Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

10to8

10to8 integration. Manage data, records, and automate workflows. Use when the user wants to interact with 10to8 data.

Quality

69%

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 ./skills/10to8/SKILL.md

Quality

Content

65%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.

A highly actionable CLI-driven skill: commands are concrete and executable throughout, with good error-state handling for connection setup. The main weaknesses are a broken step numbering scheme (dangling "Step 2" references), missing validation guidance for destructive booking operations, and some trimmable prose.

Suggestions

Fix the incoherent step references: either number the workflow explicitly (1. Install, 2. Authenticate, 3. Connect, 4. Discover actions, 5. Run actions) or remove the "Step 2" and "1b" labels entirely.

Add a validation checkpoint before destructive actions (cancel-booking, update-booking), e.g. verify the booking details with get-booking and confirm with the user before running cancel.

Trim marketing prose ("focus on the integration logic rather than auth plumbing", "burn less tokens") and consider moving the full action catalog and clientAction schema details into a reference file to slim the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	The bulk is lean (commands, tables, brief explanations), but there is unnecessary prose that could be trimmed: the marketing-flavored sentences ("you can focus on the integration logic rather than auth plumbing", "This will burn less tokens and make communication more secure") and the low-value "10to8 Overview" bullet tree of app entities.	3 / 5
Actionability	Every section provides copy-paste-ready commands: install (npm install -g @membranehq/cli@latest), login, connection ensure, polling with --wait, action list/run with concrete --input JSON examples, and the proxy command with a full options table. The popular-actions table with keys makes the catalog directly usable.	5 / 5
Workflow Clarity	The overall sequence (install → login → ensure connection → poll states → search actions → run → proxy fallback) is present and the connection-state handling (READY/CLIENT_ACTION_REQUIRED/error) forms a decent feedback loop, but the flow references "Step 2" twice and labels a section "#### 1b." with no defined Step 1 or Step 2. Destructive actions (Cancel Booking, Update Booking) are offered with no validation/verification guidance, which caps this score at 3.	3 / 5
Progressive Disclosure	The skill is a single ~160-line file with no bundle files (references/, scripts/, assets/ are absent) and no one-level-deep references at all. Sections are clearly headed, but inline content like the 16-row popular-actions table and the clientAction reference details are the kind of material that could live in a separate reference file for a leaner SKILL.md.	3 / 5
	Total	14 / 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 has an explicit "Use when..." trigger and is clearly tied to a distinct product, but its capability statement is vague. Replacing "Manage data, records, and automate workflows" with concrete 10to8 actions would substantially improve it.

Suggestions

Name concrete capabilities instead of generic ones — e.g. "Manage appointments, bookings, staff, services, and customer records in 10to8".

Add natural trigger terms users would actually say: appointments, scheduling, bookings, reminders, calendar.

Keep the explicit "Use when..." clause but scope it to those concrete terms, e.g. "Use when the user wants to manage 10to8 appointments, bookings, or scheduling data."

Dimension	Reasoning	Score
Specificity	The description names the domain ("10to8 integration") but the stated actions — "Manage data, records, and automate workflows" — are generic and interchangeable with almost any integration; no concrete 10to8 capabilities like bookings, appointments, or scheduling are named.	2 / 5
Completeness	Both parts are present: a "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with 10to8 data"). Not a 5 because the "what" lacks concrete trigger phrases; not a 3 because the "when" clause is explicit rather than weakly implied.	4 / 5
Trigger Term Quality	"10to8" is the genuinely relevant trigger term and appears twice, but the surrounding keywords ("data", "records", "workflows") are generic; natural phrases users would say such as "appointments", "bookings", "scheduling", or "reminders" are missing.	3 / 5
Distinctiveness Conflict Risk	"10to8" is a clear niche trigger repeated in both the what and when clauses, making it highly distinguishable from other skills; the generic filler words do not create meaningful conflict risk.	5 / 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/10to8/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

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.

10to8

Table of Contents

Is this your skill?