Topic: prompt-engineering
2,538 skills in this topic.
-
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-attach
Attach to a running agent loop's live output stream
jmagly/aiwg 107
-
pipeline-design
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
jmagly/aiwg 107
-
flow-change-control
jmagly/aiwg 107
-
flow-architecture-evolution
jmagly/aiwg 107
-
doc-sync
Synchronize documentation and code to eliminate drift with parallel audit, auto-fix, and Al refinement
jmagly/aiwg 107
-
doc-consolidate
Crawl repository for scattered docs and consolidate into categorized reference index in .aiwg/docs/
jmagly/aiwg 107
-
decompose-file
jmagly/aiwg 107
-
decision-support
jmagly/aiwg 107
-
create-prd
jmagly/aiwg 107
-
corpus-health
Report on research corpus health, completeness, and integrity
jmagly/aiwg 107
-
contract-validate
jmagly/aiwg 107
-
contract-manifest
jmagly/aiwg 107
-
complexity-gate
jmagly/aiwg 107
-
codebase-health
jmagly/aiwg 107
-
code-chunker
jmagly/aiwg 107
-
cleanup-audit
jmagly/aiwg 107
-
citation-guard
jmagly/aiwg 107
-
citation-check
Check a file for citation quality and GRADE compliance
jmagly/aiwg 107
-
check-traceability
jmagly/aiwg 107
-
validate-metadata
jmagly/aiwg 107
-
version
jmagly/aiwg 107
-
flow-discovery-track
Orchestrate Discovery Track flow to prepare validated requirements and designs one iteration ahead of delivery
jmagly/aiwg 107
-
flow-deploy-to-production
jmagly/aiwg 107