Research enterprise context before plan mode — surface design docs, similar implementations, stakeholders, and related systems before architecting or designing a feature.
55
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./plugins/glean/skills/plan-prep/SKILL.mdResearch enterprise context before entering plan mode by gathering design docs, similar implementations, stakeholders, and related systems.
Use plan prep when users:
Better planning comes from enterprise context:
Local tools only see your current repo. This workflow searches your entire organization for existing decisions, patterns, and knowledge.
Filter aggressively for relevant, current information.
| Test | ✅ Include | ⚠️ Note | ❌ Exclude |
|---|---|---|---|
| Freshness | <6 months | 6-12 months | 12+ months |
| Relevance | Directly applies | Similar context | Keyword match only |
| Authority | Approved RFCs, official docs | Team wiki, proposals | Rejected/abandoned work |
| Quality | Well-reasoned, proven | Has tradeoffs | Experimental, hacky |
Quality over quantity: 3-4 high-quality findings beat 10 weak ones.
| Research Need | Glean Tool |
|---|---|
| Find design docs, RFCs, architecture | search |
| Find similar code implementations | code_search |
| Find code owners and stakeholders | code_search + employee_search |
| Find related/dependent systems | code_search |
| Read full document content | read_document |
Find design documents, RFCs, and architectural decisions related to the task:
search "[task] architecture OR design doc"
search "[task] RFC OR proposal"
search "[task] pattern OR best practice"Look for:
Search for similar implementations across the codebase:
code_search "[task] implementation OR pattern"
code_search "[related systems] updated:past_month"Look for:
Find who's actively working on related systems:
code_search "[relevant systems] owner:* updated:past_month"
employee_search "[systems and names identified]"Look for:
Identify upstream and downstream dependencies:
code_search "[main system] calls OR depends OR imports"
code_search "[main system] updated:past_month"For each piece of research, apply the vetting criteria above. Reject stale, tangential, or low-quality content.
Present vetted research findings organized by category:
# Planning Context: [Task]
## Design & Architecture
### Current Standards & Patterns
| Pattern | Description | Source | Updated |
|---------|-------------|--------|---------|
| [pattern] | [what it is and why] | [doc link] | [date] ✅ |
### Relevant Design Documents
| Document | Type | Key Takeaway | Updated |
|----------|------|--------------|---------|
| [Title] | RFC | [1-2 sentence summary] | [date] ✅ |
## Implementations & Patterns
### Recommended Examples
| Location | What It Does | Why It's Good | Status |
|----------|--------------|---------------|--------|
| [repo/path] | [brief description] | [Why recommend] | Active ✅ |
## Stakeholders & Ownership
### Active Owners
| Name | Role | Involvement | Contact |
|------|------|-------------|---------|
| [Name] | [Title] | [X] commits past month in [system] | [email] |
### Teams & Channels
- **Primary Team**: [team name]
- **Slack Channel**: [#channel] for questions
## Related Systems
- **Upstream** (depend on this): [systems]
- **Downstream** (this depends on): [systems]
## Key Insights
- [Important constraint or opportunity]
- [Proven pattern or anti-pattern]
- [Stakeholders who must be involved]
## Sources
| Document | Type | Relevance | Currency |
|----------|------|-----------|----------|
| [Title](URL) | RFC | [how it applies] | [date] ✅ |Don't pad with weak results:
# Planning Context: [Task]
## Limited Research Available
Found limited enterprise context for this task.
**What was searched:** Design docs, similar implementations, related systems
**Gaps:** No recent design docs, limited prior art
**Suggested next steps:**
1. Check with [suggested team] about prior attempts
2. Enter plan mode and design initial approach, then validate with stakeholdersa549de6
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.