CtrlK
BlogDocsLog inGet started
Tessl Logo

adding-inbox-sources

Add a new warehouse-backed source to the PostHog Desktop Self-driving Inbox (the feature that ships GitHub, Linear, Zendesk, pganalyze, Jira). A source syncs one warehouse table (issues/tickets/conversations) and a cloud "signals scout" watches it and emits findings. Use when asked to "add a new inbox/self-driving source", "wire up <Jira/GitLab/Sentry/Intercom/Freshdesk/Front/Gorgias/etc> as a signal source", or to extend the source-toggle grid. Covers all three surfaces (posthog/posthog scout emitter + posthog/code UI wiring + the context-mill self-driving wizard skill that offers the source in `npx @posthog/wizard self-driving`), the deploy ordering between them, and created_via attribution.

72

Quality

88%

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

77%

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

The body is highly actionable and well-sequenced with strong validation checkpoints across three repos, but it is long and repeats the OAuth/DynamicSourceSetup guidance several times. Splitting the context-mill and created_via sections into reference files would reduce token cost and improve organization.

Suggestions

De-duplicate the DynamicSourceSetup / OAuth guidance: state the 'route the switch case to DynamicSourceSetup, no bespoke form' rule once and remove the restatements in the 'OAuth plumbing' and 'Setup-form specifics' sections.

Move the context-mill wizard surface and the created_via attribution table into one-level-deep reference files (e.g. references/wizard-surface.md and references/created-via.md) to shrink the main SKILL.md overview.

The posthog/code and posthog/posthog per-source checklists are the core reusable material — consider extracting them to reference files that the overview points to, keeping SKILL.md as a concise routing + deploy-ordering guide.

DimensionReasoningScore

Conciseness

The ~250-line body is mostly efficient and assumes Claude's competence (no 'what is a warehouse' preamble), but repeats the 'route to DynamicSourceSetup / no bespoke OAuth form' guidance across the setup-form, OAuth-plumbing, and Setup-form-specifics sections, which could be tightened; matching the score-2 anchor of mostly efficient but with some unnecessary restatement.

2 / 3

Actionability

Provides copy-paste-ready, executable guidance — exact paths and symbols ('packages/shared/src/inbox-types.ts — add "jira" to the SourceProduct union'), commands ('git worktree add ...', 'python manage.py makemigrations signals', 'pnpm typecheck', 'biome lint packages/core packages/ui', 'node scripts/build.js') — matching the score-3 anchor for fully executable, specific examples.

3 / 3

Workflow Clarity

The multi-repo process is clearly sequenced with explicit deploy ordering ('land the posthog/posthog PR(s) first ... then the posthog/code PR'), per-surface numbered checklists, and Verify checkpoints after each phase (makemigrations --check clean, pnpm typecheck, biome lint zero violations, build validates structure), matching the score-3 anchor for clear sequence with explicit validation steps and checklists.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is monolithic at ~250 lines; the context-mill wizard surface and the created_via attribution table are inline content that would be better split into one-level-deep reference files, matching the score-2 anchor of 'content that should be separate is inline' despite otherwise clear headers and tables.

2 / 3

Total

10

/

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.

The description is strong: third-person voice, concrete capabilities, natural trigger phrasing with named products, and an explicit Use-when clause. It cleanly answers both what the skill does and when to invoke it, with low conflict risk.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'syncs one warehouse table (issues/tickets/conversations)', 'a cloud signals scout watches it and emits findings', and 'Covers all three surfaces ... deploy ordering ... created_via attribution' — matching the score-3 anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers both what (the surfaces, syncing, emission, attribution) and when (an explicit 'Use when...' clause), matching the score-3 anchor; it is not score 2 because the 'when' is explicit rather than implied.

3 / 3

Trigger Term Quality

Provides natural trigger phrasing users would say — "Use when asked to 'add a new inbox/self-driving source', 'wire up <Jira/GitLab/Sentry/Intercom/Freshdesk/Front/Gorgias/etc> as a signal source'" — with multiple concrete product names, matching the score-3 anchor for good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche ('Self-driving Inbox', 'warehouse-backed source', 'signals scout', 'source-toggle grid') with distinct triggers and named products, making it unlikely to fire for the wrong skill, matching the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

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.