Name: cx-olly
Rating: 64.8 (1 reviews)
Author: coralogix

cx-olly

This skill should be used when the user asks to "chat with AI", "ask Olly", "ask the agent", "send message to AI", "continue a chat", "follow up on chat", "get artifact", "download artifact", "list artifacts", "retrieve generated content", "AI-generated charts", "AI analysis", "conversational observability", "natural language query", or wants to interact with the Coralogix Observability Agent (Olly) using the cx CLI.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/cx-olly/SKILL.md

Quality

Content

75%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 well-structured, highly actionable skill body with concrete CLI examples and clear workflows. Its weaknesses are minor: a duplicated recap of the agent-to-agent/async points and the absence of an executable example for the backgrounding-and-polling pattern it insists on.

Suggestions

Add one concrete background-and-poll example (e.g., `cx olly ask "..." --agent-to-agent-mode > /tmp/olly.out 2>&1 &` plus a poll loop) since 'async by default' is emphasized throughout but never shown how to execute.

Collapse the Key Principles recap entries that merely restate --agent-to-agent-mode and async-by-default already covered above, keeping only principles that add new information.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (no explaining of basic concepts), but the --agent-to-agent-mode and async-by-default points are restated across the intro, dedicated section, and Key Principles recap, which is minor over-explanation that could be trimmed.	4 / 5
Actionability	Copy-paste-ready `cx olly` commands with specific flags cover the common cases (start/continue chat, model selection, timeout, artifacts list/get, JSON piping), but the repeatedly instructed 'run in background and poll for completion' is never shown as a concrete executable mechanism (no `&`/`nohup`/poll-loop example).	4 / 5
Workflow Clarity	The 'Investigate an issue' example gives a clear start → follow-up-with-chat-id → list → get sequence and the async guidance is consistent, with no destructive/batch cap applying to this read-only Q&A skill; the only gap is the missing concrete completion/poll checkpoint mechanism.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the single-file body is organized into clear, navigable sections (CLI Commands, Running Olly, Chat Commands, Artifacts, Workflow Examples, Key Principles, Related Skills) with no nested references, though at ~110 lines a couple of sections could optionally be split out.	4 / 5
	Total	16 / 20 Passed

Description

77%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, well-targeted description that clearly signals when to invoke the skill and is anchored to a distinct product (Olly/cx CLI). Its main weakness is that the "what" understates the skill's actual capabilities, listing them only indirectly through trigger phrases rather than as concrete actions.

Suggestions

Open with a crisp capability statement (e.g., 'Analyzes observability data, answers questions about alerts/metrics/logs, and generates charts and reports via the Coralogix Olly agent') before the trigger list, so the 'what' is comprehensive and not just implied by triggers.

Trim a few near-duplicate trigger phrases (e.g., 'chat with AI' / 'send message to AI') to reduce length without losing coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("interact with the Coralogix Observability Agent (Olly) using the cx CLI") and embeds a few implied actions via triggers ("get artifact", "download artifact", "list artifacts", "AI analysis"), but it never states the core capabilities crisply (analyze data, answer questions about alerts/metrics/logs, generate charts) — those live only in the body.	3 / 5
Completeness	Both "what" (interact with Olly via cx CLI) and "when" (explicit, concrete trigger phrases) are present and the "when" is very explicit, but the "what" is thin and omits the concrete actions the skill performs, keeping it just below a 5.	4 / 5
Trigger Term Quality	It packs in a comprehensive, natural set of synonyms and phrases users would actually say ("chat with AI", "ask Olly", "ask the agent", "continue a chat", "follow up on chat", "get/download/list artifacts", "AI analysis", "conversational observability", "natural language query").	5 / 5
Distinctiveness Conflict Risk	The Olly/Coralogix/cx CLI anchoring gives it a clear, distinct niche with minimal conflict risk against the related cx-telemetry-querying and cx-alerts skills, though a few generic phrases ("AI analysis", "natural language query") leave minor overlap risk.	4 / 5
	Total	16 / 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-olly/SKILL.md
Commit: 4aa811a

Reviewed: 2 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.