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.

74

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

85%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 highly actionable, well-sequenced skill body with strong validation checkpoints, held back only by repeated DynamicSourceSetup guidance and a lack of progressive disclosure — everything is inlined in one large file with no reference bundle.

Suggestions

Split the source catalog table and the per-repo checklists (posthog/code items 1-9, posthog/posthog items 1-7) into separate reference files under references/ and link to them from SKILL.md to enable progressive disclosure.

Consolidate the 'route the DataSourceSetup case to DynamicSourceSetup, no bespoke form' guidance, which is currently repeated in 'The setup form', 'posthog/code checklist > Setup-form specifics', and 'OAuth plumbing' sections, into a single authoritative statement.

Move the created_via attribution table into its own reference file, since it is reference material rather than steps the agent performs.

DimensionReasoningScore

Conciseness

The body is dense with high-signal specifics (paths, enums, commands) and assumes Claude's competence without explaining basic concepts, but the 'route to DynamicSourceSetup, no bespoke form' guidance is restated across ~4 sections and could be trimmed. Not a 5 due to that repetition; not a 3 because almost every token is actionable rather than padded.

4 / 5

Actionability

Provides copy-paste-ready commands ('python manage.py makemigrations signals', the worktree block), exact file paths, enum/symbol names, a worked payload-key catalog, and concrete 'copy github_issues.py and adapt' guidance covering common cases.

5 / 5

Workflow Clarity

Clear sequencing with explicit deploy ordering ('do not skip'), numbered per-repo checklists, dedicated 'Verify' sections with validation commands, and feedback loops (migration-collision batching, 'can only be confirmed by running a sync') for risky batch/migration operations.

5 / 5

Progressive Disclosure

Section headers and tables give good structure, but the ~250-line body is monolithic with no bundle/reference files at all, despite clearly separable chunks (source catalog, per-repo checklists, created_via attribution) that belong in one-level-deep references. Not a 4 because no references exist; not a 2 because the in-file organization is solid.

3 / 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.

The description is exemplary: it states concrete capabilities, gives multiple natural trigger phrases, covers what and when explicitly, and occupies a clear distinct niche. No weaknesses to address.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Add a new warehouse-backed source', 'syncs one warehouse table (issues/tickets/conversations)', 'a cloud signals scout watches it and emits findings', plus covering 'three surfaces', 'deploy ordering', and 'created_via attribution' — with named products, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what (sync a warehouse table, scout emits findings, three surfaces, deploy ordering, created_via) and when via a concrete 'Use when asked to ...' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Provides natural trigger phrases users would actually say — 'add a new inbox/self-driving source', 'wire up <Jira/GitLab/Sentry/Intercom/Freshdesk/Front/Gorgias/etc> as a signal source', and 'extend the source-toggle grid' — with broad synonym/product coverage.

5 / 5

Distinctiveness Conflict Risk

Targets a narrow, product-specific niche (PostHog Desktop Self-driving Inbox warehouse-backed sources) with distinct triggers, making conflict with unrelated skills minimal.

5 / 5

Total

20

/

20

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.