repo-intake-and-plan

Name: repo-intake-and-plan
Author: lllllllama

161kinstalls10forks

How to install repo-intake-and-plan?

lllllllama/rigorpilot-skills/repo-intake-and-plan

$npx -y skills add lllllllama/RigorPilot-Skills --skill repo-intake-and-plan

Installs into the current project.

Summary

Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest tr

Files · 1

View on GitHub

SKILL.md

1	# repo-intake-and-plan
2
3	Use this as the Rigor Intake helper. The installed slug remains
4	`repo-intake-and-plan` for compatibility.
5
6	## When to apply
7
8	- At the beginning of README-first reproduction work.
9	- When the main skill needs a fast map of repo structure and documented commands.
10	- When inference, evaluation, and training candidates must be classified conservatively.
11	- When the user explicitly wants to inspect the repo first and not run anything yet.
12
13	## When not to apply
14
15	- When execution has already started and the task is now about running commands or writing outputs.
16	- When the target is not a repository-backed reproduction task.
17	- When the user only wants paper interpretation without repo inspection.
18	- When the user already has a selected documented command and only needs setup or execution.
19
20	## Clear boundaries
21
22	- This skill scans and plans.
23	- This skill is helper-tier and should usually be orchestrator-invoked.
24	- It does not install environments.
25	- It does not prepare large assets.
26	- It does not execute substantive reproduction commands.
27	- It does not decide high-risk patching.
28
29	## Input expectations
30
31	- Target repository path.
32	- Access to README and common project files if present.
33	- Optional user hints about desired priority, such as inference-first.
34
35	## Output expectations
36
37	- concise repo structure summary
38	- documented command inventory
39	- inferred candidate categories: inference, evaluation, training, other
40	- minimum trustworthy reproduction recommendation
41	- notable ambiguity or risk list
42
43	## Notes
44
45	Use `references/repo-scan-rules.md` and helper scripts under `scripts/`.

People who liked this also viewed

6 picks

Type

repo-intake-and-plan

161kinstalls10forks

View on GitHub

How to install repo-intake-and-plan?

lllllllama/rigorpilot-skills/repo-intake-and-plan

$npx -y skills add lllllllama/RigorPilot-Skills --skill repo-intake-and-plan

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# repo-intake-and-plan
2
3	Use this as the Rigor Intake helper. The installed slug remains
4	`repo-intake-and-plan` for compatibility.
5
6	## When to apply
7
8	- At the beginning of README-first reproduction work.
9	- When the main skill needs a fast map of repo structure and documented commands.
10	- When inference, evaluation, and training candidates must be classified conservatively.
11	- When the user explicitly wants to inspect the repo first and not run anything yet.
12
13	## When not to apply
14
15	- When execution has already started and the task is now about running commands or writing outputs.
16	- When the target is not a repository-backed reproduction task.
17	- When the user only wants paper interpretation without repo inspection.
18	- When the user already has a selected documented command and only needs setup or execution.
19
20	## Clear boundaries
21
22	- This skill scans and plans.
23	- This skill is helper-tier and should usually be orchestrator-invoked.
24	- It does not install environments.
25	- It does not prepare large assets.
26	- It does not execute substantive reproduction commands.
27	- It does not decide high-risk patching.
28
29	## Input expectations
30
31	- Target repository path.
32	- Access to README and common project files if present.
33	- Optional user hints about desired priority, such as inference-first.
34
35	## Output expectations
36
37	- concise repo structure summary
38	- documented command inventory
39	- inferred candidate categories: inference, evaluation, training, other
40	- minimum trustworthy reproduction recommendation
41	- notable ambiguity or risk list
42
43	## Notes
44
45	Use `references/repo-scan-rules.md` and helper scripts under `scripts/`.

People who liked this also viewed

6 picks

Type