ai-engineering-fluency

Find all hardcoded path-to-editor-name mappings in the CLI (cli/src/analysis.ts::getEditorSourceFromPath) and VS Code extension (src/workspaceHelpers.ts::getEditorTypeFromPath), verify they return matching friendly display names for the same path patterns, and confirm every CLI-returned name appears in the EDITOR_ICON_MAP in formatUtils.ts. Use after adding a new editor adapter, after CLI changes, or if JetBrains/other CLI-based consumers show raw editor keys instead of friendly names.

Validate that ~/.copilot/data.db has the required schema for session hierarchy (workspace_parent_links, workspaces, sessions tables and columns). Runs an actual today's-data query so schema regressions are caught early. Use when data.db schema changes may have broken hierarchy enrichment, or on a periodic schedule to detect breaking changes.

Find all hardcoded path-to-editor-name mappings in the CLI (cli/src/analysis.ts::getEditorSourceFromPath) and VS Code extension (src/workspaceHelpers.ts::getEditorTypeFromPath), verify they return matching friendly display names for the same path patterns, and confirm every CLI-returned name appears in the EDITOR_ICON_MAP in formatUtils.ts. Use after adding a new editor adapter, after CLI changes, or if JetBrains/other CLI-based consumers show raw editor keys instead of friendly names.

Find all model IDs referenced in local AI-coding session log files and debug logs, then compare them against the keys in src/modelPricing.json. Reports models found in logs that have no pricing entry (unknown — informational only) and pricing entries never observed locally (unused). Use after adding a new model to modelPricing.json, after seeing unexpected cost attributions, or to discover which new models have appeared in recent sessions. Depends on file discovery patterns from the validate-session-schemas skill.

Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they still match the documented schema, while surfacing newly-discovered fields we could start using. Use after an editor/CLI update, when adding a parser, or on a schedule to catch schema drift early.

Validate that ~/.copilot/data.db has the required schema for session hierarchy (workspace_parent_links, workspaces, sessions tables and columns). Runs an actual today's-data query so schema regressions are caught early. Use when data.db schema changes may have broken hierarchy enrichment, or on a periodic schedule to detect breaking changes.

Find all model IDs referenced in local AI-coding session log files and debug logs, then compare them against the keys in src/modelPricing.json. Reports models found in logs that have no pricing entry (unknown — informational only) and pricing entries never observed locally (unused). Use after adding a new model to modelPricing.json, after seeing unexpected cost attributions, or to discover which new models have appeared in recent sessions. Depends on file discovery patterns from the validate-session-schemas skill.

Loop over recent local AI-coding session log files for every supported file-based platform (Copilot Chat, Copilot CLI, JetBrains, Claude Code, Gemini CLI, Antigravity, OpenCode) and validate they still match the documented schema, while surfacing newly-discovered fields we could start using. Use after an editor/CLI update, when adding a parser, or on a schedule to catch schema drift early.

Load token usage data from Azure Table Storage for faster iteration and analysis in chat conversations

Find all hardcoded URLs in TypeScript source files and verify they resolve (return HTTP 2xx/3xx). Use when you want to validate that links in tips, hints, and documentation strings are still live.

Analyzing GitHub Copilot session log files to extract token usage, model information, and interaction data. Use when working with session files, understanding the extension's log analysis methods, or debugging token tracking issues.

Load and display the last 10 cache entries as raw JSON output. DO NOT create extra files or pretty-print the data - output raw JSON only. Use when you need to understand cached session statistics, debug cache behavior, or work with actual cached data.

Pick one large function flagged by ESLint max-lines-per-function and refactor it into smaller, focused helpers without breaking tests.

Refresh token estimator and model pricing JSON files with latest data from AI model providers

Describes the data files available in the coding agent environment after copilot-setup-steps runs. Use when analyzing downloaded session logs or aggregated usage data.

Keep the Visual Studio and JetBrains webview views (screens) in sync with the VS Code views, while preserving the exact set of views each host ships. Detects views added to the VS Code extension (vscode-extension/esbuild.js entryPoints) that the Visual Studio host (CopilotTokenTracker.csproj + committed webview/*.js) or JetBrains host (jetbrains-plugin/build.gradle.kts) do not yet ship, and surfaces them for a human decision instead of auto-adding. Also refreshes the committed Visual Studio bundles from a fresh dist build so existing views stay current. Use after building/updating the VS Code webviews, before a Visual Studio or JetBrains release, or whenever a host shows stale screens.

Refresh token estimator and model pricing JSON files with latest data from AI model providers

Keep the Visual Studio and JetBrains webview views (screens) in sync with the VS Code views, while preserving the exact set of views each host ships. Detects views added to the VS Code extension (vscode-extension/esbuild.js entryPoints) that the Visual Studio host (CopilotTokenTracker.csproj + committed webview/*.js) or JetBrains host (jetbrains-plugin/build.gradle.kts) do not yet ship, and surfaces them for a human decision instead of auto-adding. Also refreshes the committed Visual Studio bundles from a fresh dist build so existing views stay current. Use after building/updating the VS Code webviews, before a Visual Studio or JetBrains release, or whenever a host shows stale screens.

Analyzing GitHub Copilot session log files to extract token usage, model information, and interaction data. Use when working with session files, understanding the extension's log analysis methods, or debugging token tracking issues.

Load token usage data from Azure Table Storage for faster iteration and analysis in chat conversations

Find all hardcoded URLs in TypeScript source files and verify they resolve (return HTTP 2xx/3xx). Use when you want to validate that links in tips, hints, and documentation strings are still live.

Load and display the last 10 cache entries as raw JSON output. DO NOT create extra files or pretty-print the data - output raw JSON only. Use when you need to understand cached session statistics, debug cache behavior, or work with actual cached data.