context fetch
2
总安装量
0
周安装量
#65542
全站排名
安装命令
npx skills add https://github.com/toonight/get-shit-done-for-antigravity --skill 'Context Fetch'
Skill 文档
Context Fetch Skill
Core principle: Search first, read targeted sections, never load full files blindly.
When to Use
Activate this skill before:
- Starting any coding task
- Beginning a refactor
- Investigating a bug
- Understanding unfamiliar code
Process
Step 1: Define the Question
What are you trying to find or understand?
Examples:
- “Where is the login endpoint defined?”
- “How does the caching layer work?”
- “What calls the
processPaymentfunction?”
Step 2: Identify Keywords
Extract searchable terms:
| Question | Keywords |
|---|---|
| Login endpoint | login, auth, POST.*login |
| Caching layer | cache, redis, memoize |
| Payment calls | processPayment, payment |
Step 3: Search Before Reading
PowerShell:
# Simple pattern search
Select-String -Path "src/**/*.ts" -Pattern "login" -Recurse
# With ripgrep (if available)
rg "login" --type ts
Bash:
# With ripgrep (recommended)
rg "login" --type ts
# With grep
grep -r "login" src/ --include="*.ts"
Step 4: Evaluate Results
From search results, identify:
- Primary candidates â Files directly matching your question
- Secondary candidates â Files that reference primary candidates
- Ignore list â Files with keyword but unrelated context
Step 5: Targeted Reading
Only read what’s justified:
# Read specific line range (PowerShell)
Get-Content "src/auth/login.ts" | Select-Object -Skip 49 -First 30
# Read specific function (with view_code_item tool)
# view_code_item: src/auth/login.ts -> handleLogin
Inputs
When invoking this skill, provide:
| Input | Description | Example |
|---|---|---|
| Question | What you’re trying to find | “Where is user validation?” |
| Scope | Directory or file pattern | src/, *.service.ts |
| Keywords | Terms to search for | validate, user, schema |
Outputs
After executing this skill, report:
- Candidate files â Ranked by relevance
- Relevant extracts â Key snippets found
- Next reads â Specific files/line-ranges to read next
- Skip list â Files searched but not relevant
Anti-Patterns
â Loading Everything First
# BAD: Reading 5 full files to "understand context"
Read: src/auth/login.ts (500 lines)
Read: src/auth/register.ts (400 lines)
Read: src/auth/types.ts (200 lines)
â Search Then Target
# GOOD: Search first, read only what's needed
Search: "validatePassword" in src/auth/
Found: login.ts:45, register.ts:78
Read: login.ts lines 40-60
â Broad Searches
# BAD: Searching for common terms
Search: "function" â 10,000 results
â Specific Searches
# GOOD: Searching for specific identifiers
Search: "validateUserCredentials" â 3 results
Context Efficiency Metrics
Track your efficiency:
| Metric | Good | Poor |
|---|---|---|
| Files searched | 10+ | <5 |
| Files fully read | <3 | 10+ |
| Lines read | <200 | 1000+ |
| Targeted sections | Yes | No |
Integration with GSD
This skill supports GSD’s context management:
- Prevents context pollution â Less irrelevant code loaded
- Supports wave execution â Each wave starts with minimal context
- Enables model switching â Less context = easier handoff
Quick Reference
1. Define question â What am I looking for?
2. Extract keywords â What terms to search?
3. Search codebase â rg/grep/Select-String
4. Evaluate results â Which files matter?
5. Read targeted â Specific lines only
6. Report findings â Candidates + extracts
Part of GSD methodology. See PROJECT_RULES.md for search-first discipline rules.