Name: trackingtime
Rating: 53.6 (1 reviews)
Author: membranedev

trackingtime

TrackingTime integration. Manage data, records, and automate workflows. Use when the user wants to interact with TrackingTime data.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/trackingtime/SKILL.md

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 body is genuinely actionable with real CLI commands and a strong connection-state workflow, but it is padded with a needless product intro and redundant sections, lacks validation around destructive action/proxy calls, and does no progressive disclosure. It is competent but improvable.

Suggestions

Remove the introductory paragraph defining TrackingTime and the 'Use action names and parameters as needed.' filler; consolidate the duplicate `action list` examples under 'Searching for actions'.

Add a validation/confirmation checkpoint before running or proxying actions (especially non-GET requests), e.g. confirm the action's effect via `action list` outputSchema or prompt the user before DELETE/mutating calls.

Label 'Step 2' (the action-search/run step) explicitly or restructure the flow so 'Skip to Step 2' resolves to a real heading.

Split the bulkier reference material (proxy flag table, full action discovery guide) into a separate reference file linked one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the opening paragraph explaining what TrackingTime is, the filler line 'Use action names and parameters as needed.', and the 'Popular actions' section re-stating the already-shown `action list` command add padding; not enough to drop to 2, but clearly trimmable.	3 / 5
Actionability	Provides copy-paste-ready bash commands with flags for install, login, connection ensure/get, action list/run, and proxy requests; minor gaps remain (CONNECTION_ID and <actionId> placeholders, no example `--input` payload tied to a real action).	4 / 5
Workflow Clarity	The connection-setup flow is well sequenced with state polling checkpoints, but 'Skip to Step 2' references a Step 2 that is never labeled, and running/proxying actions (which can issue DELETEs and other destructive calls) has no validation or confirmation step — the destructive-operations cap holds it at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all material lives inline in SKILL.md; section headers give some structure, but content that would naturally be separate (the proxy flag table, a full action catalog, best-practices detail) is monolithic with no one-level-deep references.	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 correctly pairs a 'what' with an explicit 'Use when' trigger and is third-person, but its action list is generic and the trigger vocabulary is thin beyond the product name. It is solid but not exemplary.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete TrackingTime actions, e.g. 'Log time entries, manage projects and tasks, pull reports'.

Expand the trigger phrase to include natural user terms such as 'timesheets', 'hours', 'time entries', or 'project reports', not just 'TrackingTime data'.

Add the user-visible nouns (projects, tasks, clients, reports) so the description signals exactly when to invoke this skill over a generic productivity integration.

Dimension	Reasoning	Score
Specificity	Names the domain ('TrackingTime integration') and a few actions ('Manage data, records, and automate workflows'), but the listed actions are generic rather than concrete; it does not reach the 'several specific actions' bar of 4.	3 / 5
Completeness	It states both the 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with TrackingTime data'); the trigger is present but could name concrete scenarios to reach 5.	4 / 5
Trigger Term Quality	The only natural keyword is 'TrackingTime' (repeated) plus the generic 'data'; common user phrasings like 'time entries', 'projects', 'timesheets', or 'hours' are absent, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'TrackingTime' gives it a clear niche and low conflict risk, but the generic 'interact with data' trigger leaves minor overlap with other time-tracking integrations, keeping it below 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/trackingtime/SKILL.md
Commit: f484c82

Reviewed: 4 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.