Skill Detail

Retrieve upstream implementation evidence before coding with XERJ

Build a focused reference corpus, retrieve implementation passages with file-and-line citations, and check license constraints before adapting unfamiliar code.

Developer ToolsMulti-Framework
Developer Tools Multi-Framework Security Reviewed
⭐ 17.2k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill retrieve-upstream-implementation-evidence-before-coding-with-xerj Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
XERJ binary; Git; reachable XERJ node; shell-capable agent or configured MCP client
Install & setup
Use the upstream v1.0.0-rc.100 release or official installation instructions to install the platform binary; the shell installer places it in ~/.local/bin. On a trusted single-user dev machine, start xerj –insecure –data-dir ~/xerj-data and wait for the loopback node at http://localhost:9200. This disables TLS/auth; use the documented authenticated configuration on shared hosts. Keep storage outside indexed directories. Add the binary directory to PATH if required. Then run xerj corpus add reference-task …, xerj corpus index reference-task, and xerj code reference-task "". No npm dependency is asserted. For MCP, configure the absolute binary path with argument mcp and the appropriate XERJ_URL; this proxy requires an already running node.
Author
xerj-org
Publisher
Organization
Last updated
Oct 28, 2026
Quick brief

Use this workflow before implementing against an unfamiliar API, porting an algorithm, or continuing a coding task that has stalled through repeated guesses. The agent selects reference repositories relevant to the specific problem, indexes a focused corpus, and retrieves implementation evidence before editing the target project.

How it works

What this skill actually does

Inputs are the coding question, the selected repository URLs or a locally downloaded corpus manifest, and a running XERJ node. Keep reference corpora separate from the working repository. The result is a short implementation brief containing relevant passages, source paths and lines, recorded revisions and licenses, and an explanation of what can be adapted.

  1. Choose a small corpus by problem domain. Register references with xerj corpus add reference-task <git-url>..., or reproduce recorded revisions with xerj corpus add --from ./corpus.json. A manifest must be a local file. Use dedicated managed clones: reproducing a manifest can discard edits inside existing corpus clones.
  2. Run xerj corpus index reference-task against the running node. Check its completion and xerj corpus list before trusting coverage. Indexing exit 3 indicates completion with skipped or junk files; it differs from query exit 3.
  3. Ask a specific implementation question with xerj code reference-task "the contract or algorithm needed". The default BM25 mode does not require configuring vector retrieval. Read the returned definitions and cite their file-and-line locators.
  4. Explain the reference’s assumptions and license constraints before adapting its approach. Preserve provenance in the implementation brief. Irrelevant or weak matches require normal source inspection or another corpus. Query exit 1 is a miss, exit 2 an operational refusal or error, and exit 3 means the corpus is not loaded on this node.

Invoke this when the agent needs implementation precedent and a reproducible reference set. Ordinary file reads remain appropriate for small edits or APIs already understood. This entry covers reference selection, indexing, retrieval and the evidence handoff; it does not cover general database administration, shared agent memory, Corpus Hub publishing, automated code copying, or external feedback submission.

The native CLI can be called by multiple agent runtimes. Shell-free MCP clients can query an already prepared corpus through xerj_code_search using the upstream registration instructions. Keep node storage outside indexed trees. The documented --insecure startup is only for a trusted single-user loopback environment: it disables TLS and authentication and grants reachable callers full access. Shared deployments require the documented authenticated configuration.

Metadata and invocation documentation were verified against upstream; no runtime installation or security review was performed. See the pinned reference-coding skill and reviewed release.