Name: managing-reminders
Rating: 75.2 (1 reviews)
Author: PostHog

managing-reminders

Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be reminded to look at a dashboard, insight, experiment, feature flag, survey, notebook, replay, or error, or wants to list, change, or cancel their reminders. Covers when to pick a reminder over an alert or subscription, the one-off vs recurring vs cron schedule field mappings, timezones, and attaching a resource.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%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 lean, highly actionable, and well-structured, with concrete field mappings and a copy-paste worked example. The main gap is a missing explicit confirm-before-delete checkpoint for the destructive reminder-delete operation, and some reference-style content could be progressively offloaded.

Suggestions

Add an explicit validation/confirm checkpoint to the destructive workflow: before calling reminder-delete, confirm the target reminder id/title with the user and re-list via reminders-list to verify the match.

Consider moving the full resource_type → resource_id mapping table and lifecycle state transitions into a reference file (e.g. references/resource-types.md) to shorten SKILL.md and apply progressive disclosure.

Add a brief validation step after reminder-create beyond confirming next_fire_at (e.g. reminder-get to confirm the persisted schedule/timezone) so the creation workflow has a complete feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with tables mapping user phrases directly to fields, no over-explanation of concepts Claude already knows, and a compact worked example; every section earns its place, matching the 'lean and efficient' anchor.	5 / 5
Actionability	Fully executable guidance: concrete field mappings, real cron strings, a copy-paste-ready reminder-create JSON payload, and a tool list; matches the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	The worked example is a clear numbered sequence ending in a verify/confirm step ("Confirm back to the user… use next_fire_at"), matching 'clear sequence with most checkpoints present'; not a 5 because the destructive reminder-delete operation has no explicit validation/confirm-before-delete checkpoint.	4 / 5
Progressive Disclosure	Well-organized single file with clear section headers, no nested references, and content split into scannable tables; matches 'good structure, most content appropriately placed'; not a 5 because at ~135 lines some reference material (e.g. the full resource_type table or lifecycle details) could be offloaded to a reference file, and no bundle references are used.	4 / 5
	Total	18 / 20 Passed

Description

95%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 strong: it states concrete capabilities, includes rich natural trigger phrases, covers both what and when, and distinguishes reminders from related alert/subscription skills. Specificity is the only dimension with a minor gap, as the action list is good but not exhaustive.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("create and manage", "list, change, or cancel", "fire as in-app notifications on a schedule") with only minor coverage gaps, matching the 'lists several specific actions' anchor; not a 5 because the action list, while solid, is not exhaustive of all management operations.	4 / 5
Completeness	Explicitly answers both 'what' (create and manage PostHog reminders…) and 'when' ("Use when the user says…" with concrete trigger phrases), matching the top anchor; not below because both halves are clearly and concretely stated.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including the canonical phrase ("remind me to…"), schedule synonyms ("daily/weekly/monthly/yearly", "cron schedule", "specific date/time"), and the full resource list a user would name; matches the 'comprehensive coverage including synonyms' anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (PostHog reminders) with distinct trigger ("remind me to…") and an explicit disambiguation from alerts and subscriptions, giving minimal conflict risk; matches the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PostHog/posthog
Path: products/reminders/skills/managing-reminders/SKILL.md
Commit: b0fece0

Reviewed: ~3 hours ago

Table of Contents

Discovery Implementation Validation

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.