Tessl • The management layer for AI agent skills

SkillPublic

adatree

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

Quality

72%

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/adatree/SKILL.md

Quality

Content

75%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 a solid, executable guide: concrete CLI commands for every phase, an explicit connection-state workflow, and well-organized sections with no dead references. The main improvements are fixing the dangling "Step 2" step labels, deduplicating the action-discovery instructions, and adding one fully resolved worked example.

Suggestions

Fix the workflow numbering: "skip to **Step 2**" appears twice but no Step 2 (or Step 1) heading exists — either number the main workflow steps or replace the references with the actual section names.

Add one fully concrete worked example, e.g., a real `--intent "list datasets"` search followed by running the returned action with a real `--input '{...}'` payload, so placeholders are shown resolved.

Merge the "Searching for actions" and "Popular actions" sections, which currently repeat the same `action list --intent` discovery instructions.

Dimension	Reasoning	Score
Conciseness	The body is command-first and lean — install, login, connect, discover, run, proxy — with only minor trimmable material: the action-discovery command is duplicated between "Searching for actions" and "Popular actions", and the unannotated "Adatree Overview" entity bullet list adds little. Fits "Efficient; minor instances of over-explanation that could be trimmed"; it is not a 3 because there is no substantial padding, and not a 5 because of the redundancy.	4 / 5
Actionability	Concrete, copy-paste-ready CLI commands throughout, including login with headless fallback, `connection ensure`, `--wait` polling, `action run` with `--input` JSON, and a full proxy flag table. It falls short of anchor 5 because placeholders ("QUERY", "CONNECTION_ID", "<actionId>") are never shown resolved — there is no fully worked example with a real intent string, action id, and input payload.	4 / 5
Workflow Clarity	The install → login → connect → discover → run/proxy sequence is clear, and connection readiness is handled as an explicit state machine (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with what to do in each). Minor gaps keep it at anchor 4: "skip to Step 2" references a step label that never exists in the document, and there is no error-recovery guidance for failed action runs.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent), so all guidance is inline in a single well-sectioned ~145-line file with no nested references — a sound structure for a skill of this size. It fits "Good structure; most content is appropriately placed" rather than 5 because the file exceeds the short-skill range and detail like the proxy flag table and entity list would naturally live in a reference file if the skill grows.	4 / 5
	Total	16 / 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 is serviceable: it names the domain, keeps third person, and includes an explicit "Use when" clause, so it answers both what and when. Its main weakness is vague, generic capability language ("manage data", "automate workflows") with no concrete operations and thin trigger coverage beyond the brand name.

Suggestions

Replace the generic verbs with the skill's concrete capabilities, e.g., "List and query datasets, data products, and data requests; manage members, subscriptions, and wallets via the Adatree API."

Expand the trigger clause with concrete phrases and synonyms, e.g., "Use when the user mentions Adatree, consumer data sharing, CDR, or wants to retrieve or exchange Australian consumer data."

Drop buzzword phrasing like "automate workflows" in favor of the specific operations the skill actually supports.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Adatree domain, but the actions are generic — "manage" and "automate workflows" are buzzword-level verbs with no concrete operations (it never says what is done to the data or records). This matches the anchor "Names the domain but actions are minimal or generic"; it is not a 3 because no action is concrete enough to count as specific.	2 / 5
Completeness	It explicitly answers both: what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Adatree data"). Anchor 3 does not apply because the "when" is explicit rather than weakly implied, but it is not a 5 since the "what" is vague and the "when" merely restates the domain instead of giving concrete trigger phrases.	4 / 5
Trigger Term Quality	"Adatree", "data", and "records" are relevant keywords — a user needing this skill would say "Adatree" — but common variations and synonyms are missing (e.g., "data sharing", "consumer data", "CDR", or use-case phrases like retrieving Australian consumer data). Fits "Some relevant keywords but missing common variations or synonyms".	3 / 5
Distinctiveness Conflict Risk	The "Adatree" brand name gives a distinct trigger with a clear niche, but the generic phrases "Manage data" and "automate workflows" create overlap risk with other data-integration and automation skills if the user does not name Adatree. Fits "Mostly distinct; minor overlap risk with closely related skills".	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/adatree/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.

adatree

Table of Contents

Is this your skill?