Claude Skills by jmagly

Update AIWG to the latest stable version and re-deploy all installed frameworks from the registry

Deploy AIWG frameworks and addons to the current workspace across supported providers

Validate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints

Display the current AIWG version, release channel, and installation path

Generate a SOUL.md from an existing AIWG voice profile

Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files

Reorganize and update .aiwg/ documentation to reflect current project reality

Wipe .aiwg/ directory and optionally restart with fresh intake

Crash-resilient external agent loop with state persistence and CI/CD integration

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

Query and manage the executable feedback debug memory

Execute tests on generated code and iterate until passing

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop

Abort a running agent loop and optionally revert changes

Show analytics and metrics from agent loop execution history

Attach to a running agent loop's live output stream

View and configure agent loop settings — show, set, reset, and apply named presets

Crash-resilient external loop with state persistence and CI/CD integration

Manages bounded iteration loops for autonomous implementation with escalation.

Automatically execute tests when code-generating agents write to source files, enforcing the execute-before-return pattern.

Enable Ralph loops to learn from similar past tasks and share patterns across loops

Detect requests for iterative AI task loops and invoke the Ralph command

Automatically inject relevant past reflections into agent context when starting new iterations or retrying after failures.

Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing

Automatically generates W3C PROV-compliant provenance records when agents create or modify artifacts.

Automatically verify citations when agents generate content that makes factual claims or references research.

Automatically triggers GRADE quality assessment when new research sources or findings are added to the corpus.

Automatically detect and update linked issues after commits or artifact changes.

Activate this skill when the user says: - "address the open issues" - "work through the bugs" - "fix open issues" - "tackle issue {N}" - "address issues {N}, {M}, {P}" - "work on the bug backlog" - "fix the reported bugs" - "go through the open tickets" - "handle the issue queue" - "process the open issues" - "work on issue {N}"

Detect breaking changes in API contracts across REST, GraphQL, and gRPC interfaces.

Automatically manage regression test baseline lifecycle with triggers for releases, deployments, and quality gates.

Create and maintain regression test baselines for comparison and drift detection.

Automatically identify the commit that introduced a regression using git bisect.

Integrate regression testing into CI/CD pipelines with automated baseline comparison, merge blocking, and multi-platform support.

Cross-task learning skill for improving regression detection over time through pattern recognition, test prioritization, and historical analysis.

Track and analyze regression statistics, trends, and health indicators.

Detect performance regressions by comparing benchmarks across versions, analyzing latency/throughput degradation, and providing statistical significance testing.

Generate comprehensive regression analysis reports combining bisect, baseline, and metrics data.

Detect visual and UI regressions through screenshot comparison and pixel-diff analysis.

Automatically trigger Tree of Thoughts exploration when agents face architectural decisions with multiple valid approaches.

Unified gap analysis with natural language routing to specialized skills.

Create a new AIWG skill with AI-guided design

Manage artifact metadata, versioning, ownership, and history tracking.

Validate documentation for unsupported claims, made-up metrics, and unverifiable statements.

Validate AIWG configuration files and project setup for correctness and completeness.

Route natural language requests to appropriate skills and workflows.

Generic parallel agent orchestration utility for launching multiple agents concurrently.

Comprehensive project context detection and state awareness.

Load, validate, and populate templates consistently across frameworks.