AC clickhouse
Comprehensive ClickHouse skill covering everything you need to work with a ClickHouse analytics database: schema design, query optimization, insert strategies, CLI usage, table creation and migrations, backend integration (Node.js, Python, Go), Redis caching strategy, cluster vs single-node differences, and how to test/debug data in the database. MUST USE whenever the user mentions ClickHouse, asks about analytics tables, high-volume insert pipelines, MergeTree schemas, ORDER BY / PRIMARY KEY design, materialized views, ClickHouse query performance, connecting to ClickHouse from code, or running ClickHouse CLI commands to inspect data.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8840 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 40Consistency. Frontmatter name (clickhouse) differs from the folder (clickhouse-developer)
- 40Execution cost. Instruction body is 8840 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
- 85Steps. 33 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 643: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (51 code blocks)
- +4Reference files are cited in the instructions (6 of 28)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.