Agent Skills: rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
ID: microck/ordinary-claude-skills/rag-implementation
39953
Install this agent skill to your local
Skill Files
The files that make up rag-implementation.
More agent skills
- do-in-stepsExecute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
- commitRead this skill before making git commits
- test-coverage-improverMeasure JS SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.
- ralph-loopRun, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.
- using-redis-token-bucketsUse when adding a bucket-like rate limit backed by Redis: a per-caller budget with burst capacity and continuous refill, a refund path for requests that did no work, or a limit whose Retry-After must be a real wait rather than a window edge. `posthog/token_bucket.py` provides an atomic Lua token bucket (`consume`, `refund`, `peek`) over `posthog.redis.get_client()`. Choose it over DRF `SimpleRateThrottle`/fixed-window cache counters when boundary bursts, top-of-window lockouts, or charge-then-refund semantics matter. Trigger terms: token bucket, rate limit, burst, refill, quota, Retry-After, fixed window, throttle.
- adversarial-reviewCommission an independent review of a change from an isolated reviewer, before opening or updating a PR or on demand by the user. For the agent requesting the review — if you were spawned to review something, you are the reviewer and this is not your skill.