Menu
SkillsMP has collected 25 skills from sidagarwal04/click-a-thon-26-submissions. Open a skill to review its source and details.
Showing 25 of 25 collected skills.
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
Use this skill before running any EDA, funnel, or insight query against the Atlys `atlys` ClickHouse database, or before trusting a business/data claim about it. Loads the current business context from `agent_meta.current_context` and explains the…
Use this skill whenever you've verified something new about Atlys (a contradiction, a confirmation, a new table/entity/metric, a resolved open question) and need to write it into the living context layer — the same append-only path this repo's Chronicler…
Ground-truth schema for the Atlys ClickHouse `atlys` database — real table and column names, data quirks, metric formulas, and the planted contradictions in base_context.md to surface. Apply on every Atlys analytics query so column names and metric…
Use when a newly instrumented feature table has been created and you must analyze it end-to-end and produce a PM-ready insight summary AND a machine-readable insights manifest (Atlys/schemas/{spec_name}.insights.json — numeric confidence scores, related known…
Use when analyzing the Atlys 4-step conversion funnel (destination_card_clicked -> application_started -> document_uploaded -> purchase_completed), computing drop-off, step-through, or conversion rate. Provides correct windowFunnel/uniqExact ClickHouse…
How to query the two table shapes in the Atlys `atlys` database — the 8 legacy raw tables have FLAT columns, while every newly instrumented spec is ONE table with a single JSON column named `payload`. Detect the shape with DESCRIBE first, then use the right…
Use when an anomaly or unusual segment/time movement appears in Atlys data and you need to explain the why by correlating it with the documented known-issues log (K1-K7) — e.g. iOS pay drop vs OTP autofill regression. Correlate, don't over-claim causation.
Token-safe, ClickHouse-idiomatic SQL discipline for the Atlys analytics agent — always compute aggregates in ClickHouse and return small result sets, never raw rows. Apply on every query the agent writes.
Use when comparing an Atlys metric across segments (device, os, geo/country, destination, user type, acquisition) to find where performance is unusually good or bad. Provides normalization for messy data and volume guardrails.
Enforce provable context freshness for the Atlys knowledge bundle — bump context_version in overview.md and append a newest-first, dated changelog entry to the reserved log.md listing added/updated/contradiction files and the source, on every context change.…
Surface conflicts and gaps in the Atlys context (base_context.md is deliberately imperfect) as explicit OKF contradiction concepts — the dual "conversion" definition, the ETA column mismatch, os=NULL envelope gaps, the legacy sort key smell, and…
Author and maintain the Atlys living-context bundle as an Open Knowledge Format (OKF) set of markdown concept files under librechat/context_docs/ — scaffold and seed the bundle, determine the update trigger, gather live-schema/DDL/base_context sources, diff…
Optionally mirror the Atlys context bundle into a queryable ClickHouse context_registry table (so the Analytics Agent can fetch the current context version over the ClickHouse MCP) and/or commit + PR the knowledge bundle. Invoke only when queryable lineage or…
The hard validation gate for an Atlys ClickHouse DDL, run on the live ClickHouse Cloud service via the clickhouse_write_tools MCP (run_query) — no shell/chdb needed. Static-lint the .sql for escaped double-quoted literals, then create the DDL against a…
Create the PRODUCTION Atlys schema on the live ClickHouse Cloud instance via the clickhouse_write_tools MCP (HTTP, no CLI) after the MCP validation gate passes — run each DDL statement (CREATE DATABASE / CREATE TABLE / CREATE MATERIALIZED VIEW) as a run_query…
Commit a validated Atlys ClickHouse schema and push it DIRECTLY to the target branch (default master, no feature branch, no PR) using the clickhouse_git_write MCP — no shell/git/gh needed. The MCP holds the repo clone + a GitHub PAT; you call…
Turn an Atlys spec's "Questions the PM will ask" into confirmed metrics, decide whether each warrants a materialized view, and if so generate incremental AggregatingMergeTree MVs that read payload.* from the single base table and filter by payload.event for…
Profile an Atlys NDJSON events file before designing any ClickHouse DDL — detect the event-type discriminator, union-scan every JSON path across all event types, locate the identity and timestamp paths, flag numeric metric paths and boolean/hot-filter paths…
The Atlys ClickHouse DDL pattern — one base table per spec, a single JSON column named `payload`, typed hints for the discriminator + ORDER BY / PARTITION BY paths + every string/bool skip-indexed path (a set/bloom_filter index over an untyped JSON sub-column…
OPTIONAL, confirm-gated step that runs AFTER the schema (+ metrics manifest) has been committed and pushed, but BEFORE the Context Agent handoff. It updates the Vector pipeline config (Atlys/vector-pipeline/vector.toml) so the newly-created ClickHouse table…
Create the PRODUCTION Atlys schema on the live ClickHouse Cloud instance via the clickhouse_write_tools MCP (HTTP, no CLI) after the MCP validation gate passes — run each DDL statement (CREATE DATABASE / CREATE TABLE / CREATE MATERIALIZED VIEW) as a run_query…
Maintain and evolve the Atlys living context layer as an Open Knowledge Format (OKF) bundle under knowledge/. Use when the user says "update the context", "refresh the knowledge base", "run the context agent", "a new table landed — update context", "register…
Onboard a product/spec into ClickHouse by generating a production-ready DDL schema from its NDJSON events file. Use when a user says "onboard product in clickhouse", "onboard this spec into clickhouse", "onboard product to clickhouse", "design a ClickHouse…
Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.