SKILLEMALL.ai
GitHub ↗ RU Sign in

DC clickhouse-managed-postgres-rca

MUST USE when investigating performance issues on a ClickHouse-managed Postgres instance. Provides an evidence-based RCA workflow that scrapes the Prometheus endpoint for system signal, pulls per-digest evidence from the Slow Query Patterns API, and recommends (does not apply) a fix.

ClickHouse/agent-skills Agent Skills author: ClickHouse 13 files body ≈ 1 119 tokens Open the sourcegithub.com↗ analyzed 5 d ago

MUST USE when investigating performance issues on a ClickHouse-managed Postgres instance.

As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedurePostgreSQLData and analyticsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
70/100
safety, quality, tests
Safety 60%
60
Quality 40%
85
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • 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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • medium Exfiltration net-credential-use AGENTS.md:264
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use AGENTS.md:323
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use AGENTS.md:326
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use AGENTS.md:405
      Credential used in a network call (verify the destination is the intended service)
      curl -s -G -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use rules/prometheus-scrape.md:21
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use rules/prometheus-scrape.md:80
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use rules/prometheus-scrape.md:83
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \
    • medium Exfiltration net-credential-use rules/slow-query-patterns-fields.md:70
      Credential used in a network call (verify the destination is the intended service)
      curl -s -G -u "$CH_CLOUD_KEY:$CH_CLOUD_SECRET" \

    Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 64/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 14 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1119 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress

    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
    • +4No input/output examples
    • +2Single-language instructions
    • +3Description length 284: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 14 items
    • +4Reference files are cited in the instructions (9 of 9)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.