Updated 2w ago
by NVlabs
ASPIRE
ASPIRE: Agentic /Skills Discovery for Robotics
956 GitHub stars (956)
+718 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | +1 |
| Oct 2 | +1 |
| Oct 3 | +5 |
| Oct 4 | 0 |
| Oct 5 | +2 |
| Oct 6 | +3 |
| Oct 7 | +4 |
| Oct 8 | +3 |
| Oct 9 | +4 |
| Oct 10 | +7 |
| Oct 11 | +3 |
| Oct 12 | +4 |
| Oct 13 | +8 |
| Oct 14 | +2 |
| Oct 15 | +6 |
| Oct 16 | +2 |
| Oct 17 | +170 |
| Oct 18 | +14 |
| Oct 19 | +87 |
| Oct 20 | +140 |
| Oct 21 | +105 |
| Oct 22 | +8 |
| Oct 23 | +26 |
| Oct 24 | +22 |
| Oct 25 | +9 |
| Oct 26 | +4 |
| Oct 27 | +14 |
| Oct 28 | +13 |
| Oct 29 | +10 |
| Oct 30 | +11 |
| Oct 31 | 0 |
| Nov 1 | +4 |
| Nov 2 | +7 |
| Nov 3 | +13 |
| Nov 4 | +8 |
| Nov 5 | +10 |
- 5 skills (5 skills found in its SKILL.md files)
- 86 forks (86 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add NVlabs/ASPIRE
Asks which skills and agents to install. Just one: npx skills add NVlabs/ASPIRE --skill cap-tool-usage — add -g for every project.
Claude Code
git clone https://github.com/NVlabs/ASPIREcp -r "ASPIRE/.agents/skills/cap-tool-usage" ~/.claude/skills/
Copies the cap-tool-usage skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add NVlabs/ASPIRE
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
cap-tool-usage
Localize objects and compose low-level CAP MCP actions using observations, Cartesian or synchronized motion, joint targets, and single-arm gripper control.
.agents/skills/ on GitHub (opens in a new tab)cap-tool-usage/ SKILL.md -
manipulation-tasks
Perform task-specific real YAM manipulation with native CAP tools. Use for solving or turning a physical Rubik's Cube, bottle-cap removal and pouring, pill insertion and bottle closure, or inverted cup nesting.
.agents/skills/ on GitHub (opens in a new tab)manipulation-tasks/ SKILL.md -
evosearch
Run the CaP Fix Loop + Evolutionary Search experiment on a user-supplied list of low-performing benchmark tasks: iterative K=8 candidate search on development seeds 51–65, validation selection, and final held-out evaluation on seeds 1–50.
.claude/skills/ on GitHub (opens in a new tab)evosearch/ SKILL.md -
iterative-debugging
Run the baseline-free CaP iterative debugging (fix loop) pipeline on a user-supplied list of benchmark tasks: inspect one initial observed scene per task, generate task-level code, debug failures on development seeds using recorded run artifacts, validate on the held-out partition, grade the skill library against what actually worked, and promote only those patterns a verifier could reproduce the…
.claude/skills/ on GitHub (opens in a new tab)iterative-debugging/ SKILL.md -
iterative-debugging-behavior
Block-by-block fix loop on BEHAVIOR-1K (R1 Pro, OmniGibson on Isaac Sim). The policy is grown one code block at a time against what the robot actually did, and what carries across seeds is a skill library, not a program. Use for the two R1 Pro pickup tasks; Stage 1 learns on seeds 26-35, Stage 2 evaluates on 1-25 with a frozen library.
.claude/skills/ on GitHub (opens in a new tab)iterative-debugging/ behavior/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.