bookings

Booking lifecycle — pending, confirmed, rescheduled, cancelled — plus attendees, references, no-shows, and reminders.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/scheduling/docs/skills/bookings/SKILL.md

Quality

Content

86%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 lean, well-organized knowledge skill that adds only project-specific facts Claude could not know (lifecycle semantics, token fields, reference propagation, the ICS endpoint). It would score higher on actionability if it included concrete commands or API paths for the actions it names (mark-no-show, reschedule-booking, cancel).

Dimension	Reasoning	Score
Conciseness	Every section is 2–4 lines of dense project-specific facts ('the old booking after a reschedule... `from_reschedule` links them', 'iCalUID is preserved across the reschedule chain (RFC 5545), and `iCalSequence` is bumped') with zero padding or explanation of concepts Claude already knows. Matches the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	An instruction-only knowledge skill with concrete, specific guidance throughout: exact identifiers ('`mark-no-show` sets `noShow: true`', '`/booking/:uid.ics` returns the RFC 5545 calendar file', 'Stored in `booking_references`'). Minor gaps — e.g., no API paths or commands for the reschedule/cancel actions themselves — keep it below fully executable anchor 5.	4 / 5
Workflow Clarity	The reschedule chain semantics are laid out clearly (new booking, `fromReschedule` link, iCalUID preservation, sequence bump) and the lifecycle states are coherent, but no sequenced workflow with validation checkpoints is presented. Not 5 because there is no unambiguous single action or explicit step sequence; not 3 because nothing is incoherent and no risky operation lacks ordering.	4 / 5
Progressive Disclosure	Under 50 lines, no external references needed, and the content is organized into clear headed sections (Lifecycle, Reschedule vs cancel+rebook, No-show, Cancel/reschedule tokens, References, ICS). Per the rubric guideline, skills under 50 lines with no need for external references score 5 with just well-organized sections; no bundle files exist and none are referenced.	5 / 5
	Total	18 / 20 Passed

Description

61%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 concise and concrete about the domain's entities and lifecycle states, but it never states what the skill actually does (no action verbs) and lacks any 'Use when...' trigger guidance, which caps completeness. Trigger keywords are good though missing common synonyms like 'appointments' or 'calendar'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with bookings, appointments, or scheduling data — creating, rescheduling, or cancelling bookings, or handling no-shows and reminders.'

Lead with action verbs to state what the skill does, e.g. 'Manages the booking lifecycle — confirming, rescheduling, cancelling — and tracks attendees, no-shows, and reminders.'

Include common synonyms users would naturally say (appointments, calendar events, scheduling) to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates concrete concepts ('pending, confirmed, rescheduled, cancelled — plus attendees, references, no-shows, and reminders') but contains no action verbs, describing entities rather than what the skill does. More concrete than anchor 2, but lacks the specific actions required for anchor 4.	3 / 5
Completeness	Has a clear 'what' (the lifecycle states and related entities) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Natural keywords a user would say are present ('booking', 'rescheduled', 'cancelled', 'no-shows', 'reminders'), giving good coverage. Missing common synonyms such as 'appointments', 'calendar', or 'scheduling', keeping it below anchor 5.	4 / 5
Distinctiveness Conflict Risk	'Booking lifecycle' with terms like 'no-shows' and 'rescheduled' carves a mostly distinct niche with distinct triggers. Minor overlap risk with general calendar or scheduling skills, so it falls just short of anchor 5.	4 / 5
	Total	14 / 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: BuilderIO/agent-native
Path: packages/scheduling/docs/skills/bookings/SKILL.md
Commit: a941a2e

Reviewed: 9 days 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.