Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
validate-addon
Validate an entire AIWG addon package for completeness and release readiness
jmagly/aiwg 107
-
devkit-validate
Validate addon, framework, or extension structure and manifest
jmagly/aiwg 107
-
dev-doctor
Run a development-focused health check on the AIWG repository structure
jmagly/aiwg 107
-
devkit-create-agent
Create a new agent with AI-guided expertise definition following the Agent Design Bible
jmagly/aiwg 107
-
devkit-create-skill
Enable interactive design mode
jmagly/aiwg 107
-
devkit-test
Auto-fix discoverable issues
jmagly/aiwg 107
-
devkit-create-command
Create a new slash command with AI-guided behavior definition
jmagly/aiwg 107
-
rlm-mode
Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
jmagly/aiwg 107
-
rlm-search
jmagly/aiwg 107
-
rlm-query
jmagly/aiwg 107
-
rlm-prep
jmagly/aiwg 107
-
chunk
jmagly/aiwg 107
-
rlm-status
Show status of RLM task tree execution
jmagly/aiwg 107
-
fanout
jmagly/aiwg 107
-
rlm-batch
jmagly/aiwg 107
-
ralph-external
Crash-resilient external loop with state persistence and CI/CD integration
jmagly/aiwg 107
-
ralph-resume
jmagly/aiwg 107
-
ralph-abort
jmagly/aiwg 107
-
execute-feedback
Execute tests on generated code and iterate until passing
jmagly/aiwg 107
-
auto-test-execution
jmagly/aiwg 107
-
ralph-reflect
View and manage agent loop reflections and episodic memory
jmagly/aiwg 107
-
ralph-analytics
Show analytics and metrics from agent loop execution history
jmagly/aiwg 107
-
reflection-injection
jmagly/aiwg 107
-
mission-control
jmagly/aiwg 107