Tessl • The management layer for AI agent skills

The body delivers strong executable CLI guidance with a sensible proxy fallback and good state-handling for connections. Its weaknesses are padding (the promotional intro and the information-free module list), broken workflow numbering (references to a nonexistent 'Step 2'), and an empty 'Popular actions' section.

Suggestions

Cut the introductory paragraph about what 1CRM is and who uses it — Claude doesn't need it — and either give the 45-item module list a purpose (e.g. mapping module names to example actions) or move it to a reference file.

Fix the workflow numbering: the text references 'Step 2' and '1b' but no numbered steps exist; number the full sequence (install → login → connect → wait for READY → search → run) explicitly.

Make the 'Popular actions' section actually list a few common actions (e.g. list accounts, create contact, update opportunity) and standardize on one CLI invocation form ('membrane ...' vs 'npx @membranehq/cli ...').

Dimension	Reasoning	Score
Conciseness	The intro paragraph ("1CRM is a customer relationship management platform designed to help businesses manage sales, marketing, and customer service activities...") is background Claude does not need, and the 45-item bolded module list conveys no actionable information, capped by the filler line "Use action names and parameters as needed." Otherwise the CLI instructions are reasonably tight, matching anchor 3 (mostly efficient but includes some unnecessary explanation).	3 / 5
Actionability	Concrete, copy-paste-ready commands cover install, login, connection setup, action discovery/execution, and proxying (with a full flag table), which approaches anchor 5. But minor gaps keep it at anchor 4: the CLI is invoked inconsistently ("npx @membranehq/cli connection get" vs "membrane connection get"), and the 'Popular actions' section contains no actual popular actions — just a duplicated discovery command.	4 / 5
Workflow Clarity	The overall sequence (install → login → connection ensure → poll state → search actions → run → proxy) is present and includes per-state next actions, but it is broken by dangling references: the text says "skip to Step 2" twice yet no Step 2 exists, and "#### 1b. Wait for the connection to be ready" is orphaned numbering with no Step 1 or 2 labels. This matches anchor 3 (steps listed but validation/sequence gaps) rather than 4's clear sequence with most checkpoints.	3 / 5
Progressive Disclosure	A single SKILL.md with no bundle files, organized into clear sections (overview, install, auth, connect, search, run, proxy, best practices). Most content is appropriately placed, matching anchor 4; the 45-item module list and the proxy flag table are minor candidates for a separate reference file, keeping it below anchor 5.	4 / 5
	Total	14 / 20 Passed

Description

66%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 well-formed with an explicit 'Use when' clause and a distinctive product-name trigger, but its capability statements are generic. Naming the concrete record types and operations (contacts, leads, opportunities, invoices, etc.) would sharpen both specificity and trigger-term quality.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete capabilities, e.g. 'Create, update, and search 1CRM records — accounts, contacts, leads, opportunities, cases, invoices — and automate workflows'.

Broaden trigger terms to include natural synonyms users would say: 'contacts', 'leads', 'deals/opportunities', 'CRM records', not just '1CRM data'.

Consider adding file- or domain-based triggers (e.g. 'when the user mentions 1CRM, their CRM, or asks about customer records') to make the 'when' clause more explicit.

Dimension	Reasoning	Score
Specificity	The description names the domain ("1CRM integration") and a couple of actions ("Manage data, records, and automate workflows"), but the actions are generic — no concrete capabilities like managing contacts, leads, opportunities, or invoices are stated. It matches anchor 3 (domain plus 1-2 actions, not comprehensive) rather than 2, since multiple actions are listed, and not 4, since none are truly concrete.	3 / 5
Completeness	It answers both parts: a what ("1CRM integration. Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with 1CRM data"). It matches anchor 4 rather than 5 because the when is a single generic trigger phrase and the what is vague about concrete capabilities.	4 / 5
Trigger Term Quality	Relevant keywords are limited to "1CRM", "data", "records", and "workflows"; common natural terms users would say — "contacts", "leads", "accounts", "opportunities", "CRM" — are missing. This matches anchor 3 (some relevant keywords but missing common variations or synonyms), falling short of anchor 4's good keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The "1CRM" product name gives it a clear niche with distinct triggers ("Use when the user wants to interact with 1CRM data"), making it unlikely to trigger for the wrong skill — a direct match for anchor 5.	5 / 5
	Total	15 / 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/1crm/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.

1crm

Table of Contents

Is this your skill?