Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

agave

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

Quality

71%

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/agave/SKILL.md

Quality

Content

67%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 solid, command-centric integration skill whose strongest section is the connection state-handling workflow with explicit polling checkpoints. Its main weaknesses are a handful of padded or content-free sections, a duplicated discovery command, and broken internal step references ('Step 2', '1b') that point at steps that are never defined.

Suggestions

Fix or remove the phantom step references: 'skip to Step 2' and the '#### 1b.' heading reference a numbering scheme that never appears; either number the actual steps (Install → Authenticate → Connect → Discover → Run) or drop the numbers.

Delete the empty 'Agave Overview' bullet list (Files/Folders/Apps/Tasks/Users) and merge the 'Popular actions' section into 'Searching for actions' to remove the duplicated `action list` command and inert headings.

Tighten the intro and Best Practices sections (e.g., trim 'It's used by researchers and scientists to streamline...' and 'This will burn less tokens') and standardize on one CLI invocation form (membrane vs npx @membranehq/cli).

Dimension	Reasoning	Score
Conciseness	Mostly command-driven and efficient, but includes unnecessary filler: a two-sentence marketing-style intro, a content-free 'Agave Overview' bullet list, and a 'Popular actions' section that duplicates the discovery command from 'Searching for actions'.	3 / 5
Actionability	Concrete, copy-paste-ready commands throughout (install, login, connection ensure, polling, action run with JSON input, proxy flag table) with explicit placeholders. Falls short of 5 due to the dangling 'skip to Step 2' reference and inconsistent invocation style (membrane vs npx @membranehq/cli).	4 / 5
Workflow Clarity	The install → login → connect → poll → search → run sequence is discernible and the connection state machine (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with re-polling instructions) provides explicit checkpoints and a feedback loop. Not 5 because the 'Step 2' and '1b' numbering references steps that are never labeled, which breaks navigability of the sequence.	4 / 5
Progressive Disclosure	Single-file skill with no bundle files and clear section organization; operational detail is appropriately inlined. Minor gaps: the 'Popular actions' heading contains no actions and the phantom step numbering confuses navigation.	4 / 5
	Total	15 / 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.

A functional description that names the platform, lists its capabilities, and includes an explicit 'Use when' trigger — better than most vague descriptions but not exemplary. Its main gaps are generic action verbs and thin trigger-term coverage relative to the breadth the body actually supports (files, apps, tasks, users).

Suggestions

Replace the generic verbs with concrete capabilities drawn from the body, e.g., 'Manage Agave files and folders, run apps and tasks, and search user records.'

Broaden the 'Use when' clause with natural trigger phrases users would say, e.g., 'Use when the user mentions Agave, wants to upload or list files on Agave, run Agave apps or jobs, or automate scientific workflows.'

Include the terms users actually type (files, apps, tasks, jobs) rather than only 'Agave data' to improve trigger matching.

Dimension	Reasoning	Score
Specificity	Names the Agave domain and lists actions ('Manage data, records, and automate workflows'), but the verbs are generic ('manage') rather than concrete; this sits above anchor 2 (minimal/generic actions only) but below anchor 4 (several specific actions with minor gaps).	3 / 5
Completeness	Explicitly answers both: 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Agave data'). The 'when' clause is present so the 3-cap does not apply, but neither part carries the concrete trigger phrases needed for anchor 5.	4 / 5
Trigger Term Quality	'Agave' is the key natural trigger and 'data', 'records', 'workflows' add some relevance, but common variations users would actually say (files, apps, tasks, jobs, uploading data, running analyses) are missing — matching anchor 3's 'missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The named platform 'Agave' creates a clear niche with distinct triggers and minimal conflict risk, but the generic tail 'Manage data, records, and automate workflows' could overlap with general data/automation skills, keeping it just below anchor 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/agave/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.

agave

Table of Contents

Is this your skill?