jmagly
- 528 skills
- 0 followers
- 2 days ago last updated
- ▌ Generate Realization · jmagly-ai-writing-guideGenerate behavioral specifications (Layer 3) from use cases and architecture documents using multi-agent orchestration
- ▌ Intake From Codebase · jmagly-ai-writing-guideScan existing codebase and generate intake documents by analyzing code, dependencies, and infrastructure. Accepts optional guidance text to tailor analysis.
- ▌
- ▌ Aiwg Utils Quickref · jmagly-ai-writing-guideAUTO-INVOKE for ANY AIWG capability question, framework/addon/extension query, steward routing, MCP profile, or when unsure where to start. ALWAYS consult before filesystem search on .claude/.factory/.codex/.warp/etc. AIWG core utilities quick reference — always-on framing, steward, index, meta operations.
- ▌ Mention Conventions · jmagly-ai-writing-guideDisplay @-mention naming conventions and placement rules
- ▌ Package All Plugins · jmagly-ai-writing-guideBatch package every AIWG/Codex marketplace wrapper in the workspace into distributable plugin archives — runs package-plugin for all wrappers at once
- ▌ Execute Feedback · jmagly-ai-writing-guideExecute tests on generated code and iterate until passing
- ▌ Setup Run · jmagly-ai-writing-guideExecute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati
- ▌
- ▌
- ▌ Corpus Snapshot · jmagly-ai-writing-guideGenerate a corpus snapshot report — computes dimensions, topology, degree distribution, delta from previous. Helps with cluster, chain, and gap analysis sections.
- ▌ Induct Research · jmagly-ai-writing-guideInduct research sources (issue, file, directory, or URI) into a research corpus — reads, annotates, and files structured induction tasks. Like address-issues but for research.
- ▌ Induction Audit · jmagly-ai-writing-guideAudit research-corpus induction quality — depth bands (stub/compact/good/full/deep), structural integrity (analysis doc + sidecar + PDF, honoring audit-exclude conventions), and per-source-type required sections (a blog isn't flagged for missing Benchmark Results). Plus additive frontmatter backfill for legacy docs. Runs via `aiwg corpus induction-audit` / `aiwg corpus frontmatter-backfill`.
- ▌ Profile Metrics · jmagly-ai-writing-guideCompute corpus-local influence/centrality metrics — per-paper CD-index + PageRank, and per-PROF-P h-index / mean-CD / mean-PageRank / betweenness / eigenvector + influence grade. Runs via `aiwg corpus profile-metrics`.
- ▌
- ▌ Flow Change Control · jmagly-ai-writing-guideOrchestrate change control workflow with baseline management, impact assessment, CCB review, and communication
- ▌ Flow Delivery Track · jmagly-ai-writing-guideOrchestrate Delivery Track flow with test-driven development, quality gates, and iteration assessment
- ▌ Orchestrate Project · jmagly-ai-writing-guidePlan iterations, delegate to SDLC agents, and compile iteration status
- ▌ Provenance Validate · jmagly-ai-writing-guideValidate provenance records and chains for completeness and consistency
- ▌ Regression Baseline · jmagly-ai-writing-guideCreate and maintain regression test baselines for comparison and drift detection across versioned snapshots
- ▌ Regression Learning · jmagly-ai-writing-guideImprove regression detection over time through cross-task pattern recognition, test prioritization, and historical analysis
- ▌ Security Assessment · jmagly-ai-writing-guideExecute STRIDE threat modeling, vulnerability scanning, and security control validation with risk scoring
- ▌ Rollback Workspace · jmagly-ai-writing-guideRestore the .aiwg/ directory from a migrate-workspace backup, listing available backups when none is specified
- ▌ Scaffold Extension · jmagly-ai-writing-guideCreate a new extension package inside an existing framework's extensions/ directory. Use when authoring an expansion (extension) for AIWG.
- ▌ Scaffold Framework · jmagly-ai-writing-guideCreate a complete framework package structure inside agentic/code/frameworks/. Use when authoring an expansion (framework) for AIWG.
- ▌ Mission Control · jmagly-ai-writing-guide bundleOrchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop
- ▌ Ralph Analytics · jmagly-ai-writing-guideShow analytics and metrics from agent loop execution history
- ▌ Cloud Forensics · jmagly-ai-writing-guideAWS, Azure, and GCP forensic investigation covering audit logs, IAM review, storage access, network flows, and compute instance forensics
- ▌ Aiwg Language Map · jmagly-ai-writing-guideAIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs
- ▌ Artifact Metadata · jmagly-ai-writing-guide bundleManage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle
- ▌ Customize Rebuild · jmagly-ai-writing-guideRebuild and redeploy AIWG from local customization source — makes recent edits live
- ▌ Migrate Workspace · jmagly-ai-writing-guideMigrate the .aiwg/ directory from single-framework layout to the multi-framework layout with an automatic backup
- ▌ Parallel Dispatch · jmagly-ai-writing-guide bundleLaunch multiple agents concurrently, collect their results, and handle timeouts for fan-out orchestration patterns
- ▌ Project Awareness · jmagly-ai-writing-guide bundleDetect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
- ▌ Validate Metadata · jmagly-ai-writing-guideValidate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints
- ▌ Workspace Realign · jmagly-ai-writing-guideReorganize and update .aiwg/ documentation to reflect current project reality
- ▌ Output Mode Guide · jmagly-ai-writing-guideConfigure, use, troubleshoot, or extend AIWG composable output modes (also called output masks), including Wittgenstein-inspired clarity, engineering controlled language, and personal syntax profiles
- ▌ Agent Loop Ext · jmagly-ai-writing-guideCrash-resilient external agent loop with state persistence and CI/CD integration
- ▌ Ralph External · jmagly-ai-writing-guideCrash-resilient external loop with state persistence and CI/CD integration
- ▌ Pattern Selector · jmagly-ai-writing-guideRecommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
- ▌ Premortem V2 · jmagly-ai-writing-guideRun a diversity-first premortem with bounded deep dives, blind plausibility and impact verification, and explicit provenance labels.
- ▌ Flaky Fix · jmagly-ai-writing-guideSuggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
- ▌ Test Sync · jmagly-ai-writing-guideDetect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
- ▌
- ▌ Ioc Extraction · jmagly-ai-writing-guideExtract, classify, deduplicate, and enrich IOCs from investigation artifacts; map to STIX 2.1 observables
- ▌ Kb Health · jmagly-ai-writing-guideLint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.
- ▌ Kb Ingest · jmagly-ai-writing-guideIngest a source (URL, file, or freeform note) into the knowledge base. Creates a source summary and updates or creates relevant entity and concept pages.
- ▌ Eval Workflow · jmagly-ai-writing-guideRun evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance
- ▌ Pipeline Design · jmagly-ai-writing-guideInteractive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
- ▌ Pipeline Status · jmagly-ai-writing-guideShow status overview of all LLM inference pipelines in the current project
- ▌ Prompt Engineer · jmagly-ai-writing-guideProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- ▌
- ▌
- ▌ Data Pipeline · jmagly-ai-writing-guideOrchestrate marketing data collection, transformation, aggregation, and reporting workflows across platforms
- ▌ Theme Manager · jmagly-ai-writing-guide bundleResearch, compare, sample, select, persist, adapt, rotate, and archive reusable visual themes and design templates
- ▌ Curator Status · jmagly-ai-writing-guideReport research-corpus discovery curators (PROF-S) ranked by yield (return-to score = inducted-ref-count × avg GRADE), with revisit-cadence staleness and a discovery-orphan check. Runs via `aiwg corpus curator-status`.
- ▌ Funder Network · jmagly-ai-writing-guideBuild the bipartite funder↔paper analytics — per-funder paper/A-grade/mean-grade rollup, mean CD-index + novelty bias, and co-funding clusters. Runs via `aiwg corpus funder-network`.
- ▌ Integrity Scan · jmagly-ai-writing-guideTriage research-corpus artifacts for LLM residue, placeholder/template markers, unresolved citation markers, non-final experiment language, and submission risks. Per-REF scoring → pass / review / quarantine. Conservative — flags for human review, does not decide misconduct. Runs via `aiwg corpus integrity-scan`.
- ▌ Profile Status · jmagly-ai-writing-guideReport research-corpus entity profiles (PROF-P/O/G/F) past their refresh cadence. Computes staleness via the shared cadence helper, sorted most-overdue-first. Runs via `aiwg corpus profile-status`.
- ▌ Research Query · jmagly-ai-writing-guideSearch the local research corpus, read matching findings, and synthesize an answer with inline citations to REF-XXX sources. The "query" operation for the research pipeline.
- ▌ Vision Extract · jmagly-ai-writing-guideTranscribe scanned page images into per-page + combined Markdown source text for induction, via a provider-neutral vision adapter (codex CLI or a generic command template for Claude/any vision tool). Resumable, with retry + `# Page N` validation + extraction-status markers; optionally rasterizes a PDF to page PNGs first. Runs via `aiwg corpus vision-extract`.
- ▌ Aiwg Setup Project · jmagly-ai-writing-guideUpdate project CLAUDE.md with AIWG framework context and configuration
- ▌ Aiwg Update Claude · jmagly-ai-writing-guideUpdate existing project CLAUDE.md with latest AIWG orchestration guidance
- ▌ Check Traceability · jmagly-ai-writing-guideVerify the full refinement chain from use cases through behavioral specs, pseudo-code specs, code, and tests — report coverage at each layer and identify gaps
- ▌ Regression Metrics · jmagly-ai-writing-guideTrack and analyze regression statistics, trends, hotspots, and health indicators across test suites
- ▌ Traceability Check · jmagly-ai-writing-guideVerify bidirectional traceability from requirements to code to tests and identify coverage gaps and orphan artifacts
- ▌ Star Prompt · jmagly-ai-writing-guideTastefully invite users to star AIWG after a successful workflow.
- ▌ Hook Regenerate · jmagly-ai-writing-guideRebuild AIWG hook files from currently installed framework manifests
- ▌ Session Explore · jmagly-ai-writing-guide bundleInvestigate past AI session activity with cited catalog search, timelines, tool analytics, and bounded comparisons across providers
- ▌ Template Engine · jmagly-ai-writing-guide bundleLoad, validate, and populate templates consistently across frameworks
- ▌ Workspace Reset · jmagly-ai-writing-guideWipe .aiwg/ directory and optionally restart with fresh intake
- ▌
- ▌
- ▌ Ralph Config · jmagly-ai-writing-guideView and configure agent loop settings — show, set, reset, and apply named presets
- ▌ Ralph Memory · jmagly-ai-writing-guideManage Al semantic memory entries — list, query, and clear lessons learned across loop iterations
- ▌
- ▌
- ▌ Validate Addon · jmagly-ai-writing-guideValidate an entire AIWG addon package for completeness and release readiness
- ▌ Auto Memory · jmagly-ai-writing-guideConfigure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.
- ▌ Line Memory · jmagly-ai-writing-guideRetain and retrieve small durable project facts through a bounded, recency-ordered plain-text memory
- ▌ Cost Optimizer · jmagly-ai-writing-guideAnalyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates
- ▌ Log Analysis · jmagly-ai-writing-guideCorrelate auth.log, syslog, journald, application, and web logs to detect brute force, privilege escalation, and lateral movement.
- ▌
- ▌ Assemble · jmagly-ai-writing-guideAssemble media into thematic compilations, concert films, era playlists, and narrative experiences
- ▌ Corpus Export · jmagly-ai-writing-guidePackage corpus subsets as distribution archives. Filter by cluster, topic, REF range, or custom expression; bundles PDFs, analysis, citations, and BibTeX into tar.gz.
- ▌ Discovery Log · jmagly-ai-writing-guideRecord the source-tracking `discovery` block on a research-corpus citation sidecar — where/how a paper was found (surface, via, curator). Runs via `aiwg corpus discovery-log`.
- ▌ Profile Graph · jmagly-ai-writing-guideEntity-profile graph edges + embedding similarity for a research corpus — profile→REF edges (first-class adjacency, reconciled against the citation graph) and text-embedding researcher similarity + collaboration link-prediction. Completes the
- ▌ Research Lint · jmagly-ai-writing-guideRun the research corpus lint ruleset to detect structural and referential integrity issues — orphan notes, missing frontmatter, broken references, missing GRADE assessments.
- ▌ Contract Manifest · jmagly-ai-writing-guideGenerate a human-readable manifest for an AIWG skill chain — agent assignments, requires/ensures contracts, data flow, and parallelization opportunities.
- ▌ Contract Validate · jmagly-ai-writing-guideValidate that an AIWG skill chain has all requires inputs satisfied by upstream ensures outputs. Catches missing dependencies at wiring time, not runtime.
- ▌ Provenance Create · jmagly-ai-writing-guideCreate a W3C PROV-compliant provenance record for an artifact
- ▌
- ▌ Regression Bisect · jmagly-ai-writing-guideIdentify the commit that introduced a regression using git bisect with automated test execution and blame context
- ▌ Regression Report · jmagly-ai-writing-guideGenerate comprehensive regression analysis reports combining bisect, baseline, and metrics data with actionable recommendations
- ▌ Regression Visual · jmagly-ai-writing-guideDetect visual and UI regressions through screenshot comparison and pixel-diff analysis across browsers and viewports
- ▌ Aiwg Delivery Pr · jmagly-ai-writing-guideAIWG-specific delivery pull request workflow; explicit alias for aiwg-pr, not a generic repository PR guide
- ▌ Claims Validator · jmagly-ai-writing-guideValidate documentation for unsupported claims, made-up metrics, and unverifiable statements
- ▌ Config Validator · jmagly-ai-writing-guideValidate AIWG configuration files and project setup for correctness and completeness
- ▌ Context Firewall · jmagly-ai-writing-guideAudit provider-facing context, trust, drift, poisoning signals, and budget, then manage the reviewed baseline through a plan-first public CLI workflow
- ▌ Contribute Start · jmagly-ai-writing-guideInitialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue