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%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.

The body is a thorough, executable engineering playbook with strong workflow sequencing and validation checkpoints, but it is monolithic: everything lives inline in SKILL.md with no bundled reference files to progressively disclose the catalog and per-source detail.

Suggestions

Move the Tier-1 source catalog table and the per-file posthog/code and posthog/posthog checklists into a references/ file (e.g. references/source-catalog.md and references/checklists.md), keeping SKILL.md a concise overview that links one level deep.

Provide a complete, copy-paste-ready emitter template (the full github_issues.py shape) in a reference file rather than instructing to 'copy github_issues.py and adapt', so the most failure-prone step is fully executable.

Tighten the OAuth/form-rendering section by consolidating the three overlapping explanations of DynamicSourceSetup into a single concise statement plus a reference link.

DimensionReasoningScore

Conciseness

Dense and domain-specific, assuming Claude's knowledge of worktrees, migrations, and PRs without padding; the OAuth/form-rendering sections could be tightened slightly but every token earns its place with concrete file paths and gotchas.

4 / 5

Actionability

Provides exact file paths, exact commands (`python manage.py makemigrations signals`), concrete switch-case routing, and a copy-paste worktree block; falls just short of 5 because the emitter step says to copy and adapt github_issues.py rather than giving complete code.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced across the posthog/posthog and posthog/code checklists with explicit deploy-ordering dependencies and dedicated 'Verify' checkpoints, including validation for the destructive migration step (`makemigrations --check`).

5 / 5

Progressive Disclosure

No references/scripts/assets bundle exists, so all detail — the full Tier-1 catalog table and the per-source checklists — is inlined in one ~250-line file; cross-references to other skills exist, but content that could be offloaded to one-level-deep reference files is not split out.

3 / 5

Total

16

/

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 what the skill does con concrete terms, gives explicit natural-language triggers for when to use it, and is tightly scoped to a distinct niche. Third-person voice is used throughout with no first/second-person slips.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — syncing a warehouse table, a signals scout emitting findings, wiring three named surfaces, deploy ordering, and created_via attribution — giving comprehensive coverage of the domain with no vague filler.

5 / 5

Completeness

Explicitly answers both 'what' (add a warehouse-backed source to the Self-driving Inbox) and 'when' (a clear 'Use when...' clause with concrete 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/...> as a signal source', 'extend the source-toggle grid') with broad synonym coverage of named providers.

5 / 5

Distinctiveness Conflict Risk

Occupies a very specific niche (PostHog Self-driving Inbox sources across three named repos) with distinct triggers and minimal overlap risk with other skills.

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.