Skill Claude CodeCodex
Find usage examples of an API, library, or code pattern across internal repositories — use when looking for how other teams use an internal API, library, or pattern before implementing something new.
Skill Claude CodeCodex
Find subject matter experts on a topic, technology, or internal system by combining real expertise signals (code contributions, document authorship, and meeting or discussion activity) rather than relying on job titles. Use this whenever the user wants to know who to ask about something — phrasings such as who knows…
Skill Claude CodeCodex
Discover and run Glean skills for enterprise app tasks.
Skill Claude CodeCodex
Prepare for an upcoming meeting — surface context from past meetings, related docs, and attendee information. Trigger phrases include "prep for my meeting", "context for the meeting", "what should I know before", "1:1 prep with", "prepare for [name]", "background on this meeting", "agenda context", "talking points…
Skill Claude CodeCodex
Get up to speed on a new team, project, or area — surface key people, foundational docs, current priorities, and recent activity. Trigger phrases include "onboard me on", "get me up to speed on", "intro to [team / area / project]", "I'm new to", "help me understand [team]", "where do I start with", "ramp up on"…
Skill Claude CodeCodex
Research enterprise context before plan mode — surface design docs, similar implementations, stakeholders, and related systems before architecting or designing a feature.
Skill Claude CodeCodex
Quick project context — surface a project's status, owner, recent activity, and key links. Use when the user wants a fast situational read on a project (trigger phrases include what's the status of, who owns, what's happening with, where does the project stand) rather than a deep handoff document.
Skill Claude CodeCodex
Generate a comprehensive handoff document so someone new can take over a project — current state, key people, essential knowledge, open items, and a first-30-days plan. Use when the user is handing off a project (trigger phrases include "generate a handoff", "hand off this project", "create a handoff doc", "I'm going…
Skill Claude CodeCodex
Search Glean enterprise knowledge - use for find the doc about, search for, where is, look up, search company knowledge, search Glean for; returns vetted results with freshness and authority indicators. For broader enterprise queries needing synthesis across multiple tools, prefer the using-glean skill instead.
Skill Claude CodeCodex
Find similar implementations and prior art for a code pattern across internal repositories — use when checking whether something already exists internally before building it, or looking for reference implementations to follow.
Skill Claude CodeCodex
Guide the user through authoring a new agent skill — when a skill is worth creating, the SKILL.md format, progressive disclosure, and common pitfalls. Also covers discovering skill opportunities from the user's work patterns and generating a SKILL.md from a description. Trigger phrases include "create a skill", "write…
Skill Claude CodeCodex
Identify people who need to approve, consult on, or be informed about a change or project — use when someone asks who needs to know about a change, who should be looped in, who needs to approve, who should be consulted, who is affected, or needs a RACI for a change, refactor, migration, or decision.
Skill Claude CodeCodex
Search and analyze internal source code across the organization's repositories — use when asked how something is implemented, where the code for a system lives, who has been working on a codebase, or to find similar patterns across teams. Trigger phrases include how is X implemented, where is the code for, find the…
Skill Claude CodeCodex
Synthesize the user's own work activity, priorities, and recent context using Glean — use when the user asks about their recent work, what they accomplished, what is urgent, what needs their attention, or wants help with status updates, 1:1 prep, or weekly summaries. Trigger phrases include what have I been working…
Skill Claude CodeCodex
Use Glean MCP tools to answer questions about company documents, internal wikis, policies, RFCs, design docs, people, teams, meetings, decisions, action items, email, calendar events, internal code, and the user's own work activity. Reach for this whenever the answer lives in enterprise systems rather than the local…
Skill Claude CodeCodex
Verify an RFC or design doc against the actual implementation — find drift, missing pieces, and undocumented changes. Trigger phrases include "verify the RFC", "compare design doc to implementation", "is the spec implemented", "does the code match the design", "what's drifted from the RFC", "audit the doc against"…
Instructions file CodexOpenCode
Instructions for gleanwork/mcp-server-tester, covering agents.md, project overview, common commands, build (includes ui reporter build) and unit tests (vitest).
Instructions file
Instructions for gleanwork/mcp-server-tester, a project described as: Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge.
Skill Claude CodeCodex
Reference guide for @gleanwork/mcp-server-tester — the Playwright-based testing and evaluation framework for MCP servers. Covers import paths, all 11 matchers, transport config, eval datasets, reporter setup, CLI commands, auth patterns, and common anti-patterns. Use when working with MCP server tests or evals.
Skill Claude CodeCodex
Run AI-driven tool-metadata optimization experiments for MCP servers using runVariantExperiment. Use when asked to improve tool descriptions, input schemas, or parameter descriptions, fix tool triggering, optimize tool discoverability, or run variant experiments against an eval dataset. Produces a measured…
Skill Claude CodeCodex
Generate data-driven eval datasets for MCP server testing. Use when asked to create evals, evaluation datasets, or data-driven tests for MCP tools. Produces JSON eval datasets and Playwright test runners for @gleanwork/mcp-server-tester.
Skill Claude CodeCodex
Generate LLM host simulation evals for MCP servers. Use when asked to test tool discoverability, write mcphost evals, or validate tool descriptions with real LLM calls. Produces eval datasets and test runners where an LLM discovers and calls tools from natural language scenarios.
Skill Claude CodeCodex
Generate Playwright tests for MCP server tools. Use when asked to write MCP tests, test MCP tools, or create test files for an MCP server. Produces direct-mode tests using @gleanwork/mcp-server-tester fixtures.
Instructions file
Instructions for gleanwork/pluginpack, covering pluginpack — agent guide, commands, architecture, targets and conformance.