CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

calcom

Cal.com integration. Manage Users. Use when the user wants to interact with Cal.com data.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/calcom/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 content delivers genuinely actionable CLI guidance with a well-handled connection state machine, but is weighed down by padding (the all-'No description' actions table, the malformed overview list, background prose about Cal.com) and a broken 'Step 2' cross-reference. Destructive booking operations lack any validation guidance, and everything lives in one file with no progressive disclosure.

Suggestions

Fix the dangling 'skip to Step 2' reference by numbering the workflow steps explicitly (Step 1 connect, Step 2 find/run actions).

Add a confirmation/validation checkpoint before destructive actions (e.g., verify booking details with the user before running cancel-booking or update-booking).

Trim the 'No description' column from the actions table (or populate real descriptions), drop the background paragraph explaining what Cal.com is, and move the actions catalog and CLI/auth boilerplate into a references file to slim the main body.

DimensionReasoningScore

Conciseness

The body is mostly efficient commands and tables, but includes unnecessary padding: an intro explaining what Cal.com is, a 20-row 'Popular actions' table whose Description column reads 'No description' on every row, and a malformed entity-dump 'Cal.com Overview' list ending in the vague 'Use action names and parameters as needed.' This matches the anchor for mostly efficient content with some unnecessary explanation.

3 / 5

Actionability

Concrete, executable commands appear throughout — 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://cal.com" --json', 'membrane action run <actionId> --input {...}' — plus a proxy flag table; minor gaps (the 'skip to Step 2' reference points to a nonexistent step, and there is no fully worked action-run example) keep it below the copy-paste-complete anchor 5.

4 / 5

Workflow Clarity

The install → login → connect → poll → search → run sequence exists with a good feedback loop for connection states ('--wait' polling, CLIENT_ACTION_REQUIRED handling, error-state guidance), but 'skip to Step 2' references a step that does not exist, and destructive actions (Cancel Booking, Update Booking) have no validation or confirmation steps, which caps this dimension at 3.

3 / 5

Progressive Disclosure

The body has reasonable section headers but is a single ~180-line file with no bundle references; catalog-style content (the 20-action table, proxy flag table, and CLI/auth boilerplate) is inlined where separate reference files would serve better, matching the anchor for some structure with content that should be separate kept inline.

3 / 5

Total

13

/

20

Passed

Description

62%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 has an explicit 'Use when' trigger and a distinctive Cal.com niche, but its capability statement is thin: 'Manage Users' names only one of the skill's many entity areas and the natural trigger vocabulary (bookings, appointments, scheduling) is absent. It is serviceable but under-sells and under-triggers the skill.

Suggestions

Replace 'Manage Users' with the skill's actual capability areas, e.g. 'Manage bookings, event types, schedules, availability, users, and teams in Cal.com'.

Add natural trigger terms users would say — 'bookings', 'appointments', 'scheduling', 'booking pages' — to the 'Use when' clause.

State the interaction mode (listing, creating, updating, and canceling records via the Membrane CLI) so the 'what' is concrete rather than the generic 'integration'.

DimensionReasoningScore

Specificity

'Cal.com integration' is generic but 'Manage Users' names one concrete action, matching the anchor for naming the domain plus 1-2 concrete actions without comprehensive coverage; it is not a 4 because the skill's actual capability areas (bookings, event types, schedules, teams) are unmentioned.

3 / 5

Completeness

Both parts are explicitly present: what ('Cal.com integration. Manage Users.') and when ('Use when the user wants to interact with Cal.com data'), so the anchor-3 case of a missing or merely implied trigger does not apply; both could be more specific, matching anchor 4.

4 / 5

Trigger Term Quality

'Cal.com', 'Users', and 'Cal.com data' are relevant keywords, but common natural phrases users would say — 'bookings', 'appointments', 'scheduling', 'booking pages' — are missing, matching the anchor for some relevant keywords without common variations or synonyms.

3 / 5

Distinctiveness Conflict Risk

'Cal.com' establishes a clear niche in both the what and when clauses, but 'Manage Users' is generic phrasing with minor overlap risk against generic user-management skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor 5.

4 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

membranedev/application-skills

Path

skills/calcom/SKILL.md

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.