SkillClawAMAP-ML/SkillClaw
Enables AI agents to turn approaches discovered during tasks into reusable skills that are automatically invoked and ref…
No ratings yet
Rate this skill
Stars2.7k
Forks267
Watchers2.7k
Open Issues43
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/AMAP-ML/SkillClaw.git
OverviewOverview
Key Features
Enables AI agents to turn approaches discovered during tasks into reusable skills that are automatically invoked and refined in later sessions, solving the problem that agent experience cannot persist across sessions and similar problems are repeatedly solved from scratch. Key capabilities include: 1. Skill capture: organizes the operation paths an agent forms during tasks into structured skill entries and stores them, turning one-off experience into repeatedly callable assets; 2. Skill retrieval and activation: matches existing skills to the scenario at the start of a new task and injects them into the agent context, reducing repeated exploration and wasted trial and error; 3. Skill evolution: revises and versions existing skills based on later usage feedback, so the skill library becomes more accurate over time; 4. Skill sharing: organizes skill entries in a unified format so the same skill assets can be reused across multiple agents or team members.
Use Cases
experience accumulation during long-running agent operation, fast reuse of skills for similar tasks, unified maintenance of team-internal skill conventions, continuous improvement of agent capability through use.
Target Roles
AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer, DevOps / Operations Engineer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 367 |
|---|---|
| Data source | GitHub |
| Repository | AMAP-ML/SkillClaw |
| Category | AI & Agents / Agent Skills & Tools |
| Primary language | Python |
| License | MIT License |
| Default branch | main |
| GitHub repository ID | 1206566990 |
| Node ID | R_kgDOR-rATg |
| Rank | #361 (position within the source ranking) |
| Site-wide popularity rank | #430 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now2,681
- Previous point · 09-30 2,654
- vs previous point +27
- 2 data points 11 days
- Now267
- Previous point · 09-30 264
- vs previous point +3
- 2 data points 11 days
TimelineTimeline
Repository created2026-04-10 03:25:477 months ago
Data last updated2026-10-26 11:56:5722 days ago
Last commit2026-08-17 08:48:073 months ago
CommitLatest commit
Committed by Upper9527. Update Category: Bug Fixes & Stability Improvements. Commit details: fix: allow dashboard status without LLM key (#83). This update resolves known runtime errors and enhances system reliability.