Name: cx-data-pipeline
Rating: 68.8 (1 reviews)
Author: coralogix

cx-data-pipeline

Use this skill when the user asks to "set up parsing", "create parsing rule", "extract fields from logs", "regex extraction", "log parsing", "enrich logs", "add context to logs", "custom enrichment table", "lookup table", "geo enrichment", "create metric from logs", "events to metrics", "convert logs to metrics", "generate metrics from events", "recording rule", "precomputed metrics", "PromQL recording", "configure data pipeline", "transform log data", "data processing rules", "rule group", "enrichment settings", "E2M definition", "labels cardinality", "bulk delete rules", "enrichment limits", "search enrichment table", "what should I convert to metrics", "E2M not producing metrics", "E2M no series", "reduce log cost with E2M", "logs to metrics aggregation", "spans to metrics", or wants to configure how Coralogix processes, enriches, or transforms ingested data.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable skill body: concrete CLI commands, executable payload templates, and four sequenced workflows with explicit verification steps plus a real troubleshooting feedback loop. The main improvements are consolidating the E2M compute-model explanation with the reference file and adding a validation step before the destructive bulk-delete operation.

Suggestions

Trim the 'How E2M is computed' section to a 2-3 line summary (forward-only, tier decides) and point to references/e2m-schemas.md for the full tier table and caveats, removing the duplication between the two files.

Add a pre-delete validation step for 'cx parsing-rules bulk-delete' — e.g., run 'cx parsing-rules list -o json', confirm the IDs and rule counts with the user, then delete — since it is a destructive batch operation.

Consolidate the repeated tier warnings ('not Frequent Search vs archive' appears in both the workflow and troubleshooting sections) into one location.

Dimension	Reasoning	Score
Conciseness	The body is command-first and lean: tables of subcommands, short workflows, concrete payload examples, and no explanation of concepts Claude already knows. It loses a point because the 'How E2M is computed' section (tier table, forward-only warning, 'not Frequent Search vs archive' caveat) substantially duplicates content in references/e2m-schemas.md and could be trimmed to a summary plus pointer.	4 / 5
Actionability	Fully executable throughout: copy-paste-ready cx commands with flags, jq pipelines for templating (e.g., 'cx e2m get ... \| jq ".e2m \| del(.id, ...)"'), and concrete JSON payload shapes including the v5 custom-table format and requestEnrichments structure. Specific examples cover the common cases for all four command families.	5 / 5
Workflow Clarity	All four workflows have clear numbered sequences with explicit verification checkpoints ('Verify Parsing', 'Verify Enriched Fields', 'Verify the metric', 'Verify with PromQL') and pre-flight limits checks, and the E2M troubleshooting section is a genuine feedback loop. Not 5 because the destructive batch operation 'cx parsing-rules bulk-delete' has no pre-delete validation step (e.g., list and confirm IDs first).	4 / 5
Progressive Disclosure	Good structure with a single well-signaled, one-level-deep reference (references/e2m-schemas.md, which exists and matches its in-body description), with E2M schema detail correctly pushed out of SKILL.md. Not 5 because the E2M compute-model prose is duplicated between the body and the reference rather than cleanly split, so placement is only mostly appropriate.	4 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A trigger-rich, highly scannable description with excellent natural-language coverage and an explicit use-when clause. Its main weakness is that the skill's actual capability is never stated directly — the 'what' must be inferred from the trigger list — and a handful of generic phrases carry mild overlap risk with adjacent skills.

Suggestions

Open with an explicit capability statement in third person (e.g., 'Manages Coralogix parsing rules, enrichments, custom enrichment tables, Events2Metrics definitions, and PromQL recording rule groups via the cx CLI') before the trigger list.

Qualify the generic phrases ('rule group', 'data processing rules', 'configure data pipeline') with the Coralogix context to reduce overlap with Prometheus or generic data-pipeline skills.

Dimension	Reasoning	Score
Specificity	The description names many concrete actions ('extract fields from logs', 'convert logs to metrics', 'geo enrichment', 'recording rule', 'spans to metrics'), giving broad coverage, but the capability statement is only implied through trigger phrasing rather than an explicit 'this skill manages X' statement. Not 5 because the concrete actions are framed exclusively as user prompts, leaving minor gaps in stating what the skill does; not 3 because coverage goes well beyond 1-2 actions.	4 / 5
Completeness	The 'when' is exceptionally explicit ('Use this skill when the user asks to...'), but the 'what' is only weakly implied by the trigger list — the reader must infer that the skill manages Coralogix parsing/enrichment/E2M/recording rules. Not 5 because the what is never directly stated; not 3 because the trigger list does convey the capability space concretely alongside an explicit when.	4 / 5
Trigger Term Quality	Comprehensive natural phrasing users would actually say, including synonyms ('log parsing'/'regex extraction', 'events to metrics'/'logs to metrics aggregation') and troubleshooting variants ('E2M not producing metrics', 'E2M no series', 'reduce log cost with E2M'). Matches the anchor for comprehensive coverage including synonyms; nothing material is missing.	5 / 5
Distinctiveness Conflict Risk	Most triggers are clearly niche ('E2M definition', 'custom enrichment table', 'Coralogix' appears in the closing clause), giving a clear domain. A few generic phrases ('rule group', 'data processing rules', 'configure data pipeline') could overlap with Prometheus or general data-pipeline skills, which keeps it just below the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: coralogix/cx-cli
Path: skills/cx-data-pipeline/SKILL.md
Commit: c071372

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.