Tessl • The management layer for AI agent skills

SkillPublic

breathe

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

Quality

65%

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/breathe/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 content is genuinely actionable — concrete CLI commands, auth flows, and error-state handling for the connection lifecycle — but it is undermined by incoherent step numbering, a placeholder 'Popular actions' section, and a wrong official-docs link. Tightening the workflow references and removing duplication would lift it substantially.

Suggestions

Fix the broken step numbering: 'skip to **Step 2**' has no target — either add explicit 'Step 1/Step 2' headings or remove the references and the orphaned '1b' heading.

Replace the empty 'Popular actions' section with 3-5 real action examples (id, purpose, sample input) so a first run can be copy-pasted, and merge it with 'Searching for actions' to remove the duplicated command.

Correct the official docs URL (currently pointing to Apple ClockKit's watchOS 'Breathe' documentation, unrelated to Breathe HR) and delete the vague 'Breathe Overview' bullet list.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete commands, but includes unnecessary padding: the introductory paragraph about what Breathe is, the vague 'Breathe Overview' bullet list ('Session', 'Note', 'User', 'Profile' with 'Use action names and parameters as needed'), and duplicated action-list guidance in both 'Searching for actions' and 'Popular actions'.	3 / 5
Actionability	Concrete, executable CLI commands throughout (install, login, connection ensure, action list/run with JSON input, proxy request with a flags table). Minor gaps: no worked example resolving the <actionId>/CONNECTION_ID placeholders to a real call, and inconsistent invocation between 'membrane' and 'npx @membranehq/cli@latest'.	4 / 5
Workflow Clarity	A coherent sequence exists (install → authenticate → connect → poll state → search actions → run → proxy fallback) with a real feedback loop for CLIENT_ACTION_REQUIRED, but 'skip to Step 2' references a step heading that does not exist, and running actions against HR data has no verification checkpoint.	3 / 5
Progressive Disclosure	A single ~140-line file with section headers and no bundle files; all detail is inline. Organization gaps beyond minor: the 'Popular actions' section lists no actual actions and duplicates the action-list command, and the vague overview bullets add no navigational value.	3 / 5
	Total	13 / 20 Passed

Description

57%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 a clear trigger clause and a distinctive domain name, but the capability statement is generic and padded. It communicates when to use the skill but only weakly what the skill can concretely do.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities drawn from the body, e.g. 'Manage employee records, absence and leave tracking, and performance reviews in Breathe HR'.

Add natural trigger synonyms to the 'Use when' clause: 'Use when the user mentions Breathe, Breathe HR, employee data, absence/leave, or performance reviews'.

Trim buzzword phrasing like 'automate workflows' that adds no concrete information.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Breathe integration') but its actions — 'Manage data, records, and automate workflows' — are generic buzzword-level phrasing with no concrete capability like absence tracking or employee record management.	2 / 5
Completeness	Both 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Breathe data') are present, but the 'what' is vague and the 'when' is generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	'Breathe' and 'Breathe data' are relevant natural keywords, but common variations users would actually say — 'HR', 'employees', 'absence', 'time off', 'performance reviews' — are missing.	3 / 5
Distinctiveness Conflict Risk	'Breathe' is a clear niche trigger with minimal conflict risk, but the generic 'Manage data, records, and automate workflows' tail could match many data-integration skills, and 'Breathe' is also an Apple Watch/fitness concept.	4 / 5
	Total	13 / 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/breathe/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.

breathe

Table of Contents

Is this your skill?