jmagly
- 454 skills
- 0 followers
- 229 repo stars
- 19 hours ago last updated
- ▌
- ▌ Uat Generate 2 · jmaglyDiscover MCP tools and generate a phased UAT plan with agent-executable test specifications
- ▌
- ▌ Link Check 4 · jmaglyVerify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
- ▌ Agent Loop 3 · jmagly bundleDetect requests for iterative autonomous agent loops and route to the appropriate loop executor
- ▌ Eval Agent 2 · jmaglyRun evaluation tests against an agent to assess quality and archetype resistance
- ▌ Aiwg Hooks 2 · jmaglyInstall, configure, and inspect AIWG lifecycle hooks for tracing, permissions, session management, context injection, and quality gates.
- ▌
- ▌
- ▌ Dev Mode Init 3 · 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 2 · jmaglyGenerate an aggregate agent quality report from evaluation results, showing scores, regressions, and recommendations
- ▌ Productionize 3 · jmaglyProduction readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
- ▌ Agent Loop 4 · jmagly bundleDetect requests for iterative autonomous agent loops and route to the appropriate loop executor
- ▌
- ▌
- ▌ Ralph Config 3 · jmaglyView and configure agent loop settings — show, set, reset, and apply named presets
- ▌ Ralph Memory 3 · jmaglyManage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
- ▌
- ▌
- ▌ Validate Addon 3 · jmaglyValidate an entire AIWG addon package for completeness and release readiness
- ▌ Auto Memory 3 · jmaglyConfigure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
- ▌ Cost Optimizer 3 · jmaglyAnalyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
- ▌
- ▌ Dev Mode Init 4 · jmaglySwitch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
- ▌ Productionize 4 · jmaglyProduction readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
- ▌
- ▌
- ▌ Eval Workflow 2 · jmaglyRun evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance
- ▌ Pipeline Design 3 · jmaglyInteractive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
- ▌ Pipeline Status 3 · jmaglyShow status overview of all LLM inference pipelines in the current project
- ▌ Prompt Engineer 3 · jmaglyProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- ▌
- ▌
- ▌ Ralph Config 4 · jmaglyView and configure agent loop settings — show, set, reset, and apply named presets
- ▌ Ralph Memory 4 · jmaglyManage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
- ▌
- ▌
- ▌ Validate Addon 4 · jmaglyValidate an entire AIWG addon package for completeness and release readiness
- ▌ Auto Memory 4 · jmaglyConfigure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
- ▌ Cost Optimizer 4 · jmaglyAnalyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
- ▌
- ▌ Agent Loop Ext 3 · jmaglyCrash-resilient external agent loop with state persistence and CI/CD integration
- ▌ Ralph External 2 · jmaglyCrash-resilient external loop with state persistence and CI/CD integration
- ▌ Droid Bridge 3 · jmaglyConfigure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.
- ▌ Pattern Selector 3 · jmaglyRecommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
- ▌ Premortem V2 2 · jmaglyRun a diversity-first premortem with bounded deep dives, blind plausibility and impact verification, and explicit provenance labels.
- ▌ Flaky Fix 3 · jmaglySuggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
- ▌ Test Sync 3 · jmaglyDetect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
- ▌
- ▌
- ▌ Issue Planner 2 · jmaglyResearch-grounded SDLC issue planner — dispatches parallel research, generates the supporting doc corpus, then files prioritized cross-referenced issues for human review.
- ▌ Sdlc Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions SDLC, requirements, architecture, ADR, use case, user story, test plan, phase gate, inception, elaboration, construction, transition, intake, deploy. SDLC framework quick reference — phase model, capability domains, and curated discovery phrases for aiwg discover.
- ▌ Pipeline Design 4 · jmaglyInteractive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
- ▌ Pipeline Status 4 · jmaglyShow status overview of all LLM inference pipelines in the current project
- ▌ Prompt Engineer 4 · jmaglyProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- ▌
- ▌ Agent Loop Ext 4 · jmaglyCrash-resilient external agent loop with state persistence and CI/CD integration
- ▌ Droid Bridge 4 · jmaglyConfigure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.
- ▌ Pattern Selector 4 · jmaglyRecommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
- ▌ Flaky Fix 4 · jmaglySuggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
- ▌ Test Sync 4 · jmaglyDetect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
- ▌
- ▌ Setup Run 3 · jmaglyExecute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati
- ▌ Validate Component 3 · jmaglyValidate a single AIWG component (skill, agent, or command) for completeness and correctness
- ▌ Prose Run 3 · jmaglyExecute an OpenProse program within the current AIWG session, following the two-phase model (Forme wiring + Prose VM execution)
- ▌ Tdd Enforce 3 · 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 2 · 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.
- ▌
- ▌ Devkit Create Agent 3 · jmaglyCreate a new agent with AI-guided expertise definition following the Agent Design Bible
- ▌
- ▌ Flaky Detect 3 · 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 4 · jmaglyExecute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati
- ▌ Validate Component 4 · jmaglyValidate a single AIWG component (skill, agent, or command) for completeness and correctness
- ▌ Color Palette 2 · jmaglyGenerate, analyze, compare, export, and suggest color palettes using color theory. Use when user asks about colors, palettes, color schemes, or needs help choosing colors for a project.
- ▌ Prose Run 4 · jmaglyExecute an OpenProse program within the current AIWG session, following the two-phase model (Forme wiring + Prose VM execution)
- ▌ Tdd Enforce 4 · jmagly bundleConfigure TDD enforcement via pre-commit hooks and CI coverage gates. Use when setting up test-first workflows or adding coverage gates.
- ▌ Cross Task Learner 3 · jmagly bundleEnable agent loops to learn from similar past tasks and share patterns across loops
- ▌ Prose Setup 3 · jmaglyClone or update the OpenProse repository to ensure AIWG prose tools hook into the latest version of the specification and examples
- ▌ Mutation Test 3 · jmagly bundleRun mutation testing to validate test quality beyond code coverage. Use when assessing test effectiveness, finding weak tests, or validating test suite quality.
- ▌
- ▌ Devkit Create Agent 4 · jmaglyCreate a new agent with AI-guided expertise definition following the Agent Design Bible
- ▌
- ▌ Flaky Detect 4 · jmaglyIdentify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.
- ▌ Auto Test Execution 3 · jmaglyAutomatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
- ▌
- ▌ Browser Doctor 3 · jmaglyRead-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.
- ▌ Prose Detect 3 · jmaglyLocate 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.
- ▌ Prose Reader 3 · jmaglyRead and parse an OpenProse program file, extracting its contract (requires, ensures, strategies, errors, invariants) and services into a structured representation
- ▌ Cross Task Learner 4 · jmagly bundleEnable agent loops to learn from similar past tasks and share patterns across loops
- ▌ Check Traceability 2 · jmaglyVerify the full refinement chain from use cases through behavioral specs, pseudo-code specs, code, and tests — report coverage at each layer and identify gaps
- ▌ Prose Setup 4 · jmaglyClone or update the OpenProse repository to ensure AIWG prose tools hook into the latest version of the specification and examples
- ▌ Mutation Test 4 · jmagly bundleRun mutation testing to validate test quality beyond code coverage. Use when assessing test effectiveness, finding weak tests, or validating test suite quality.
- ▌ Civic Publish Gate 2 · jmagly bundleRun deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
- ▌ Compound Memory 3 · jmaglyOrchestrate governed persistent project memory across immutable evidence, llm-wiki, line-memory, reviewed session candidates, generated outputs, and bounded context packs.
- ▌ Prose Install 3 · jmaglyInstall OpenProse for AIWG when not found. Tries `npx skills add`, falls back to git clone, then saves the resolved path to .aiwg/config.json.
- ▌ Schema Author 2 · jmaglyAuthor and register a canonical governed schema with fixtures and consumer metadata from a schema brief.
- ▌ Schema Evolve 2 · jmaglyChange a governed schema with conservative compatibility analysis, consumer impact review, migration, and deprecation planning.
- ▌ Schema Intake 2 · jmaglyDetect whether a new or changed data element needs a governed schema and create a plain-language schema brief. Use for records, configuration, events, APIs, files, messages, persistence, or structured user input.