teamcraft-glgd:discover-problem
Facilitate a live problem discovery session with a client or stakeholders. Designed for use during a meeting or call — helps the PM guide structured exploration of a problem space before any requirements are written. Produces a discovery summary in Google Drive that seeds capture-requirements. Works in Claude Cowork and Claude Code.
What this skill does
## Goal Facilitate structured problem discovery with a client or stakeholder — the session that happens before requirements can be written. The PM is in a live conversation. The goal is not to document what the client already knows; it is to help the client discover what the real problem is, surface hidden assumptions, and narrow to a problem statement clear enough to become a PRD. A well-run discovery session ends with: a sharp problem statement, identified root causes, competing hypotheses ranked by evidence, known gaps that need research before committing to a solution, and a clear recommendation on whether to proceed directly to requirements or validate further first. ## Hard Constraints - This skill facilitates a live session. Move at conversation pace — do not overwhelm the PM with questions to relay. Surface one thing at a time. - Never start writing requirements during this session. If the PM or client jumps to solutions, acknowledge the idea, park it, and redirect to the problem. - If a Drive file operation fails with a path error, read the error message to identify a valid accessible host path and retry with it. ## Resolve Drive Account Call `mcp__google-drive__list_accounts` before any other Drive operation: - **No accounts** — Drive is not configured. Tell the user and skip Drive operations — the discovery summary can be shared as session output instead. - **One account** — Use it. Pass `account_email` explicitly on every Drive tool call this session. - **Multiple accounts** — Present the list, ask which account to use for this session. ## Facilitate the Session Start by asking the PM what situation they are walking into — who is in the room, what the client has said so far, and whether there are any existing documents to load as context. Guide the discovery through the problem space. The depth and order follow the conversation, not a fixed script. What matters is reaching a clear problem statement: **Understand the pain** — what is happening that should not be, or not happening that should be? Who experiences it and how often? What does it cost — in time, money, errors, missed opportunities? **Find the root** — what causes the problem? Challenge surface symptoms. Ask why until the real driver emerges. If multiple causes exist, name them separately. **Surface competing hypotheses** — what are the different ways this problem could be solved? Do not evaluate yet — list them. Include the client's initial ideas. **Assess what is known vs. assumed** — for each hypothesis, what evidence supports it? What is being assumed? What would need to be true for this to be the right solution? **Identify gaps** — what do we not know that we need to know before committing to a direction? Is more research needed, or is there enough to write requirements now? ## Use Visuals When They Help When a visual would make the problem clearer — a process flow, a data model, a user journey, a rough UI concept — generate it inline. Mermaid diagrams for flows and relationships. HTML artifacts for interactive UI concepts. Visuals are part of the session, not a separate step. Use them whenever a picture clarifies faster than words. The `frontend-design` plugin, if installed, will automatically improve the quality of any HTML mockup generated during this session. ## Discovery Summary When the session reaches a natural stopping point, produce a discovery summary. See `references/example-discovery-summary.md` for the expected structure and depth. Show the complete summary for review before storing. Confirm content with the PM. Ask the user where in Google Drive to store it — which folder. Never save to the Drive root. Do not search Drive for a location; ask directly. Record the URL. ## Done Share the Drive URL. If the problem is well-enough understood to write requirements, the natural next step is `capture-requirements` — point at this discovery summary as the primary input. If more research is needed first, say so explicitly and name what questions need answers before a PRD session makes sense.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.