jmagly
- 453 skills
- 0 followers
- 229 repo stars
- last month last updated
- ▌ Aiwg Status 2 · jmagly bundleDisplay workspace status dashboard showing installed frameworks, deployments, artifact counts, and health indicators
- ▌
- ▌ Aiwg Language Map 2 · jmagly bundleAIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs
- ▌ Aiwg Utils Quickref 2 · jmagly bundleAUTO-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.
- ▌ Security Engineering Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions cryptography, AEAD, KDF, chain of trust, signing key, auth factor, MFA, secret hygiene, supply chain trust, physical threat. Security-engineering quick reference — decision domains for crypto primitives, chain-of-trust, auth factors, degraded modes, supply-chain trust, physical-threat modeling.
- ▌ Aiwg Issue 2 · jmagly bundleAIWG project issue filing only — templates, environment capture, duplicate detection, and import flow for AIWG tracker reports; not for general issue audits or address-issues processing
- ▌ Use 2 · jmagly bundleDeploy AIWG frameworks and addons to the current workspace across supported providers
- ▌ Aiwg Pr 2 · jmagly bundleGuide for opening high-quality pull requests — template, verification gates, delivery-policy compliance, no-attribution rule, and CI-green-before-done discipline
- ▌ Aiwg Help 2 · jmagly bundleDisplay all available AIWG CLI commands, their arguments, and usage examples
- ▌ Aiwg Doctor 2 · jmagly bundleRun a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps
- ▌ Aiwg Refresh 2 · jmagly bundleUpdate AIWG CLI and redeploy frameworks/tools to current project without leaving the session
- ▌ Ops Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions ops, runbook, inventory, audit trail, ops repo, sysops, devops, itops, infrastructure operations, fleet management. Ops framework quick reference — capability domains, extension model, and discovery phrases for runbooks, inventory, audit trail, verification.
- ▌ Research Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions research, paper, citation, GRADE, corpus, provenance, literature review, induct paper, evidence, bibliography. Research framework quick reference — discovery phrases for corpus inception, paper acquisition, GRADE quality, citation graphs, provenance-tracked synthesis.
- ▌ Forensics Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions forensics, incident response, IOC, log analysis, evidence preservation, breach investigation, threat hunting, attack timeline. Forensics framework quick reference — discovery phrases for incident response, log analysis, evidence preservation, IOC extraction.
- ▌ Marketing Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions marketing, campaign, brand, content production, audience persona, copy, social media, marketing intake, approval workflow. Marketing framework quick reference — discovery phrases for campaign intake, brand compliance, content production, audience synthesis, approval workflows.
- ▌ Media Curator Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions media curation, discography, archive, music collection, source acquisition, metadata tagging, Plex, Jellyfin, MPD. Media-curator framework quick reference — discovery phrases for discography analysis, source discovery, acquisition, quality filtering, metadata, archive integrity.
- ▌ Knowledge Base Quickref 2 · jmagly bundleAUTO-INVOKE when user mentions knowledge base, wiki, KB, semantic memory, llm-wiki, knowledge ingest, document corpus. Knowledge-base framework quick reference — discovery phrases for KB ingest/health, semantic-memory kernel skills, llm-wiki profiles.
- ▌ Compound Memory 4 · jmaglyOrchestrate governed persistent project memory across immutable evidence, llm-wiki, line-memory, reviewed session candidates, generated outputs, and bounded context packs.
- ▌ Prose Install 4 · 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.
- ▌ Local Resource Index 2 · jmaglyIndex cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.
- ▌ Twelve Factor Audit 3 · jmaglyAudit an application against Twelve-Factor and modern 12+ Factor criteria with structured evidence, risks, and remediation tasks.
- ▌ Setup Generate 4 · jmaglyGenerate a `setup.manifest.yaml` file for a project using the `setup.aiwg.io/v1`
- ▌ Setup Validate 4 · jmaglyValidate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons
- ▌ Devkit Create Extension 4 · jmaglyCreate a new AIWG extension (framework expansion pack) with AI-guided setup
- ▌
- ▌ Forme Manifest 4 · jmaglyRead a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging
- ▌ Prose Validate 4 · jmaglyValidate an OpenProse program file against Prose contract grammar without executing it — checks frontmatter, contract structure, service references, and strategy syntax
- ▌ Generate Factory 4 · jmaglyAuto-generate test data factories from schemas, types, or models. Use when creating test data infrastructure, setting up fixtures, or reducing test setup boilerplate.
- ▌ Dataset Trace 2 · jmaglyExplain dataset, record, field, index, graph, and export lineage using evidence-bearing bounded queries.
- ▌ Twelve Factor Design 3 · jmaglyGenerate or review application architecture against Twelve-Factor and modern 12+ Factor design criteria.
- ▌ Color Accessibility 2 · jmaglyWCAG accessibility analysis for color palettes including contrast ratios, compliance checking, and remediation suggestions. Use when user needs to verify colors meet accessibility standards.
- ▌ Twelve Factor Audit 4 · jmaglyAudit an application against Twelve-Factor and modern 12+ Factor criteria with structured evidence, risks, and remediation tasks.
- ▌ Agent Persistence 3 · jmaglyEnable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
- ▌ Source Compliance Gate 2 · jmagly bundleEvaluate source access, rights, robots, authorization, provenance, and freshness before automated acquisition or public reuse.
- ▌ Dataset Export 2 · jmaglyPlan and delegate a governed portable dataset or lineage export with explicit standards coverage and loss reporting.
- ▌ Dataset Ingest 2 · jmaglyDelegate approved one-shot or incremental dataset execution to the shared orchestration service with resumable receipts.
- ▌ Dataset Intake 2 · jmaglyTurn a source path or URI and desired outcome into a governed dataset intake envelope for any AIWG domain.
- ▌ Dataset Retire 2 · jmaglyPlan and delegate safe dataset retirement, tombstoning, derived-artifact cleanup, and reconciliation.
- ▌ Dataset Verify 2 · jmaglyVerify a dataset plan or run receipt, checkpoint continuity, provenance completeness, and derived-artifact freshness.
- ▌ Twelve Factor Design 4 · jmaglyGenerate or review application architecture against Twelve-Factor and modern 12+ Factor design criteria.
- ▌ Infer Completion Criteria 3 · jmaglyInfer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
- ▌ Agent Persistence 4 · jmaglyEnable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
- ▌ Public Meeting Reconcile 2 · jmagly bundleReconcile a supplied public-meeting transcript, vote ledger, and official minutes while preserving uncertainty and requiring human verification.
- ▌ Public Technology Review 2 · jmaglyBuild a vendor-neutral, source-linked public-technology procurement evidence and risk review without autonomous scoring or award recommendations.
- ▌ Long Context Bench 2 · jmaglyBenchmark compressed context against summary, direct retrieval, and provider-context baselines without enabling product integration
- ▌ Infer Completion Criteria 4 · jmaglyInfer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly
- ▌ Composition Evaluate 2 · jmaglyCompare FlowGraph composition policies with fixed tasks, requested-versus-realized resources, failure injection, and an evidence claim gate
- ▌ Composition Validate 2 · jmaglyValidate a Flow graph manifest, explain semantic diagnostics, and emit one provider-neutral normalized composition contract.
- ▌ Topology Lab 2 · jmaglyCompare orchestration topologies on one task family using integrity-gated observations and coordination metrics
- ▌ Editorial Correction Review 2 · jmaglyReview a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
- ▌ Dataset Plan Review 2 · jmaglyReview an immutable dataset plan, impacts, capability degradation, and approval requirements before execution.
- ▌ Analyze Network Capture 2 · jmaglyAnalyze an authorized saved PCAP or PCAPNG with bounded TShark recipes and produce governed frame and stream evidence. Use for packet troubleshooting, protocol inspection, or optional local Termshark review.
- ▌ Validation Complete 3 · jmaglyActivate and run provider-normalized validation playbooks across configured AIWG providers, including single-provider and all-provider checks.
- ▌ Polyrhythmic Reasoning 2 · jmaglyBuild a safe strict-LCM or adaptive polyrhythmic FlowGraph for explicit multi-track reasoning.
- ▌ Dataset Intelligence 2 · jmaglyRoute any dataset, custom indexing, traceability, provenance, lineage, synchronization, or retirement request through one governed workflow. Use when a user points AIWG at data and wants an outcome without knowing schema or indexing terminology.
- ▌ Century Readiness Review 2 · jmaglyReview long-horizon obligations, stable cores, dependencies, replacement paths, stewardship, degradation, evidence, and meaning preservation
- ▌ Dataset Source Assess 2 · jmaglyPlan and review a bounded, non-mutating dataset source check and redacted preview.
- ▌ Validation Complete 4 · jmaglyActivate and run provider-normalized validation playbooks across configured AIWG providers, including single-provider and all-provider checks.
- ▌ Research Brainstorm 2 · jmaglyCapture and expand free-form research thoughts into wiki memory without requiring REF-* structure.
- ▌ Monitorability Red Team 2 · jmaglyEvaluate synthetic local multi-agent monitorability fixtures and label content, tool, state, and evidence blind spots
- ▌ Pr Reviewer 2 · jmaglyReview GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
- ▌ Venv Manager 2 · jmaglyCreate, manage, and validate Python virtual environments. Use for project isolation and dependency management.
- ▌ Dataset Capability Recommend 2 · jmaglyRecommend an independently composable dataset capability profile with plain-language rationale and safe defaults.
- ▌ Natural Language Harness 2 · jmaglyValidate and ablate readable NLAH.md harness policy without executing ambiguous prose
- ▌ Repo Analyzer 2 · jmaglyAnalyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
- ▌ Pytest Runner 2 · jmaglyExecute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
- ▌ Research Brainstorm Map 2 · jmaglyRender idea, question, and hypothesis maps from KB graph neighbors and brainstorming notes.
- ▌ Aiwg Orchestrate 2 · jmaglyRoute structured artifact work to AIWG workflows via MCP with zero parent context cost
- ▌ Research Brainstorm Query 2 · jmaglyRetrieve adjacent wiki/research context and produce exploratory synthesis for a brainstorm topic.
- ▌ Vitest Runner 2 · jmaglyExecute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
- ▌ Research Brainstorm Promote 2 · jmaglyPromote selected brainstorm material into structured research questions, acquisition targets, REF candidates, gap reports, or synthesis plans.
- ▌ Eslint Checker 2 · jmaglyRun ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
- ▌ Chunk 3 · jmaglySplit a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
- ▌ Fanout 3 · jmaglyDispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
- ▌ Chunk 4 · jmaglySplit a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
- ▌ Fanout 4 · jmaglyDispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
- ▌ Rlm Mode 3 · jmaglyDetect requests for recursive decomposition and large-scale operations that benefit from RLM processing
- ▌ Rlm Prep 3 · jmaglyPrepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
- ▌ Rlm Batch 3 · jmaglyParallel fan-out processing - spawn multiple sub-agents for chunked context processing
- ▌
- ▌ Rlm Mode 4 · jmaglyDetect requests for recursive decomposition and large-scale operations that benefit from RLM processing
- ▌ Rlm Prep 4 · jmaglyPrepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
- ▌ Rlm Search 3 · jmaglyRun the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
- ▌
- ▌ Rlm Batch 4 · jmaglyParallel fan-out processing - spawn multiple sub-agents for chunked context processing
- ▌
- ▌ Rlm Search 4 · jmaglyRun the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window
- ▌
- ▌ Ralph 3 · jmaglyExecute iterative task loop until completion criteria are met - iteration beats perfection
- ▌ LLM Wiki 3 · 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 4 · jmaglyExecute iterative task loop until completion criteria are met - iteration beats perfection
- ▌ Steward 2 · jmagly bundleProvide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate
- ▌ Eval Loop 3 · jmaglyConfigure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
- ▌ Uat Report 2 · jmaglyGenerate UAT completion report with tool coverage matrix, pass/fail metrics, and regression detection
- ▌ LLM Wiki 4 · 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 3 · jmaglyVerify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix
- ▌ Uat Execute 2 · jmaglyExecute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure
- ▌ Eval Loop 4 · jmaglyConfigure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met
- ▌