New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Query Finelog

by marin-community in marin-community/marin

Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Query Finelog

skills CLI
$ npx skills add marin-community/marin --skill query-finelog -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install marin-community/marin query-finelog --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/query-finelog .claude/skills/query-finelog && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
query-finelog
GitHub stars
3.9k
Token cost
~1.1k tokens
SKILL.md length
279 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

  • Schema discovery
  • Calls uv
  • Hub-versus-regional comparisons
  • Counter semantics

What it does

Query Finelog is an agent skill from marin-community/marin. Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding. Use for schema discovery, SQL, memory or CPU summaries, hub-versus-regional comparisons, counter semantics, and query-performance diagnosis.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM inference and serving, Query optimization and SQL. It works with SQL and vLLM. The repository describes itself as: Open-source framework for the research and development of foundation models. The licence is Apache-2.0.

When your agent uses it

  • Schema discovery
  • Hub-versus-regional comparisons
  • Counter semantics
  • Query-performance diagnosis

Example prompts

  • “/query-finelog”

What it can do on your machine

Read from SKILL.md and the folder at commit 2ea1c1d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    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):

    • echo.oa.dev

    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

Query Finelog loads about 1.1k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 279 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 marin-community/marin at commit 2ea1c1d, republished under its Apache-2.0 licence (© marin-community). 279 words, ~1,147 tokens.

Download SKILL.mdSave it as .claude/skills/query-finelog/SKILL.md (or your agent's skills folder).
name
query-finelog
description
Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding. Use for schema discovery, SQL, memory or CPU summaries, hub-versus-regional comparisons, counter semantics, and query-performance diagnosis.

Query Finelog

Read lib/finelog/OPS.md for access and query behavior. Read lib/iris/OPS.md under Stats Namespaces for Iris namespace meanings.

Discover before querying; do not assert remembered columns:

bash
uv run finelog namespaces <deployment>
uv run finelog schema <deployment> <namespace>
uv run finelog query <deployment> --format table <<'SQL'
<bounded SQL using schema-confirmed columns>
SQL

finelog query reads SQL from stdin when the positional SQL argument is omitted.

Use marin for the federated view and a regional deployment for peer-local truth or recent rows that may not have forwarded. Preserve cluster and full process/label identity until after per-series delta calculations.

Bound the native time key. Keep telemetry_v1.timestamp_ms predicates numeric. Treat current snapshots as values, imported Prometheus counters as cumulative snapshots with LAG and reset handling, and native Rigging counters as deltas to SUM directly.

Never reset or change a shared namespace during diagnosis. Return the deployment, namespace, time window, query, series semantics, and any forwarding or retention caveat.

Examples

Confirm every schema before adapting an example. Angle-bracket values are placeholders.

Iris task memory by half-hour

Adapted from Echo wiki 230. The dashboard task ID includes the final task index. Select or group by attempt_id after retries.

sql
SELECT date_bin(INTERVAL '30 minutes', ts,
                TIMESTAMP '1970-01-01 00:00:00') AS bucket_start_utc,
       count(*) AS samples,
       round(min(memory_mb) / 1024.0, 1) AS min_gib,
       round(median(memory_mb) / 1024.0, 1) AS median_gib,
       round(max(memory_mb) / 1024.0, 1) AS max_gib,
       round(max(memory_peak_mb) / 1024.0, 1) AS attempt_peak_gib
FROM "iris.task"
WHERE task_id = '/user/job/task'
  AND attempt_id = 0
GROUP BY bucket_start_utc
ORDER BY bucket_start_utc

memory_mb is sampled current memory; memory_peak_mb is the attempt's cumulative peak. Values are MiB despite the names. count(*) exposes partial buckets and gaps. Query the regional deployment if recent hub rows appear incomplete.

Missing federated logs

Use the exact attempt-suffixed log key on both stores:

sql
-- marin hub
SELECT seq, epoch_ms, source, data, cluster
FROM "log"
WHERE key = '/user/job/task:0' AND cluster = 'cw-us-east-08a'
ORDER BY seq;

-- cw-us-east-08a regional deployment
SELECT seq, epoch_ms, source, data
FROM "log"
WHERE key = '/user/job/task:0'
ORDER BY seq;

Regional rows with a missing or shorter hub result mean forwarding delay. Runtime task logs with no regional rows point to shipper or regional ingest. Iris job describe remains the liveness source.

Native delta counter

Native rigging.telemetry.counter(...).add(...) rows are already increments:

sql
SELECT sum(value)
FROM "telemetry_v1.<semantic_scope>"
WHERE name = 'requests_completed'
  AND timestamp_ms >= <start_ms>
  AND timestamp_ms < <end_ms>
Imported cumulative counter

Imported vLLM counters carry source_temporality = 'cumulative_snapshot'. Scan one 60-second scrape before the visible window, preserve the complete series identity, and discard reset intervals.

sql
WITH base AS (
  SELECT COALESCE(NULLIF(cluster, ''), 'local') AS origin_cluster,
         service, name, resource_attributes_json, attributes_json,
         timestamp_ms, seq, value
  FROM "telemetry_v1.vllm"
  WHERE service = 'vllm'
    AND name = 'generation_tokens_total'
    AND json_get(attributes_json, 'source_temporality') = 'cumulative_snapshot'
    AND timestamp_ms >= <start_ms - 60000>
    AND timestamp_ms < <end_ms>
), samples AS (
  SELECT *, lag(value) OVER (
    PARTITION BY origin_cluster, service, name,
                 resource_attributes_json, attributes_json
    ORDER BY timestamp_ms, seq) AS previous_value
  FROM base
), deltas AS (
  SELECT *, CASE WHEN previous_value IS NULL OR value < previous_value
                 THEN NULL ELSE value - previous_value END AS delta
  FROM samples
)
SELECT date_bin(INTERVAL '5 minutes', to_timestamp_millis(timestamp_ms)) AS bucket,
       sum(delta) AS generated_tokens
FROM deltas
WHERE timestamp_ms >= <start_ms>
GROUP BY bucket
ORDER BY bucket

© marin-community, 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 .agents/skills/query-finelog of marin-community/marin.

Open the folder on GitHubat commit 2ea1c1d

Compare with similar skills

Query Finelog next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Query Finelog compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Query Finelog this skillmarin-community/marin3.9k—~1.1kAutomated safety check: PassApache-2.0
Pytorch Clickhousepytorch/test-infra113—~2.8kAutomated safety check: PassCustom licence
SQL Optimization Patternsynulihao/AgentSkillOS61811 repos~3.3kAutomated safety check: PassNone
Query Engine Designrevfactory/claude-code-harness120—~474Automated safety check: PassNone
Tinybird Datafile RulesTryGhost/Ghost56k—~417Automated safety check: PassMIT
SQL Optimization Patternssickn33/agentic-awesome-skills47k1 repos~566Automated safety check: PassMIT

Similar skills

  • Pytorch Clickhouse

    pytorch/test-infra

    Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.

    113 GitHub stars~2.8k tokensUpdated today
    DatabasesAuto-check passed

  • SQL Optimization Patterns

    ynulihao/AgentSkillOS

    Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.

    618 GitHub starsUsed in 11 repos~3.3k tokens
    DatabasesAuto-check passed

  • Query Engine Design

    revfactory/claude-code-harness

    SQL query engine design and implementation guide. An agent skill from revfactory/claude-code-harness.

    120 GitHub stars~474 tokensUpdated 7 mo ago
    DatabasesAuto-check passed

  • Tinybird Datafile Rules

    TryGhost/Ghost

    Rules for writing Tinybird datasources, pipes, endpoints and materialized views, with SQL constraints, optimization habits and deduplication patterns.

    56k GitHub stars~417 tokensUpdated today
    DatabasesAuto-check passed

  • SQL Optimization Patterns

    sickn33/agentic-awesome-skills

    Diagnose slow SQL with query plans, preserve query results, and verify indexing or query changes against representative data.

    47k GitHub starsUsed in 1 repo~566 tokens
    DatabasesAuto-check passed

  • Gke Inference

    google/skills

    Official

    Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers.

    21k GitHub stars~2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from marin-community/marin

All 41 skills in this repo

  • Noslop

    marin-community/marin

    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Use Iris

    marin-community/marin

    Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs.

    3.9k GitHub stars~745 tokensUpdated today
    Auto-check passed

  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Auto-check passed

  • Marina Applet

    marin-community/marin

    Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet.

    3.9k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Trace Pulumi Diff

    marin-community/marin

    Run a read-only preview for a specified Marin infra/pulumi stack and trace each pending resource change to merged pull requests since its latest successful update when that update records a clean…

    3.9k GitHub stars~663 tokensUpdated today
    Auto-check passed

  • Deploy Hero Change

    marin-community/marin

    Deploy a significant code change (backend, kernel, optimizer, data path) to the live hero run: relaunch it under a new run id from a permanent checkpoint, compare against the old run over a trial…

    3.9k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Query Finelog

What does Query Finelog do?

Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding. Query Finelog is an agent skill from marin-community/marin. Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

When should I use Query Finelog?

Query Finelog fits situations like: schema discovery; hub-versus-regional comparisons; counter semantics; query-performance diagnosis.

How do I install Query Finelog in Claude Code?

Run `npx skills add marin-community/marin --skill query-finelog -a claude-code`. Or copy the skill folder (.agents/skills/query-finelog in marin-community/marin) into .claude/skills/query-finelog in your project. Claude Code loads it when a task matches its description.

How do I install Query Finelog in Codex?

Run `npx skills add marin-community/marin --skill query-finelog -a codex`. Or copy the skill folder (.agents/skills/query-finelog in marin-community/marin) into .agents/skills/query-finelog in your project. Codex loads it when a task matches its description.

Can I use Query Finelog in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add marin-community/marin --skill query-finelog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/query-finelog, .gemini/skills/query-finelog, .github/skills/query-finelog and .opencode/skills/query-finelog in your project.

What does Query Finelog need to run?

Going by SKILL.md and its folder, Query Finelog needs the command-line tools its instructions call (uv).

Does Query Finelog access the network?

SKILL.md names 1 domain. As links in the text: echo.oa.dev. This is read from the text; nothing was executed.

Is Query Finelog safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Query Finelog use?

Query Finelog is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Query Finelog use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Query Finelog?

Skills that share tags, products or a category with Query Finelog: Pytorch Clickhouse (pytorch/test-infra, 113 stars), SQL Optimization Patterns (ynulihao/AgentSkillOS, 618 stars), Query Engine Design (revfactory/claude-code-harness, 120 stars) and Tinybird Datafile Rules (TryGhost/Ghost, 56k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Query Finelog?

marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,925 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 11, 2026.

Source: marin-community/marin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.