jcaiagent7143-ui
- 20 skills
- 0 followers
- 1 week ago last updated
- ▌ Add Unit Test · jcaiagent7143-uiWrite a unit test using the project's existing test framework, matching its conventions.
- ▌ Retrieve And Rerank · jcaiagent7143-uiRetrieve top-k chunks for a question, rerank with a cross-encoder, return the top-n with scores.
- ▌ Classify Intent · jcaiagent7143-uiClassify an inbound support message into question / bug / feature / billing / other.
- ▌
- ▌ Screen Positions · jcaiagent7143-uiFilter the user's positions (or a universe) by declarative criteria — return only what matches.
- ▌ Add CLI Command · jcaiagent7143-uiAdd a new subcommand or flag to the project's CLI without breaking existing UX.
- ▌ Fetch Market Data · jcaiagent7143-uiFetch OHLCV / quote / fundamental data from the configured source; never auto-retry on rate limits without backoff.
- ▌ Answer With Citations · jcaiagent7143-uiCompose an answer that cites every factual claim by chunk_id, in a format the verifier understands.
- ▌ Eval Recall Precision · jcaiagent7143-uiRun the project's eval question set and report recall/precision against gold chunk_ids.
- ▌ Compute Technicals · jcaiagent7143-uiCompute standard technical indicators (RSI, SMA, EMA, MACD, Bollinger) on an OHLCV frame; tested against canonical references.
- ▌ Manage Dependency · jcaiagent7143-uiAdd, remove, or pin a Python dependency in pyproject.toml — and only when it's actually needed.
- ▌ Retrieve Kb Answer · jcaiagent7143-uiSearch the project KB and return either a direct answer with citations or "no high-confidence match".
- ▌ Call Tool With Retry · jcaiagent7143-uiCall one tool, retry with exponential backoff on transient errors, log every attempt.
- ▌ Escalate If Unresolved · jcaiagent7143-uiEscalate any open ticket past its SLA to a human, preserving lineage.
- ▌ Aegis · jcaiagent7143-ui bundleApply this self-harnessing methodology yourself — using your own reasoning and your own tools — when about to take a risky, irreversible, or under-evidenced action: financial recommendations, code refactors that ship, multi-step research with citations, numeric computations from raw data, edits that touch production, anything where wrong = real cost. This skill is METHODOLOGY, not delegation. You (the LLM reading this) do all five stages yourself in this conversation. There is no subprocess to call, no other LLM to spin up, no API key needed. You read this skill once, then for each risky task you apply the 5 stages using your existing tools (Bash, Edit, Read, web fetch, whatever you have). Skip this skill for: casual chat, simple formatting, single-line edits, anything where the user accepts an "I don't know" or rough estimate, and anything where the ~3-5× extra thinking is not worth the audit trail.
- ▌ Chunk And Embed · jcaiagent7143-uiSplit source documents into stable-id chunks and embed them into the configured vector store.
- ▌ File Ticket · jcaiagent7143-uiCreate a ticket with intent, priority, and lineage back to the originating conversation turn.
- ▌ Check Style · jcaiagent7143-uiRun the project's lint + formatter before declaring done; fix what's auto-fixable.
- ▌ Check Result · jcaiagent7143-uiVerify the expected effect of a step actually happened before moving to the next.
- ▌ Flag Attention · jcaiagent7143-uiTurn screened matches into a calibrated, sourced summary the user can act on — without recommending action.