name: "spectre-kickoff" description: "๐ป | Project kickoff with deep research & MVP pathfinding - primary agent" user-invocable: true
kickoff
Input Handling
Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded $ARGUMENTS value.
kickoff: Deep Codebase Research + MVP Path Discovery
Comprehensive codebase research, external best practices, and MVP implementation path with file:line evidence. Output: kickoff document with architecture insights, gap analysis, and implementation options saved to docs/tasks/{task_name}/kickoff/.
ARGUMENTS
Step 1: Acknowledge & Clarify
- Action โ ImmediateReply: Respond before any tools.
- If ARGUMENTS โ acknowledge context, identify: what we're exploring, what decision we're heading toward, what success looks like
- Else โ prompt for project context
- CRITICAL: No tool calls in this step
Step 2: Gather Context & Decompose
- Action โ ReadMentionedDocs: Read referenced docs FULLY in main context (not subagent). Extract: vision, constraints, decisions made, open questions.
- Action โ DecomposeResearchAreas: Break project into research areas. Consider: components to investigate, directories/files, architectural patterns, data flows, existing code to extend.
- Action โ CreateResearchPlan: Use TodoWrite to track research subtasks.
Step 3: Deep Parallel Research
- Action โ SpawnResearchAgents: Launch parallel agents for comprehensive context.
| Agent | Task | Required Output |
|---|---|---|
| @finder | Find relevant files, entry points, handlers, models | File paths by domain |
| @analyst | Trace data flow, dependencies, behavior, edge cases | file:line refs for ALL findings |
| @patterns | Find similar implementations, patterns to follow/avoid | Code examples with file:line |
| @web-research | Best practices, similar solutions, pitfalls | Findings WITH LINKS |
Strategy: locator โ analyzer on findings โ parallel for breadth. Spawn follow-ups if shallow. Demand file:line evidence.
3rd Party Libs: Use Context7 MCP for central libraries.
- Action โ WaitForAgents: ALL agents must complete before synthesis. Update TodoWrite as each completes.
Step 4: Synthesize Understanding
Action โ CompileFindings: Synthesize with file:line refs throughout.
- Codebase: Connect findings across components, document data flow, answer "how does codebase handle [area]?"
- Architecture: Patterns to follow (with examples), conventions, constraints, reuse vs build new
- External: Industry patterns (with links), best practices, pitfalls
Action โ PerformGapAnalysis: Current capabilities (with file refs) vs required capabilities. What's missing vs needs modification.
Action โ IdentifyMVPAndOptions:
- MVP: Core value, minimum for value, what to defer (informed by codebase complexity)
- Options: 2-3 approaches with: summary, key decisions, code to leverage (file refs), new work, effort sense, trade-offs
- Decision points: Architecture, scope, technology, integration, patterns
Step 5: Generate Document
Action โ DetermineOutputDir:
- Derive
task_namefrom context (kebab-case) OUT_DIR = user_specified || docs/tasks/{task_name}/kickoffmkdir -p "$OUT_DIR"
- Derive
Action โ CreateDocument: Structure with YAML frontmatter (date, git_commit, branch, repo, topic, tags, status).
Sections: Title โ Metadata โ Project Context โ Research Summary โ Detailed Codebase Findings (by area, file:line refs, code snippets) โ Code References (table) โ Architecture Insights (patterns, conventions, constraints) โ External Research (with links) โ Gap Analysis โ MVP Suggestion โ Implementation Options (2-3 with trade-offs) โ Decision Points โ Open Questions โ Related Resources
Action โ AddGitHubPermalinks: If on main/pushed, convert file refs to
https://github.com/{owner}/{repo}/blob/{commit}/{file}#L{line}Action โ SaveDocument: Save as
{task_name}_kickoff.md(timestamp variant if exists). CRITICAL: Save before Step 6.
Step 6: Present & Scope
Action โ PresentSummary:
Kickoff Complete โ saved to
{path}Vision: [1-2 sentences] What Exists: [key components with file:line refs] Architecture Insights: [patterns, conventions, constraints] External Learnings: [key insights with links] Gap: [have โ need] MVP Path: [smallest valuable slice]
Scoping Questions (before planning):
- [Scope/boundary question] โ Option A (leverages
code:line) vs Option B - [Technical approach] โ suggested vs alternative
- [Priority/constraint question]
- [Scope/boundary question] โ Option A (leverages
Action โ EngageInScoping: Wait for response, ask follow-ups. No planning until ambiguities resolved. Research answerable questions instead of asking.
Step 7: Handle Follow-ups
- Action โ HandleFollowUps:
- If clarifications โ update doc with
## Scoping Clarifications [timestamp] - If more research needed โ spawn agents, demand file:line evidence, update doc
- Continue until ambiguities resolved
- If clarifications โ update doc with
Step 8: Transition to Scope
Action โ SummarizeAndTransition:
Ready for Scope Definition
Established: User problem, user value, key findings (file:line), decisions made, remaining ambiguities
Options:
- "Proceed with scope" โ
spectre-scopewith FROM_KICKOFF=true, SKIP_EXPLORATION=true - "Skip to planning" โ
spectre-planwith kickoff doc context - "Need to think" โ
spectre-handoff
- "Proceed with scope" โ
Action โ ExecuteChoice:
- If scope โ invoke
spectre-scopewith: FROM_KICKOFF=true, KICKOFF_DOC={path}, SKIP_EXPLORATION=true, context summary - If planning โ suggest
spectre-plan - If pause โ run
spectre-handoff
- If scope โ invoke