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.

75

Quality

92%

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

100%

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

The content is an exemplary debugging skill: concise yet complete, fully actionable with copy-paste commands, a clearly sequenced workflow with recovery guidance, and well-organized despite (appropriately) having no external bundle files.

DimensionReasoningScore

Conciseness

Dense, high-signal debugging instructions with no padding explaining Docker/Temporal/object-storage basics; every section (env table, three steps, failure signatures) earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands — 'docker ps --format ... | grep task-sandbox', 'docker exec posthog-temporal-admin-tools-1 temporal workflow list ...', 'docker exec "$CID" tail -f /tmp/posthog-wizard.log', and a complete manage.py shell heredoc to read the durable log — matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

Clear three-step sequence (find UUID -> tail live logs while running -> read durable log after teardown) with explicit 'when to use which' checkpoints ('Mid-run, use Step 2'), teardown warnings, and a failure-signatures recovery section serving as feedback loops, matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.

3 / 3

Progressive Disclosure

No bundle files exist; the self-contained SKILL.md is well-organized into Prerequisites, three numbered steps, and Common failure signatures with clear section signaling, which per the simple-skills scoring note earns a 3 without external references.

3 / 3

Total

12

/

12

Passed

Description

85%

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

The description is highly specific, complete (explicit what + when), and occupies a clear niche unlikely to conflict with other skills. Its main weakness is trigger-term quality: the listed triggers lean toward internal identifiers rather than natural phrases a user would say.

Suggestions

Add natural-language trigger phrases alongside the technical identifiers (e.g. 'local task run is stuck', 'wizard cloud run failed', 'agent PR didn't open') so non-expert users can also surface the skill.

Consider trimming or grouping the long list of env keys and log paths in the description — these detail the 'how' and may dilute the 'what/when' clarity that the description is meant to convey.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'finding the task UUID (docker ps, temporal CLI, Temporal UI at localhost:8081)', 'tailing live logs inside the sandbox container', and 'reading the durable per-run console log from object storage after the sandbox is torn down' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Debug the output of local PostHog task runs') and when ('Use when a local run looks stuck, failed, or silent, or when you need to read the wizard or agent logs'), matching the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Trigger terms ('task-sandbox, run_wizard, agent-server, process-task, SANDBOX_PROVIDER, LLM_GATEWAY, cloud_run, posthog-wizard.log') are internal identifiers rather than natural user vocabulary, fitting the 'some relevant keywords but missing common variations' anchor rather than natural-language terms.

2 / 3

Distinctiveness Conflict Risk

Highly specific niche (local PostHog task/agent Docker sandbox runs under the Temporal process-task workflow) with distinct, unlikely-to-conflict triggers, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.

3 / 3

Total

11

/

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.