CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging-signals-pipeline

Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox agent logs from object storage, inspecting Docker sandbox containers, and diagnosing common failures (stale ClickHouse embeddings, agentsh network denials, inactivity timeouts). Use when a signal isn't reaching the inbox, a signal-report-summary workflow fails, or a sandbox task run times out.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and concise operational content with clear sequenced workflows and validation for destructive operations. The main gap is progressive disclosure: everything lives in one long file with no reference split for the detailed failure playbooks.

Suggestions

Move the per-failure playbooks (the 'Common failures' section with ClickHouse SQL, inactivity diagnostics, etc.) into a references/ file such as COMMON_FAILURES.md, keeping SKILL.md as an overview that links to it one level deep.

Extract the long Temporal REST inspection curl/Python snippets into a references/ script (e.g. scripts/inspect_workflow.py) and reference it from the monitoring section to reduce inline bulk.

Add a short 'Quick start' or triage section at the top that maps each symptom to the relevant section, so the overview routes the reader before they hit the detailed inline procedures.

DimensionReasoningScore

Conciseness

The body is dense with executable commands and pipeline-specific operational detail Claude would not already know, with no padding explaining general concepts. Not a 2 because there is little to no unnecessary explanation that could be trimmed without losing information.

3 / 3

Actionability

Provides copy-paste-ready bash, python, curl, and SQL with real flags, URLs, and table names (e.g. the emit_signals_from_fixture command, the Temporal history curl, the ClickHouse DELETE/SELECT). Not a 2 because the examples are complete and executable rather than pseudocode or missing key details.

3 / 3

Workflow Clarity

The pipeline-flow diagram gives an explicit sequence, and the emit workflow has validation checkpoints (cleanup before re-emit, 'Verify embeddings are clean', signal_pipeline_status --wait) with feedback loops for the destructive cleanup operation. Not a 2 because validation steps are explicit for the batch/destructive operations rather than missing or implicit.

3 / 3

Progressive Disclosure

A single ~220-line file with clear section headers and easy navigation, but monolithic: detailed failure playbooks and the long Temporal/curl inspection scripts are inline with no split into reference files. Not a 3 because no bundle references are used to move detail one level deep, and the under-50-line simple-skill exemption does not apply; not a 1 because organization is clean with no nested references.

2 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both the capability surface and concrete trigger conditions in third person. It avoids fluff and uses natural failure phrases a user would say. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox agent logs from object storage, inspecting Docker sandbox containers, and diagnosing common failures'), matching the anchor for several specific concrete actions. Not a 2 because the action list is comprehensive rather than naming only a domain and a few actions.

3 / 3

Completeness

Explicitly answers both what (debug the signals pipeline, with a listed action surface) and when (an explicit 'Use when...' trigger clause). Not a 2 because the 'when' is stated explicitly rather than only implied.

3 / 3

Trigger Term Quality

The 'Use when a signal isn't reaching the inbox, a signal-report-summary workflow fails, or a sandbox task run times out' clause uses natural problem phrasing a user would actually say. Not a 2 because it covers multiple common variations of the failure rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

A narrow, domain-specific niche (signals pipeline debugging) with distinct, unlikely-to-overlap triggers. Not a 2 because the triggers are specific enough that this would not fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.