# Agentdb Optimization

> Performance tuning for AgentDB across indexing, storage, and query paths.

- Skill: `majiayu000/agentdb-optimization` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds add majiayu000/agentdb-optimization`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/agentdb-optimization/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/agentdb-optimization

---





## Purpose
Reduce latency and cost while preserving recall through disciplined benchmarking.

## Trigger Conditions
- **Use this skill when:** Need to tune index params, hardware sizing, or quantization strategies.
- **Reroute when:** If designing features or memory patterns, use other AgentDB skills first.

## Guardrails (Inherited from Skill-Forge + Prompt-Architect)
- Structure-first: every platform skill keeps `SKILL.md`, `examples/`, and `tests/` populated; create `resources/` and `references/` as needed. Log any missing artifact and fill a placeholder before proceeding.
- Confidence ceilings are mandatory in outputs: inference/report 0.70, research 0.85, observation/definition 0.95. State as `Confidence: X.XX (ceiling: TYPE Y.YY)`.
- English-only user-facing text; keep VCL markers internal. Do not leak internal notation.
- Adversarial validation is required before sign-off: boundary, failure, and COV checks with notes.
- MCP tagging for runs: `WHO=agentdb-optimization-{session}`, `WHY=skill-execution`, namespace `skills/platforms/agentdb-optimization/{project}`.

## Execution Framework
1. **Intent & Constraints** — clarify task goal, inputs, success criteria, and risk limits; extract hard/soft/inferred constraints explicitly.
2. **Plan & Docs** — outline steps, needed examples/tests, and data contracts; confirm platform-specific policies.
3. **Build & Optimize** — apply platform playbook below; keep iterative checkpoints and diffs.
4. **Validate** — run adversarial tests, measure KPIs, and record evidence with ceilings.
5. **Deliver & Hand off** — summarize decisions, artifacts, and next actions; capture learnings for reuse.

## Platform Playbook
- **Workflow patterns:**
  - Benchmark search latency/recall across ef_search/ef_construction
  - Apply quantization or PQ and track quality delta
  - Profile ingestion and background maintenance tasks
- **Anti-patterns to avoid:** Benchmarking without fixed datasets, Tuning latency while ignoring recall regressions, Changing multiple knobs without baselines
- **Example executions:**
  - Compare HNSW parameter sets to hit <10ms p99
  - Enable 8-bit quantization and validate recall remains above target

## Documentation & Artifacts
- `SKILL.md` (this file) is canonical; keep quick-reference notes in `README.md` if present.
- `examples/` should hold runnable or narrative examples; `tests/` should include validation steps or checklists.
- `resources/` stores helper scripts/templates; `references/` stores background links or research.
- Update `metadata.json` version if behavior meaningfully changes.

## Verification Checklist
- [ ] Trigger matched and reroute considered
- [ ] Examples/tests present or stubbed with TODOs
- [ ] Constraints captured and confidence ceiling stated
- [ ] Validation evidence captured (boundary, failure, COV)
- [ ] MCP tags applied for this run

Confidence: 0.70 (ceiling: inference 0.70) - Standardized platform skill rewrite aligned with skill-forge + prompt-architect guardrails.