CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging-local-task-agent-runs

Debug the output of local PostHog task runs — the wizard cloud-run path that executes inside a Docker sandbox under the local Temporal `process-task` workflow (the wizard that integrates PostHog, then the coding agent that commits and opens the PR). Use when a local run looks stuck, failed, or silent, or when you need to read the wizard or agent logs. Covers the `.env.local` keys + `ai_features` intent required for cloud runs locally, finding the task UUID (docker ps, temporal CLI, Temporal UI at localhost:8081), tailing live logs inside the sandbox container (`/tmp/posthog-wizard.log`, `/tmp/agent-server.log`), and reading the durable per-run console log from object storage after the sandbox is torn down. Trigger terms: task-sandbox, run_wizard, agent-server, process-task, SANDBOX_PROVIDER, LLM_GATEWAY, cloud_run, posthog-wizard.log.

72

Quality

87%

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

82%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.

A dense, highly actionable debugging runbook with executable commands at every step and clear state-aware sequencing. It is concise for its complexity and well-structured as a single file, with only minor room to tighten prose and make validation checkpoints more explicit.

DimensionReasoningScore

Conciseness

Efficient and assumes Claude's competence (no padding of what Docker/Temporal/PostHog are); every line delivers non-obvious system behavior. A few narrative intro sentences and parenthetical asides are slightly more than minimal, keeping it just below the 5 anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (docker ps grep, temporal workflow list, docker exec tail -f) plus a complete Python manage.py shell script for the durable log, covering the common debug cases — matches the 5 anchor.

5 / 5

Workflow Clarity

Clear sequenced Prerequisites then Steps 1–3 keyed to run state (live vs after teardown) plus an error-recovery failure-signatures section. It is a read-only debug skill so the destructive/batch validation cap does not apply, but checkpoints are implicit state-checks rather than explicit validate-then-proceed gates, so it sits below 5.

4 / 5

Progressive Disclosure

Well-organized into clean, self-contained sections with no nested references and nothing buried. No external files are genuinely needed for this focused runbook, but the 5 anchor specifically rewards one-level-deep file references/splitting, which is not exercised here.

4 / 5

Total

17

/

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 highly specific, well-triggered description that clearly states both capability and use conditions for a narrow debugging niche. The only soft spot is trigger-term phrasing being more technical-identifier-heavy than natural-synonym-rich.

DimensionReasoningScore

Specificity

Lists multiple concrete debug actions (find task UUID via docker ps/temporal CLI/UI, tail live logs, read the durable object-storage log) with comprehensive coverage of the run lifecycle, matching the 5 anchor; no meaningful coverage gaps to drop it to 4.

5 / 5

Completeness

Explicitly answers both 'what' (debug wizard/agent task-run output through the Docker sandbox/Temporal path) and 'when' (stuck, failed, silent runs, or needing wizard/agent logs) with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Comprehensive domain-appropriate triggers including file extensions (posthog-wizard.log) and a natural 'Use when a local run looks stuck, failed, or silent' clause, but the set leans on technical identifiers over broadly natural synonyms, so it sits below the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

A hyper-specific niche (PostHog process-task, task-sandbox, posthog-wizard.log) with distinct triggers that would not fire for any other skill, matching the 5 anchor for minimal conflict risk.

5 / 5

Total

19

/

20

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.