discernment-nudge
claudeAppends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
19 skills
Build searchable context over documents or your own datastore, answer questions from live data, query a property graph through SQL, read cached documents by section, and reuse the queries that already worked instead of rewriting them. Bundles the auto-context, retrieval, graph-source, graph-rag, document-cache, and skardi-query-log skills.
Plugin skardi from marketplace skardi-skills in SkardiLabs/skardi-skills. Commands read from the repo's manifest — 20 days ago.
auto-contextTurn a folder of documents, a table you already have, or documents still inside a service (a wiki, cloud docs, a mailbox) into governed searchable context an agent can query — hybrid search (vector + full-text) served over HTTP by skardi-server. Three raw-material entries, one flow: ingest a folder;
document-cacheCache the local documents you read in the user''s personal Skardi workspace, so that when the user refers to the same file again you read only the sections you need instead of the whole file. Use whenever you are about to read a local PDF, DOCX, XLSX or PPTX of any real size, and whenever the user r
graph-ragAnswer a question about a knowledge graph or property graph served by a skardi-server — including graphs stored in Postgres via Apache AGE. Two shapes, one skill: when the question already names the entity (what implements UpgradeStep, who calls verify_token, what does this class extend) go straight
graph-sourceConnect a property graph (knowledge graph, GraphRAG corpus, Apache AGE / openCypher data) to Skardi and query it through SQL, end to end: provision the AGE backend with a least-privilege role, declare the `type: graph` source and its views in context YAML, verify registration health, write correct q
retrievalAnswer questions from live data through a running skardi-server using the skardi CLI. Discover at runtime what sources and named pipelines the server has (and table schemas where the deployment exposes them), run the question through any semantic search surface first (search-hybrid and friends), the
skardi-query-logBefore you send Skardi another ad-hoc SQL statement, check whether you have already asked this question — if you have, reuse the SQL that worked instead of rewriting it. **Come here after a failure too**: the errors record what the system cannot answer and where people have guessed wrong before. **Y
Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
19 skills
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.