jmagly
- 236 skills
- 0 followers
- 3 hours ago last updated
- ▌ Chunk · jmaglySplit a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
- ▌ Fanout · jmaglyDispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
- ▌ Chunk 2 · jmaglySplit a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
- ▌ Fanout 2 · jmaglyDispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
- ▌ Rlm Mode · jmaglyDetect requests for recursive decomposition and large-scale operations that benefit from RLM processing
- ▌ Rlm Prep · jmaglyPrepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
- ▌ Rlm Batch · jmaglyParallel fan-out processing - spawn multiple sub-agents for chunked context processing
- ▌
- ▌ Rlm Mode 2 · jmaglyDetect requests for recursive decomposition and large-scale operations that benefit from RLM processing
- ▌ Rlm Prep 2 · jmaglyPrepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
- ▌ Rlm Search · jmaglyRun the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
- ▌
- ▌ Rlm Batch 2 · jmaglyParallel fan-out processing - spawn multiple sub-agents for chunked context processing
- ▌
- ▌ Rlm Search 2 · jmaglyRun the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
- ▌
- ▌ Ralph · jmaglyExecute iterative task loop until completion criteria are met - iteration beats perfection
- ▌ LLM Wiki · jmaglyEnable and configure the llm-wiki addon for long-term, long-form project memory, select a wiki profile, and route ingestion and health checks through the knowledge-base and semantic-memory capabilities.
- ▌ Ralph 2 · jmaglyExecute iterative task loop until completion criteria are met - iteration beats perfection
- ▌ Eval Loop · jmaglyConfigure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
- ▌ Uat Report · jmaglyGenerate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection
- ▌ LLM Wiki 2 · jmaglyEnable and configure the llm-wiki addon for long-term, long-form project memory, select a wiki profile, and route ingestion and health checks through the knowledge-base and semantic-memory capabilities.
- ▌
- ▌ Link Check · jmaglyVerify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
- ▌ Uat Execute · jmaglyExecute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
- ▌ Eval Loop 2 · jmaglyConfigure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
- ▌
- ▌ Uat Generate · jmaglyDiscover MCP tools and generate a phased UAT plan with agent-executable test specifications
- ▌
- ▌ Link Check 2 · jmaglyVerify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
- ▌ Agent Loop · jmagly bundleDetect requests for iterative autonomous agent loops and route to the appropriate loop executor
- ▌ Eval Agent · jmaglyRun evaluation tests against an agent to assess quality and archetype resistance
- ▌ Aiwg Hooks · jmaglyInstall, configure, and inspect AIWG lifecycle hooks for tracing, permissions, session management, context injection, and quality gates.
- ▌
- ▌
- ▌ Dev Mode Init · jmaglySwitch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
- ▌ Eval Report · jmaglyGenerate an aggregate agent quality report from evaluation results, showing scores, regressions, and recommendations
- ▌ Productionize · jmaglyProduction readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
- ▌ Agent Loop 2 · jmagly bundleDetect requests for iterative autonomous agent loops and route to the appropriate loop executor
- ▌
- ▌
- ▌ Ralph Config · jmaglyView and configure agent loop settings — show, set, reset, and apply named presets
- ▌ Ralph Memory · jmaglyManage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
- ▌
- ▌
- ▌ Validate Addon · jmaglyValidate an entire AIWG addon package for completeness and release readiness
- ▌ Auto Memory · jmaglyConfigure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
- ▌ Cost Optimizer · jmaglyAnalyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
- ▌
- ▌ Dev Mode Init 2 · jmaglySwitch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
- ▌ Productionize 2 · jmaglyProduction readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
- ▌
- ▌
- ▌ Eval Workflow · jmaglyRun evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance
- ▌ Pipeline Design · jmaglyInteractive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
- ▌
- ▌ Prompt Engineer · jmaglyProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- ▌
- ▌
- ▌ Ralph Config 2 · jmaglyView and configure agent loop settings — show, set, reset, and apply named presets
- ▌ Ralph Memory 2 · jmaglyManage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
- ▌
- ▌
- ▌ Validate Addon 2 · jmaglyValidate an entire AIWG addon package for completeness and release readiness
- ▌ Auto Memory 2 · jmaglyConfigure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
- ▌ Cost Optimizer 2 · jmaglyAnalyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
- ▌
- ▌ Agent Loop Ext · jmaglyCrash-resilient external agent loop with state persistence and CI/CD integration
- ▌
- ▌ Droid Bridge · jmaglyConfigure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.
- ▌ Pattern Selector · jmaglyRecommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
- ▌ Premortem V2 · jmaglyRun a diversity-first premortem with bounded deep dives, blind plausibility and impact verification, and explicit provenance labels.
- ▌ Flaky Fix · jmaglySuggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
- ▌ Test Sync · jmaglyDetect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
- ▌
- ▌
- ▌ Issue Planner · jmaglyResearch-grounded SDLC issue planner — dispatches parallel research, generates the supporting doc corpus, then files prioritized cross-referenced issues for human review.
- ▌ Pipeline Design 2 · jmaglyInteractive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
- ▌ Pipeline Status 2 · jmaglyShow status overview of all LLM inference pipelines in the current project
- ▌ Prompt Engineer 2 · jmaglyProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- ▌
- ▌ Agent Loop Ext 2 · jmaglyCrash-resilient external agent loop with state persistence and CI/CD integration
- ▌ Droid Bridge 2 · jmaglyConfigure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.
- ▌ Pattern Selector 2 · jmaglyRecommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
- ▌ Flaky Fix 2 · jmaglySuggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
- ▌ Test Sync 2 · jmaglyDetect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
- ▌
- ▌
- ▌ Validate Component · jmaglyValidate a single AIWG component (skill, agent, or command) for completeness and correctness
- ▌ Prose Run · jmaglyExecute an OpenProse program within the current AIWG session, following the two-phase model (Forme wiring + Prose VM execution)
- ▌ Tdd Enforce · jmagly bundleConfigure TDD enforcement via pre-commit hooks and CI coverage gates. Use when setting up test-first workflows or adding coverage gates.
- ▌
- ▌ Color Trends · jmaglyResearch current color trends from Pantone, architecture, film, and design. Use when user asks about trending colors, popular palettes, or wants research-backed color inspiration.
- ▌ Portable Complete · jmagly bundleUse this complete portable fixture to verify Agent Skills round trips.
- ▌
- ▌ Devkit Create Agent · jmaglyCreate a new agent with AI-guided expertise definition following the Agent Design Bible
- ▌
- ▌ Flaky Detect · jmaglyIdentify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.
- ▌
- ▌ Setup Run 2 · jmaglyExecute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati