Topic: prompt-engineering
2,538 skills in this topic.
-
flow-inception-to-elaboration
jmagly/aiwg 107
-
aiwg-refresh
Update AIWG CLI and redeploy frameworks/tools to current project without leaving the session
jmagly/aiwg 107
-
prose-detect
Locate an existing OpenProse installation using a prioritized signal chain — env var, AIWG config, AIWG-local install, project plugin manifest, user home directory, or global CLI. Returns the resolved PROSE_ROOT path. Does not install OpenProse; triggers prose-setup if no installation is found.
jmagly/aiwg 107
-
prose-install
Install OpenProse for AIWG use when no existing installation is found. Tries npx skills add first, falls back to git clone, then saves the resolved path to .aiwg/config.json.
jmagly/aiwg 107
-
flaky-detect
Identify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.
jmagly/aiwg 107
-
flaky-fix
Suggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
jmagly/aiwg 107
-
ralph-external
Crash-resilient external loop with state persistence and CI/CD integration
jmagly/aiwg 107
-
prose-reader
Read and parse an OpenProse program file, extracting its contract (requires, ensures, strategies, errors, invariants) and services into a structured representation
jmagly/aiwg 107
-
hook-regenerate
Rebuild AIWG hook files from currently installed framework manifests
jmagly/aiwg 107
-
uat-execute
Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
jmagly/aiwg 107
-
pipeline-design
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
jmagly/aiwg 107
-
ralph-config
View and configure agent loop settings — show, set, reset, and apply named presets
jmagly/aiwg 107
-
cost-optimizer
Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
jmagly/aiwg 107
-
eval-loop
Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
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-analytics
Show analytics and metrics from agent loop execution history
jmagly/aiwg 107
-
skill-enhancer
AI-powered enhancement of skill SKILL.md files. Use to transform basic templates into comprehensive, high-quality skill documentation.
jmagly/aiwg 107
-
skill-packager
Package skills into uploadable ZIP files for Claude. Use after skill-builder/skill-enhancer to create final upload package.
jmagly/aiwg 107
-
ralph-attach
Attach to a running agent loop's live output stream
jmagly/aiwg 107
-
tot-decide
Evaluate architectural decisions using Tree of Thoughts exploration
jmagly/aiwg 107
-
debug-memory
Query and manage the executable feedback debug memory
jmagly/aiwg 107
-
flow-risk-management-cycle
jmagly/aiwg 107
-
aiwg-update-agents-md
jmagly/aiwg 107
-
devkit-create-skill
Enable interactive design mode
jmagly/aiwg 107