Cpu Profile

What it does

When your agent uses it

• The user wants to find CPU hotspots
• Analyze where time is spent in a query
• Investigate performance bottlenecks

Example prompts

• “/cpu-profile”

Requirements

• Pre-approved tools (allowed-tools): Task, Bash, Read, Grep, Glob, AskUserQuestion

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Determine what to profile
2. 2Execute query with profiling
3. 3Collect and analyze trace data
4. 4Synthesize results
5. 5Offer drill-down options

What it can do on your machine

Read from SKILL.md and the folder at commit cd023af. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Task
  • Bash
  • Read
  • Grep
  • Glob
  • AskUserQuestion

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are sql and bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • speedscope.app

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cpu Profile loads about 1.9k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 557 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~55

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Task, Bash, Read, Grep, Glob, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ClickHouse/ClickHouse at commit cd023af, republished under its Apache-2.0 licence (© ClickHouse). 557 words, ~1,873 tokens.

name

cpu-profile

description

Profile a ClickHouse query using the sampling query profiler and system.trace_log. Use when the user wants to find CPU hotspots, analyze where time is spent in a query, or investigate performance bottlenecks.

allowed-tools

Task, Bash, Read, Grep, Glob, AskUserQuestion

argument-hint

query_id or query text

disable-model-invocation

false

SELECT
    query_id,
    query_duration_ms,
    formatReadableSize(memory_usage) AS peak_memory,
    left(query, 120) AS query_preview
FROM system.query_log
WHERE type = 'QueryFinish'
  AND event_date >= today() - 1
  AND query_duration_ms > 1000
  AND query NOT LIKE '%system.%'
ORDER BY query_duration_ms DESC
LIMIT 20
SETTINGS allow_introspection_functions = 1

PROFILE_QID="cpu-profile-$(uuidgen)"
clickhouse-client --query_id "$PROFILE_QID" -q "
    SELECT ...
    SETTINGS query_profiler_cpu_time_period_ns = 100000,
             query_profiler_real_time_period_ns = 100000
"

SELECT query_id, query_duration_ms, formatReadableSize(memory_usage) AS peak_memory
FROM system.query_log
WHERE type = 'QueryFinish' AND query_id = '{query_id}'
SETTINGS allow_introspection_functions = 1

SELECT
    count() AS samples,
    round(100.0 * count() / (SELECT count() FROM system.trace_log WHERE query_id = '{query_id}' AND trace_type = 'CPU'), 2) AS pct,
    demangle(addressToSymbol(trace[1])) AS function
FROM system.trace_log
WHERE query_id = '{query_id}'
  AND trace_type = 'CPU'
GROUP BY function
ORDER BY samples DESC
LIMIT 30
SETTINGS allow_introspection_functions = 1

SELECT
    count() AS samples,
    arrayStringConcat(
        arrayMap(x -> demangle(addressToSymbol(x)), trace),
        '\n    '
    ) AS stack
FROM system.trace_log
WHERE query_id = '{query_id}'
  AND trace_type = 'CPU'
GROUP BY trace
ORDER BY samples DESC
LIMIT 15
SETTINGS allow_introspection_functions = 1

SELECT
    concat(
        arrayStringConcat(
            arrayReverse(arrayMap(x -> demangle(addressToSymbol(x)), trace)),
            ';'
        ),
        ' ',
        toString(count())
    )
FROM system.trace_log
WHERE query_id = '{query_id}'
  AND trace_type = 'CPU'
GROUP BY trace
ORDER BY count() DESC
SETTINGS allow_introspection_functions = 1
FORMAT TSVRaw

SELECT
    count() AS total_samples,
    min(event_time_microseconds) AS first_sample,
    max(event_time_microseconds) AS last_sample,
    dateDiff('millisecond', min(event_time_microseconds), max(event_time_microseconds)) AS profile_duration_ms
FROM system.trace_log
WHERE query_id = '{query_id}' AND trace_type = 'CPU'
SETTINGS allow_introspection_functions = 1

© ClickHouse, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/cpu-profile of ClickHouse/ClickHouse.

Open the folder on GitHubat commit cd023af