Topic: developer-tools
13,276 skills in this topic.
-
quality-assess
Perform GRADE quality assessment on a research source
jmagly/aiwg 107
-
codebase-health
jmagly/aiwg 107
-
cleanup-audit
jmagly/aiwg 107
-
intake-from-codebase
Scan existing codebase and generate intake documents by analyzing code, dependencies, and infrastructure. Accepts optional guidance text to tailor analysis.
jmagly/aiwg 107
-
chunk
jmagly/aiwg 107
-
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
jmagly/aiwg 107
-
provenance-validate
Validate provenance records and chains for completeness and consistency
jmagly/aiwg 107
-
competitive-analysis
jmagly/aiwg 107
-
quality-checker
Validate skill quality, completeness, and adherence to standards. Use before packaging to ensure skill meets quality requirements.
jmagly/aiwg 107
-
eval-loop
Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
jmagly/aiwg 107
-
iteration-control
jmagly/aiwg 107
-
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
jmagly/aiwg 107
-
voice-blend
jmagly/aiwg 107
-
pattern-selector
Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
jmagly/aiwg 107
-
ralph-config
View and configure agent loop settings — show, set, reset, and apply named presets
jmagly/aiwg 107
-
validate-component
Validate a single AIWG component (skill, agent, or command) for completeness and correctness
jmagly/aiwg 107
-
rlm-mode
Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
jmagly/aiwg 107
-
soul-enhance
jmagly/aiwg 107
-
devkit-create-extension
Create a new AIWG extension (framework expansion pack) with AI-guided setup
jmagly/aiwg 107
-
brand-audit
jmagly/aiwg 107
-
regression-report
jmagly/aiwg 107
-
voice-apply
Applies a voice profile to transform content. Use when user asks to write in a specific voice, match a tone, apply a style, or transform content to sound like a particular voice profile.
jmagly/aiwg 107
-
regression-learning
jmagly/aiwg 107
-
address-issues
Address open issues using issue-thread-driven agent loops with 2-way human-AI collaboration
jmagly/aiwg 107