CtrlK
BlogDocsLog inGet started
Tessl Logo

setting-up-devbox

Guide a PostHog engineer through spinning up, connecting to, running commands on, and mirroring local code to a remote devbox (a Coder workspace running the full PostHog stack). Use when asked to set up a devbox, start or connect to a devbox, configure remote dev, get gh CLI / Claude Code authed on a devbox, run a command on a devbox, sync a local checkout so you can edit locally while the stack runs remotely (devbox:sync), or diagnose why a devbox command fails. Covers the tailnet prerequisite, hogli devbox commands, Coder user secrets for auth, one-way local->remote sync via mutagen, and verifying with devbox:exec. How each dev personalizes their box is left to them.

74

Quality

91%

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 tight, command-dense skill body: it leads with executable hogli commands, sequences the workflow with a doctor-first validation checkpoint, and keeps token use lean. Minor conciseness trims and moving some edge-case troubleshooting into a reference file would lift the borderline dimensions.

Suggestions

Trim the explanatory rationale in section 6 (login-shell PATH) and the mutagen mechanics to the essential rule, keeping the concrete command.

Make the devbox:sync conflict-resolution path an explicit validate-fix-retry loop rather than descriptive prose.

Consider extracting the DNS/exit-node troubleshooting subsection into a references/ file and linking to it from the prerequisite section to deepen progressive disclosure.

DimensionReasoningScore

Conciseness

It is efficient and assumes competence — no boilerplate about what Tailscale/mutagen are — but a few explanatory passages (e.g. the login-shell PATH rationale in section 6, the mutagen one-way-safe mechanics) could be trimmed slightly.

4 / 5

Actionability

Every workflow step is backed by concrete, copy-paste-ready commands (`hogli devbox:doctor`, `devbox:exec -- bash -lc '...'`, `tailscale set --exit-node=<name>`), with flags and exit-code behavior spelled out.

5 / 5

Workflow Clarity

A clear numbered sequence runs from doctor → setup → start → auth → personalize → exec → sync, with `devbox:doctor` as an explicit validation checkpoint and diagnosis-first guidance for reachability failures; the sync section's conflict-resolution feedback loop is somewhat implicit rather than a clean validate-retry cycle.

4 / 5

Progressive Disclosure

Well-organized sections with a focused overview and clear navigation; no bundle files are present so there is no deeper reference structure to score, but the body is appropriately sectioned and could push some edge-case detail (e.g. the exit-node/DNS subsection) into a reference.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exceptionally specific, well-triggered, and distinctive description: it states concrete capabilities, provides explicit 'Use when...' triggers, and is tightly scoped to the PostHog devbox domain. All four dimensions land at the top anchor.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'spinning up, connecting to, running commands on, and mirroring local code to a remote devbox' — plus detailed trigger actions like 'configure remote dev, get gh CLI / Claude Code authed, sync a local checkout, diagnose why a devbox command fails'.

5 / 5

Completeness

It answers 'what' ('Guide a PostHog engineer through spinning up... devbox...') and 'when' with an explicit 'Use when...' clause enumerating concrete trigger phrases, satisfying both halves clearly.

5 / 5

Trigger Term Quality

It includes natural trigger phrasings a user would say ('set up a devbox', 'start or connect to a devbox', 'sync a local checkout', 'diagnose why a devbox command fails') along with concrete command/feature names like 'devbox:sync' and 'devbox:exec'.

5 / 5

Distinctiveness Conflict Risk

The PostHog/Coder/hogli devbox niche is sharply scoped with proprietary trigger terms ('hogli devbox:*', 'devbox:sync', 'devbox:exec'), making conflict with other skills minimal.

5 / 5

Total

20

/

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.