Meta-skill that audits health of the entire product launch engine, identifies broken links between phases, and generates improvement roadmaps. Use when: system health, skill audit, launch engine health, are our skills working together, process audit, workflow health check.
Launch orchestration and readiness assessment engine with cross-functional workstream tracking and go/no-go gates. Use when: launch readiness, launch checklist, launch orchestration, go no go, launch plan, are we ready to launch.
This skill should be used when the user asks to "bump the version", "release a new version", "prepare a release", "update the version number", "version bump", or needs to determine and apply a semver version increment based on recent commits.
This skill should be used when the user asks to "extract agent trajectory", "convert HAR to trajectory", "get trajectory from session", "parse agent session", "convert Claude Code logs", "convert Copilot CLI logs", "extract ATIF", or needs to convert HAR files or JSONL session logs into ATIF trajectory JSON using the…
Use this skill when asked to search public content platforms such as Bilibili or YouTube, pick the top relevant results for a topic, and summarize each item with links and brief overviews. Uses Runtime-aware routing — opencli first, fetch second, browser last.
Use this skill when investigating, adding, validating, or debugging external website profiles for the 99idea Playwright browser demo. It teaches how to probe selectors, classify failure modes, add config-driven profiles, and validate both heuristic and Gemini flows.
Use this skill when asked to work with an unfamiliar public website and the goal is to make progress generically before writing site-specific rules. It teaches Copilot how to probe controls, classify UI patterns, try multiple search and navigation strategies, follow popups, and only create a site profile when the…
Failure-aware multi-agent mission coordinator. Activate when the user invokes /collab or explicitly requests a multi-agent review, implementation, or audit mission.
Consolidated design questionnaire — get a design right on the first go by front-loading clarifying questions into one convenient web form instead of a long back-and-forth. The inverse (in cadence) of "grilling": first look up facts, ask 1-5 grilling-style "bearing" questions one at a time, then generate a capped (20…
Capture a screenshot from the currently connected Android device using ADB, wake the device first, detect the foreground app, save a PNG to system temp, and return the saved path. Use when users ask for screenshots from Android apps running on a connected device or emulator.
Forecast monthly quota burn rate and report risk before reset date. Use when user asks about quota, burn rate, credits remaining, or whether they will run out before month end.
Capture a DPI-correct, full-content PNG of a native Windows app window by title substring and return the saved file path. Use when users ask for screenshots of running Windows apps (for example Flutter desktop apps, VS Code, PowerShell, or Chrome app windows). Do not use for browser-harness page screenshots.
MCP server development: build, create, and test Model Context Protocol servers in TypeScript or Python. Tool design, input/output schemas, Zod/Pydantic validation, evaluations, stdio/HTTP transport, @modelcontextprotocol/sdk, FastMCP.
Copilot CLI plugin scaffolding and creation workflow. Covers requirements gathering, component planning, directory structure, implementation, validation, and testing. Use for new plugin projects or guided plugin development.
Hook development for Copilot CLI plugins: hooks.json, preToolUse/postToolUse/agentStop/sessionStart hooks, command hooks, event-driven validation, tool blocking, policy enforcement. Use when creating or debugging plugin hooks.
A rebuild and deployment guide for applying code changes to an already installed Engram environment. It determines whether to refresh the source version or rebuild the packaged executable.
A procedure for starting a fresh Engram overlay session, where the overlay is a persistent on-screen conversation layer. It clears the current session identifier so the next message starts without earlier context.
2 7d agoA102 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: