ Full \| ✅ Yes \| ✅ Each step \|
52	\| `--auto` \| ✅ Full \| ✅ Yes \| ❌ Auto-approve \|
53	\| `--fast` \| ❌ Skip \| ❌ Skip \| ❌ Auto-approve \|
54
55	`--fast` warning: Skipping challenge gate means no license check, no quality assessment. User accepts full responsibility. Announce: "Fast mode: skipping challenge gate. You are responsible for license and quality review."
56
57	## Scope Depth
58
59	Orthogonal to mode and speed. Controls how widely you may read.
60
61	\| Scope \| Read budget \| Graft scope \| When \|
62	\|-------\|-------------\|-------------\|------\|
63	\| (default) \| 2-5 files, hard-cap 10 \| the feature's files \| Transplant one feature/module \|
64	\| `--deep` (survey) \| unbounded reads, full clone OK \| narrow — patterns extracted, not files copied \| Study a whole repo/library to learn architecture or compare many components \|
65
66	`--deep` is for understanding, not importing. Use it when the goal is "what can I learn from this repo" rather than "port this function." Pairs naturally with `compare` mode. It relaxes the read cap and the scope-guard warning — but the transplant discipline still holds: extract the pattern, then graft narrowly (often into multiple existing

People who liked this also viewed

6 picks

Type

graft

80stars21forks

View on GitHub

How to install graft?

rune-kit/rune/graft

$npx -y skills add Rune-kit/rune --skill graft

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# graft
2
3	## Purpose
4
5	External code intelligence — structured workflow for learning from, adapting, and integrating features from any public repository into your project. Graft is NOT a copy-paste tool. It enforces understanding before adoption through a mandatory challenge gate that evaluates license compatibility, stack fit, scope, quality, and maintenance health before any code touches your codebase.
6
7	## Core Rule: The Tree is a Menu, Not the Meal
8
9	When you clone a repo you see hundreds of files. That tree is a menu — options to order from, not a meal to eat. Grafting the whole tree is how context windows die and foreign patterns leak into your codebase.
10
11	- Read the README + the 2-5 files that implement the target feature. Skip the rest.
12	- If you cannot name the specific files you need before reading, you do not know what you want yet — go back to Step 0 and narrow scope.
13	- `WebFetch` on raw GitHub URLs beats `git clone` whenever you know the exact files. Use clone only when discovery is genuinely needed.
14
15	Reading to understand is not grafting. The discipline above caps the graft scope — the files you actually transplant, port, or improve into your codebase (2-5, hard-cap 10). It does NOT cap how many files you may read to learn a pattern. Studying a 24-skill library to extract one convention legitimately reads dozens of files but grafts almost none. Keep the two counts separate: a wide read with a narrow graft is thorough; a wide graft is the failure mode.
16
17	This menu discipline applies to the transplant modes (port, copy, improve). Copy mode is not an excuse to import a directory wholesale — you still select files deliberately. Compare mode and survey scope (`--deep`) are exempt from the read cap by design: their job is breadth of understanding, not transplant. They still must NOT import code wholesale — wide reading, narrow (or zero) graft.
18
19	<HARD-GATE>
20	Challenge gate (Step 4) MUST complete before adaptation planning (Step 5).
21	No implementation without confronting trade-offs. This applies to ALL modes except compare.
22	Skip only with --fast flag (user accepts full responsibility).
23	</HARD-GATE>
24
25	## Modes
26
27	### Port (default)
28	Rewrite the target feature using YOUR stack and patterns. Source code is a reference, not a template. Output is idiomatic to your codebase.
29
30	When: Different tech stack (Vue→React, Django→FastAPI), or source patterns conflict with your conventions.
31
32	### Compare
33	Side-by-side analysis only. No code changes. Outputs a structured comparison report.
34
35	When: Evaluating whether to adopt a feature, benchmarking your implementation against another, or learning patterns without importing code.
36
37	### Copy
38	Pure transplant with minimal adaptation. Stays as close to the original as possible — only changes imports, paths, and config to fit your project structure.
39
40	When: Same tech stack, source code is high quality, you want the exact implementation.
41
42	### Improve
43	Copy the feature, then refactor and optimize. Fix anti-patterns, add missing tests, adapt to your codebase conventions, upgrade deprecated APIs.
44
45	When: Same stack but source has quality issues, or you want the feature but better.
46
47	## Speed Options
48
49	\| Flag \| Research \| Challenge Gate \| User Approval \|
50	\|------\|----------\|---------------\|---------------\|
51	\| (default) \| ✅ Full \| ✅ Yes \| ✅ Each step \|
52	\| `--auto` \| ✅ Full \| ✅ Yes \| ❌ Auto-approve \|
53	\| `--fast` \| ❌ Skip \| ❌ Skip \| ❌ Auto-approve \|
54
55	`--fast` warning: Skipping challenge gate means no license check, no quality assessment. User accepts full responsibility. Announce: "Fast mode: skipping challenge gate. You are responsible for license and quality review."
56
57	## Scope Depth
58
59	Orthogonal to mode and speed. Controls how widely you may read.
60
61	\| Scope \| Read budget \| Graft scope \| When \|
62	\|-------\|-------------\|-------------\|------\|
63	\| (default) \| 2-5 files, hard-cap 10 \| the feature's files \| Transplant one feature/module \|
64	\| `--deep` (survey) \| unbounded reads, full clone OK \| narrow — patterns extracted, not files copied \| Study a whole repo/library to learn architecture or compare many components \|
65
66	`--deep` is for understanding, not importing. Use it when the goal is "what can I learn from this repo" rather than "port this function." Pairs naturally with `compare` mode. It relaxes the read cap and the scope-guard warning — but the transplant discipline still holds: extract the pattern, then graft narrowly (often into multiple existing

People who liked this also viewed

6 picks

Type