← all publishers

jcaiagent7143-ui

@jcaiagent7143-ui source repo

20 published skills

  1. Add Unit Test · jcaiagent7143-ui
    Write a unit test using the project's existing test framework, matching its conventions.
    1 install
  2. Retrieve And Rerank · jcaiagent7143-ui
    Retrieve top-k chunks for a question, rerank with a cross-encoder, return the top-n with scores.
    1 install
  3. Classify Intent · jcaiagent7143-ui
    Classify an inbound support message into question / bug / feature / billing / other.
    1 install
  4. Decompose Task · jcaiagent7143-ui
    Turn a user task into an ordered, executable plan of named steps.
    1 install
  5. Screen Positions · jcaiagent7143-ui
    Filter the user's positions (or a universe) by declarative criteria — return only what matches.
    1 install
  6. Add CLI Command · jcaiagent7143-ui
    Add a new subcommand or flag to the project's CLI without breaking existing UX.
    1 install
  7. Fetch Market Data · jcaiagent7143-ui
    Fetch OHLCV / quote / fundamental data from the configured source; never auto-retry on rate limits without backoff.
    1 install
  8. Answer With Citations · jcaiagent7143-ui
    Compose an answer that cites every factual claim by chunk_id, in a format the verifier understands.
    1 install
  9. Eval Recall Precision · jcaiagent7143-ui
    Run the project's eval question set and report recall/precision against gold chunk_ids.
    1 install
  10. Compute Technicals · jcaiagent7143-ui
    Compute standard technical indicators (RSI, SMA, EMA, MACD, Bollinger) on an OHLCV frame; tested against canonical references.
    1 install
  11. Manage Dependency · jcaiagent7143-ui
    Add, remove, or pin a Python dependency in pyproject.toml — and only when it's actually needed.
    1 install
  12. Retrieve Kb Answer · jcaiagent7143-ui
    Search the project KB and return either a direct answer with citations or "no high-confidence match".
    1 install
  13. Call Tool With Retry · jcaiagent7143-ui
    Call one tool, retry with exponential backoff on transient errors, log every attempt.
    1 install
  14. Escalate If Unresolved · jcaiagent7143-ui
    Escalate any open ticket past its SLA to a human, preserving lineage.
    1 install
  15. Aegis · jcaiagent7143-ui bundle
    Apply 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.
    1 install
  16. Chunk And Embed · jcaiagent7143-ui
    Split source documents into stable-id chunks and embed them into the configured vector store.
    1 install
  17. File Ticket · jcaiagent7143-ui
    Create a ticket with intent, priority, and lineage back to the originating conversation turn.
    1 install
  18. Check Style · jcaiagent7143-ui
    Run the project's lint + formatter before declaring done; fix what's auto-fixable.
    1 install
  19. Check Result · jcaiagent7143-ui
    Verify the expected effect of a step actually happened before moving to the next.
    1 install
  20. Flag Attention · jcaiagent7143-ui
    Turn screened matches into a calibrated, sourced summary the user can act on — without recommending action.
    1 install