CtrlK
BlogDocsLog inGet started
Tessl Logo

inbox-exploration

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged recently?", asks about a specific report by ID or title, wants to act on / fix / implement a report (turn it into a PR), wants to resolve, dismiss, or snooze a report, or wants to see which signal sources are configured. Covers listing, filtering, drilling into, and acting on reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed.

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

Low

Low-risk findings worth noting

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.

A highly actionable, well-sequenced skill body with strong workflow validation for destructive and batch operations, dragged down by notable repetition and a monolithic structure with no reference-file offloading.

Suggestions

Deduplicate the MCP-writes list and the 'don't resolve at PR-open time' guidance — state each once and cross-reference, rather than repeating in Available tools, the act-on-report workflow, and Tips.

Move the full is_suggested_reviewer production mechanism and the canonical dismissal_reason table into a reference file (e.g. references/states.md) and keep only the triage-relevant summary inline.

Trim the internal implementation detail of resolve_reviewers.py commit-authorship weighting; the agent only needs the user-facing meaning of the flag, not the heuristic internals.

DimensionReasoningScore

Conciseness

Mostly efficient and domain-dense, but the MCP-writes list and PR-resolve guidance are each repeated three times (Available tools prose, workflow steps, and Tips), and the full is_suggested_reviewer matching mechanism (resolve_reviewers.py internals) is more than Claude needs to act.

2 / 3

Actionability

Provides concrete, copy-paste-ready JSON tool calls with real parameters — 'status': 'ready,in_progress,pending_input', the six canonical dismissal_reason codes, snooze_for, bulk ids 1–100 — plus a formatted response template.

3 / 3

Workflow Clarity

Each workflow is explicitly stepped with validation checkpoints: jump to the setup-check on count:0, inspect already_addressed/implementation_pr_url/status before acting, 'Verify the diagnosis against the code (do not skip)', and per-id outcome inspection on bulk transitions with 409/400 handling.

3 / 3

Progressive Disclosure

Sections are well-organized with clear headers and it appropriately offloads to the external signals skill, but it is a single ~480-line monolithic file with no bundle files, and reference-like content (full tool table, status terminology, reviewer mechanism, state-transition rules) lives inline where it could be split out.

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 exemplary: third-person voice, concrete capabilities, a rich set of natural trigger phrases, an explicit 'Use when' clause, and a clearly bounded niche that distinguishes it from the adjacent signals skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'listing, filtering, drilling into, and acting on reports', 'resolve, dismiss, or snooze a report', pointers to the signals skill — rather than vague language.

3 / 3

Completeness

Clearly answers both what ('Explore PostHog's Inbox and act on what it surfaces') and when via an explicit 'Use when...' clause with many enumerated triggers.

3 / 3

Trigger Term Quality

Quotes natural phrases users would actually say — 'what's in my inbox?', 'what should I look at?', 'which reports are actionable?', 'what's PostHog flagged recently?' — with strong coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Carves a clear PostHog Inbox niche and explicitly distinguishes it from the deeper 'signals' skill, making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

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.