all publishers

jmagly

@jmagly source repo

454 published skills · page 3 of 5

  1. ▌
    Schema Review 2 · jmagly
    Review a schema or data-contract change for authority, correctness, compatibility, fixtures, security, and projection integrity.
    229 repo stars
  2. ▌
    Auto Test Execution 4 · jmagly
    Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
    229 repo stars
  3. ▌
    Devkit Create Command 4 · jmagly
    Create a new slash command with AI-guided behavior definition
    229 repo stars
  4. ▌
    Browser Doctor 4 · jmagly
    Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
    229 repo stars
  5. ▌
    Prose Detect 4 · jmagly
    Locate an existing OpenProse installation via env var, AIWG config, local install, plugin manifest, or global CLI. Returns PROSE_ROOT; triggers prose-install if not found.
    229 repo stars
  6. ▌
    Prose Reader 4 · jmagly
    Read and parse an OpenProse program file, extracting its contract (requires, ensures, strategies, errors, invariants) and services into a structured representation
    229 repo stars
  7. ▌
    Setup Generate 3 · jmagly
    Generate a `setup.manifest.yaml` file for a project using the `setup.aiwg.io/v1`
    229 repo stars
  8. ▌
    Setup Validate 3 · jmagly
    Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons
    229 repo stars
  9. ▌
    Devkit Create Extension 3 · jmagly
    Create a new AIWG extension (framework expansion pack) with AI-guided setup
    229 repo stars
  10. ▌
    Devkit Create Framework 3 · jmagly
    Comma-separated phase names
    229 repo stars
  11. ▌
    Civic Newsroom Plan 2 · jmagly
    Plan an evidence-bound civic newsroom workflow with provenance, privacy, citation, correction, accessibility, and human publication gates.
    229 repo stars
  12. ▌
    Public Records Plan 2 · jmagly
    Research, draft, and track a jurisdiction-specific public-records request without legal conclusions or automated submission.
    229 repo stars
  13. ▌
    Graph Flow Profile 2 · jmagly
    Author, validate, explain, dry-run, and inspect optional graph.flow.aiwg.io GraphPlaybooks over the AIWG Flow runtime substrate
    229 repo stars
  14. ▌
    Forme Manifest 3 · jmagly
    Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging
    229 repo stars
  15. ▌
    Prose Validate 3 · jmagly
    Validate an OpenProse program file against Prose contract grammar without executing it — checks frontmatter, contract structure, service references, and strategy syntax
    229 repo stars
  16. ▌
    Schema Onboard 2 · jmagly
    Explain schema value to a non-specialist and guide them through examples-first contract creation.
    229 repo stars
  17. ▌
    Generate Factory 3 · jmagly
    Auto-generate test data factories from schemas, types, or models. Use when creating test data infrastructure, setting up fixtures, or reducing test setup boilerplate.
    229 repo stars
  18. ▌
    Reflection Injection 2 · jmagly
    Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them
    229 repo stars
  19. ▌
    Flow Discovery Track 2 · jmagly
    Orchestrate Discovery Track flow to prepare validated requirements and designs one iteration ahead of delivery
    229 repo stars
  20. ▌
    Chunk · jmagly
    Split a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
    229 repo stars
  21. ▌
    Fanout · jmagly
    Dispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
    229 repo stars
  22. ▌
    Chunk 2 · jmagly
    Split a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
    229 repo stars
  23. ▌
    Fanout 2 · jmagly
    Dispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
    229 repo stars
  24. ▌
    Rlm Mode · jmagly
    Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
    229 repo stars
  25. ▌
    Rlm Prep · jmagly
    Prepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
    229 repo stars
  26. ▌
    Rlm Batch · jmagly
    Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
    229 repo stars
  27. ▌
    Rlm Query · jmagly
    Spawn sub-agent to process focused context and return structured result
    229 repo stars
  28. ▌
    Rlm Mode 2 · jmagly
    Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
    229 repo stars
  29. ▌
    Rlm Prep 2 · jmagly
    Prepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
    229 repo stars
  30. ▌
    Rlm Search · jmagly
    Run the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
    229 repo stars
  31. ▌
    Rlm Status · jmagly
    Show status of RLM task tree execution
    229 repo stars
  32. ▌
    Rlm Batch 2 · jmagly
    Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
    229 repo stars
  33. ▌
    Rlm Query 2 · jmagly
    Spawn sub-agent to process focused context and return structured result
    229 repo stars
  34. ▌
    Rlm Search 2 · jmagly
    Run the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
    229 repo stars
  35. ▌
    Rlm Status 2 · jmagly
    Show status of RLM task tree execution
    229 repo stars
  36. ▌
    Ralph · jmagly
    Execute iterative task loop until completion criteria are met - iteration beats perfection
    229 repo stars
  37. ▌
    LLM Wiki · jmagly
    Enable 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.
    229 repo stars
  38. ▌
    Ralph 2 · jmagly
    Execute iterative task loop until completion criteria are met - iteration beats perfection
    229 repo stars
  39. ▌
    Eval Loop · jmagly
    Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
    229 repo stars
  40. ▌
    Uat Report · jmagly
    Generate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection
    229 repo stars
  41. ▌
    LLM Wiki 2 · jmagly
    Enable 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.
    229 repo stars
  42. ▌
    Dev Doctor · jmagly
    Run a development-focused health check on the AIWG repository structure
    229 repo stars
  43. ▌
    Link Check · jmagly
    Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
    229 repo stars
  44. ▌
    Uat Execute · jmagly
    Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
    229 repo stars
  45. ▌
    Eval Loop 2 · jmagly
    Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
    229 repo stars
  46. ▌
    Devkit Test · jmagly
    Auto-fix discoverable issues
    229 repo stars
  47. ▌
    Uat Generate · jmagly
    Discover MCP tools and generate a phased UAT plan with agent-executable test specifications
    229 repo stars
  48. ▌
    Dev Doctor 2 · jmagly
    Run a development-focused health check on the AIWG repository structure
    229 repo stars
  49. ▌
    Link Check 2 · jmagly
    Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
    229 repo stars
  50. ▌
    Agent Loop · jmagly bundle
    Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
    229 repo stars
  51. ▌
    Eval Agent · jmagly
    Run evaluation tests against an agent to assess quality and archetype resistance
    229 repo stars
  52. ▌
    Aiwg Hooks · jmagly
    Install, configure, and inspect AIWG lifecycle hooks for tracing, permissions, session management, context injection, and quality gates.
    229 repo stars
  53. ▌
    Devkit Test 2 · jmagly
    Auto-fix discoverable issues
    229 repo stars
  54. ▌
    Ralph Abort · jmagly
    Abort a running agent loop and optionally revert changes
    229 repo stars
  55. ▌
    Dev Mode Init · jmagly
    Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
    229 repo stars
  56. ▌
    Eval Report · jmagly
    Generate an aggregate agent quality report from evaluation results, showing scores, regressions, and recommendations
    229 repo stars
  57. ▌
    Productionize · jmagly
    Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
    229 repo stars
  58. ▌
    Agent Loop 2 · jmagly bundle
    Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
    229 repo stars
  59. ▌
    Debug Memory · jmagly
    Query and manage the executable feedback debug memory
    229 repo stars
  60. ▌
    Ralph Attach · jmagly
    Attach to a running agent loop's live output stream
    229 repo stars
  61. ▌
    Ralph Config · jmagly
    View and configure agent loop settings — show, set, reset, and apply named presets
    229 repo stars
  62. ▌
    Ralph Memory · jmagly
    Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
    229 repo stars
  63. ▌
    Ralph Resume · jmagly
    Resume an interrupted agent loop from last checkpoint
    229 repo stars
  64. ▌
    Ralph Status · jmagly
    Check status of current or previous agent loop
    229 repo stars
  65. ▌
    Validate Addon · jmagly
    Validate an entire AIWG addon package for completeness and release readiness
    229 repo stars
  66. ▌
    Auto Memory · jmagly
    Configure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
    229 repo stars
  67. ▌
    Cost Optimizer · jmagly
    Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
    229 repo stars
  68. ▌
    Ralph Abort 2 · jmagly
    Abort a running agent loop and optionally revert changes
    229 repo stars
  69. ▌
    Dev Mode Init 2 · jmagly
    Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
    229 repo stars
  70. ▌
    Productionize 2 · jmagly
    Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
    229 repo stars
  71. ▌
    Ralph Reflect · jmagly
    View and manage agent loop reflections and episodic memory
    229 repo stars
  72. ▌
    Devkit Validate · jmagly
    Validate addon, framework, or extension structure and manifest
    229 repo stars
  73. ▌
    Eval Workflow · jmagly
    Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance
    229 repo stars
  74. ▌
    Pipeline Design · jmagly
    Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
    229 repo stars
  75. ▌
    Pipeline Status · jmagly
    Show status overview of all LLM inference pipelines in the current project
    229 repo stars
  76. ▌
    Prompt Engineer · jmagly
    Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
    229 repo stars
  77. ▌
    Debug Memory 2 · jmagly
    Query and manage the executable feedback debug memory
    229 repo stars
  78. ▌
    Ralph Attach 2 · jmagly
    Attach to a running agent loop's live output stream
    229 repo stars
  79. ▌
    Ralph Config 2 · jmagly
    View and configure agent loop settings — show, set, reset, and apply named presets
    229 repo stars
  80. ▌
    Ralph Memory 2 · jmagly
    Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
    229 repo stars
  81. ▌
    Ralph Resume 2 · jmagly
    Resume an interrupted agent loop from last checkpoint
    229 repo stars
  82. ▌
    Ralph Status 2 · jmagly
    Check status of current or previous agent loop
    229 repo stars
  83. ▌
    Validate Addon 2 · jmagly
    Validate an entire AIWG addon package for completeness and release readiness
    229 repo stars
  84. ▌
    Auto Memory 2 · jmagly
    Configure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
    229 repo stars
  85. ▌
    Cost Optimizer 2 · jmagly
    Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
    229 repo stars
  86. ▌
    Star Prompt · jmagly
    Tastefully invite users to star AIWG after a successful workflow.
    229 repo stars
  87. ▌
    Agent Loop Ext · jmagly
    Crash-resilient external agent loop with state persistence and CI/CD integration
    229 repo stars
  88. ▌
    Ralph External · jmagly
    Crash-resilient external loop with state persistence and CI/CD integration
    229 repo stars
  89. ▌
    Droid Bridge · jmagly
    Configure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.
    229 repo stars
  90. ▌
    Pattern Selector · jmagly
    Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
    229 repo stars
  91. ▌
    Premortem V2 · jmagly
    Run a diversity-first premortem with bounded deep dives, blind plausibility and impact verification, and explicit provenance labels.
    229 repo stars
  92. ▌
    Flaky Fix · jmagly
    Suggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
    229 repo stars
  93. ▌
    Test Sync · jmagly
    Detect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
    229 repo stars
  94. ▌
    Ralph Reflect 2 · jmagly
    View and manage agent loop reflections and episodic memory
    229 repo stars
  95. ▌
    Devkit Validate 2 · jmagly
    Validate addon, framework, or extension structure and manifest
    229 repo stars
  96. ▌
    Issue Planner · jmagly
    Research-grounded SDLC issue planner — dispatches parallel research, generates the supporting doc corpus, then files prioritized cross-referenced issues for human review.
    229 repo stars
  97. ▌
    Pipeline Design 2 · jmagly
    Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
    229 repo stars
  98. ▌
    Pipeline Status 2 · jmagly
    Show status overview of all LLM inference pipelines in the current project
    229 repo stars
  99. ▌
    Prompt Engineer 2 · jmagly
    Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
    229 repo stars
  100. ▌
    Ralph Analytics · jmagly
    Show analytics and metrics from agent loop execution history
    229 repo stars