All skills
algorithm-data-structure-selection
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when scale, access, complexity, memory, streaming, or skew drives an algorithm/data-structure choice; skip when no choice exists.
- Group
- Technology selection
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- algorithm data structure Big O input size worst case memory budget map set list heap queue deque tree trie graph bloom filter LRU LFU interval tree segment tree top K dedupe grouping sorting streaming chunking pagination nested scan load all hot key skew
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local algorithm data structure selection decision is required
Required inputs
What must be supplied before this skill can decide anything
- current task contract
- selected primary Professional Skill
- task-local trigger evidence
Output contract
What this skill owes the next role
- Algorithm Decision: problem shape, input scale, selected structure, time/space bounds, memory budget, streaming/chunking choice, alternatives, benchmarks, and scale risk
Escalation signals
When this skill must hand the decision back
- Working code can still fail at production scale through O(n squared) nested scans unbounded memory full sorting load-all processing and mismatched data structures
Loaded by
This skill never owns a task. These professionals may pull it in as Layer 3.
Targeted references
Each reference carries its own load condition. None of them enter context by default.
| Reference | Load when | Do not load when | Required by |
|---|---|---|---|
| benchmarks-and-patterns.mdbenchmark-pattern | Scale, skew, ordering, exactness, or memory changes the algorithm. | The bounded operation has no material complexity tradeoff. | TaskReviewAnalysis |
| checklist.mddecision-checklist | Selection must cover worst-case growth, ordering, and oversize behavior. | Input bounds and correctness semantics are already explicit. | TaskReviewAnalysis |
| evidence-patterns.mdevidence-pattern | Performance claims require representative benchmarks, profiles, or query plans. | No scale or hot-path claim needs empirical proof. | TaskReviewAnalysis |