Allows agents to query and inspect QDash instances and chip metrics via the qdash-client.

Install

mkdir -p .claude/skills/qdash && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17508" && unzip -o skill.zip -d .claude/skills/qdash && rm skill.zip

Installs to .claude/skills/qdash

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Work with a running QDash instance through qdash-client and saved local profiles. Use when an agent needs to inspect chips, metrics, task results, calibration data, provenance, issues, flows, executions, project files, project-scoped QDash API data, or OpenAPI endpoints from QDash using qdash-client, ~/.config/qdash/config.ini, XDG_CONFIG_HOME/qdash/config.ini, QDASH_* environment variables, or a local oqtopus-team/qdash checkout.
434 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Query QDash for chip data and metrics
  • Retrieve task results and calibration data
  • Inspect project files and provenance statistics
  • Access QDash OpenAPI endpoints
  • Use saved local profiles for authentication
  • Summarize returned data from QDash

How it works

This skill uses `qdash-client` to interact with a running QDash instance, retrieving various data types like chips, metrics, and task results. It use saved local profiles for secure access.

Inputs & outputs

You give it
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local chips
You get back
A list of chips from the QDash instance

When to use qdash

  • Inspect chip metrics
  • Query task results
  • Verify calibration data
  • Review project issues

About this skill

QDash

Overview

Use this skill to let an agent query QDash through qdash-client instead of scraping the UI, calling curl directly, or hand-writing auth headers. Prefer saved profiles for credentials and keep tokens, Cloudflare Access secrets, passwords, and raw config contents out of conversation output.

For public/general use, assume qdash-client is the required API transport. Do not install it permanently unless the user asks; prefer ephemeral execution with uv run --with qdash-client.

Quick Start

  1. Locate the profile without printing secrets:
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py config-path
  1. Run a read-only smoke check:
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local chips
  1. Query common API data:
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local default-chip
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local metrics-config
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local chip-metrics --chip-id chip-001
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local chip-qubits --chip-id chip-001 --limit 20
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local task-results --limit 20 --status success
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local task-result --task-id task-001
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local task-knowledge --task-name t1
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local qubit-latest --task t1
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local issues --limit 20
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local flows
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local flow-templates
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local files-tree
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local ai-reviews --limit 20
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local provenance-stats
uv run --with qdash-client python skills/qdash/scripts/qdash_query.py --profile local timeseries --parameter t1 --start-at 2026-06-01T00:00:00Z --end-at 2026-06-08T00:00:00Z

For QDash development, set QDASH_REPO_PATH to a local oqtopus-team/qdash checkout to test unreleased client changes. The helper also probes ~/src/github.com/oqtopus-team/qdash.

If using a local checkout and plain python does not have client dependencies, run the helper through uv:

uv run --with httpx --with pydantic python skills/qdash/scripts/qdash_query.py --profile local chips

Workflow

  1. Use config-path first when the user mentions a local profile. Report only the path, available profile names, and whether the file exists.
  2. Prefer uv run --with qdash-client python skills/qdash/scripts/qdash_query.py ... for supported read-only operations because it handles profile loading, auth headers, project headers, model serialization, and error formatting through the official client.
  3. Use named read-only commands first: chips, default-chip, metrics-config, chip-metrics, chip-qubits, chip-qubit, chip-couplings, chip-coupling, timeseries, task-results, task-result, task-note, task-result-issues, task-knowledge, task-knowledge-markdown, qubit-latest, qubit-history, coupling-latest, coupling-history, projects, project, files-tree, file-content, git-status, issues, issue-knowledge, flows, flow, flow-templates, flow-template, flow-helper-files, flow-helper-file, executions, ai-reviews, ai-review-runs, ai-review-run, and provenance-*.
  4. Use raw-get for read-only endpoints not covered by first-class commands. It still goes through qdash-client; do not use curl as the normal path.
  5. Use a local checkout fallback only for qdash-client development or unreleased API/client changes.
  6. Before creating, updating, deleting, excluding, re-executing, pushing files, pulling files, or triggering flows, state the exact endpoint/action and wait for user confirmation.
  7. Summarize returned data instead of dumping huge JSON. Include counts, IDs, time ranges, and suspicious values that answer the user's question.

API Reference

Read references/qdash.md when you need endpoint groups, local source locations, or examples for extending the helper.

Primary local sources in the QDash checkout:

  • src/qdash/client/README.md
  • docs/user-guide/qdash-client.md
  • docs/oas/openapi.json
  • src/qdash/client/services/client.py

Safety

  • Never print api_token, password, cf_access_client_secret, or full profile contents.
  • Do not reconstruct auth headers in shell or curl unless the user explicitly asks for low-level debugging.
  • Treat /files/git/push, /files/git/pull, /flows/*/execute, re-execute, exclude, admin, auth, and project membership endpoints as write or operationally sensitive.
  • Prefer absolute UTC ISO timestamps with trailing Z for time-series calls.
  • Close QDashClient instances when writing custom snippets.

When not to use it

  • When creating, updating, deleting, or re-executing QDash entities without explicit user confirmation

Limitations

  • Primarily for read-only operations
  • Requires explicit user confirmation for write or operationally sensitive actions
  • Assumes `qdash-client` is the required API transport

How it compares

This skill provides a programmatic and secure way to query QDash data using `qdash-client` and saved profiles, avoiding manual UI scraping or direct `curl` calls with hardcoded credentials.

Compared to similar skills

qdash side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
qdash (this skill)01moReviewIntermediate
model-usage52moReviewBeginner
analytics-tracking76moNo flagsIntermediate
splunk-analysis55moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

model-usage

openclaw

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

548

analytics-tracking

davila7

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.

736

splunk-analysis

incidentfox

Splunk log analysis using SPL (Search Processing Language). Use when investigating issues via Splunk logs, saved searches, or alerts.

536

tracking-crypto-derivatives

jeremylongshore

Track cryptocurrency futures, options, and perpetual swaps with funding rates, open interest, liquidations, and comprehensive derivatives market analysis. Use when monitoring derivatives markets, analyzing funding rates, tracking open interest, finding liquidation levels, or researching options flow. Trigger with phrases like "funding rate", "open interest", "perpetual swap", "futures basis", "liquidation levels", "options flow", "put call ratio", "derivatives analysis", or "BTC perps".

437

weights-and-biases

davila7

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

325

perf-analyzer

ComposioHQ

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

324

Search skills

Search the agent skills registry