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.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%Weight 40%Scale 1-5

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

An excellent debugging skill: lean, fully actionable, with clear sequencing and validation checkpoints for its destructive batch operations. The only weakness is that all troubleshooting detail lives inline in one file rather than being split into reference files.

Suggestions

Move the per-failure troubleshooting recipes (e.g. the ClickHouse embedding cleanup and inactivity-timeout sections) into a references/FAILURE-MODES.md file, keeping SKILL.md as an overview that links one level deep.

Add a short 'Prerequisites' note (running Temporal UI at :8081, local MinIO, .env keys) so a reader can confirm the environment before running the first command.

Note the ephemeral-nature caveat for sandbox containers earlier in the inspecting-containers section rather than only at the end, so readers check them before they disappear.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout: it assumes Claude already knows what Temporal, ClickHouse, Docker, and MinIO are, and every code block earns its place with inline comments only where genuinely helpful. No padding or over-explanation of basic concepts.	5 / 5
Actionability	Fully copy-paste-ready bash, python, and curl commands with concrete values (fixture offset 26, team-id 1, specific ClickHouse table names, env var settings); examples cover the common debugging cases end to end.	5 / 5
Workflow Clarity	A clear pipeline-flow diagram sequences the stages, each stage has its own section, and destructive/batch operations carry validation checkpoints (the 'Always clean up before re-emitting' warning, verify-embeddings-clean SELECT after the DELETE mutation, and signal_pipeline_status --wait).	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a 'Key file locations' index, but the skill is a single ~230-line monolith with no bundle reference files to offload the detailed troubleshooting recipes, so it is not a clean overview pointing one level deep to separate references.	4 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 what the skill does and when to use it, with concrete capability enumeration and natural trigger phrases. The only minor gap is trigger-term synonym breadth.

Dimension	Reasoning	Score
Specificity	Enumerates 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') plus specific failure modes (stale ClickHouse embeddings, agentsh network denials, inactivity timeouts), giving comprehensive coverage of the pipeline-debugging domain.	5 / 5
Completeness	Explicitly answers both 'what' (debug the signals pipeline end-to-end with enumerated capabilities) and 'when' (a concrete 'Use when...' clause with three specific triggering scenarios).	5 / 5
Trigger Term Quality	Provides natural trigger phrases users would say ('a signal isn't reaching the inbox', 'a signal-report-summary workflow fails', 'a sandbox task run times out'), but the set is somewhat narrow and lacks common synonyms or phrasings a user might use instead.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear narrow niche (signals-pipeline debugging) with highly specific triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PostHog/posthog
Path: products/signals/skills/debugging-signals-pipeline/SKILL.md
Commit: d293866

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.