Tessl • The management layer for AI agent skills

The body is a lean, command-first operational guide with strong executable content and a well-documented connection lifecycle, including error-state and re-auth handling. Its main flaws are a broken workflow reference (two mentions of a nonexistent 'Step 2'), an empty 'Popular actions' section with no real examples, and a couple of padded sentences.

Suggestions

Fix the dangling 'Step 2' references: either add explicit numbered steps (1. Connect, 2. Discover & run actions) or reword to 'skip to Searching for actions' so the flow is navigable.

Populate 'Popular actions' with 3-5 real Bud actions (e.g. listing transactions, creating a budget line) with concrete intent strings and example input JSON, and note how to verify success by checking the `output` field.

Trim the padded intro ('It's primarily used by individuals...') and merge the duplicate `action list` instructions from 'Searching for actions' and 'Popular actions' into one section.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands and operational specifics Claude would not know (Membrane CLI, connection states), with only minor trimming opportunities: the second intro sentence ('It's primarily used by individuals looking to gain better control over their finances...') is padding, and 'searching for actions' vs 'Popular actions' repeat the same `action list` command. Not a 5 because of these few padded/redundant spots; not a 3 because nothing extensively explains concepts Claude already knows.	4 / 5
Actionability	Nearly every section gives a copy-pasteable command (install, login, connection ensure/get --wait, action list/run with --input, request with a flags table). It falls short of 5 only because no worked example uses real values — the 'Popular actions' heading promises examples but contains none, and there is no sample intent or action id for Bud.	4 / 5
Workflow Clarity	The overall sequence (install → login → connection ensure → wait for READY → search actions → run / proxy) is present and connection-state handling is well documented, but the text twice says 'skip to Step 2' and no Step 2 exists — the numbering is broken and the next phase ('Searching for actions') is never linked. It matches anchor 3 ('sequence present but checkpoints missing or implicit') rather than 4: there is no verification that an action ran successfully beyond 'the result is in the output field', and the dangling step references create a genuine navigational gap.	3 / 5
Progressive Disclosure	No bundle files exist, and the single-file structure is appropriate for a ~140-line operational guide: clear section hierarchy, a flags table, and no monolithic walls of reference material. Minor gaps (the proxy flags table and connection-state reference could live in a separate file if the skill grows) keep it at 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

41%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 correctly follows the what/when structure and is anchored to a distinct app name, but it is severely underspecified: it never mentions that Bud is a personal finance app or lists any concrete capability (budgets, transactions, accounts, goals). The 'when' clause is circular, restating 'interact with Bud data' rather than naming natural user triggers.

Suggestions

State what Bud is and its concrete capabilities, e.g. 'Manage Bud personal-finance data: budgets, budget lines, accounts, transactions, and goals' — mirror the entity list already present in the body.

Replace the circular trigger with natural user phrases, e.g. 'Use when the user mentions Bud, wants to check spending, update budgets or budget lines, or pull transaction/account data from Bud.'

Drop the buzzword phrase 'automate workflows', which conveys no concrete capability and inflates conflict risk with generic automation skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Bud integration") but the actions are entirely generic — "Manage data, records, and automate workflows" — with no concrete finance-specific actions like budgets, transactions, accounts, or goals. This matches the anchor 'Names the domain but actions are minimal or generic' and falls short of 3 because no concrete Bud action is actually stated.	2 / 5
Completeness	Both a 'what' ("Manage data, records, and automate workflows") and a 'when' ("Use when the user wants to interact with Bud data") are present, but the 'what' is vague and the 'when' is circular — it restates 'interact with Bud data' without concrete triggers. It sits between anchors 3 and 4: the 'what' is not clear enough and the 'when' adds too little specificity for a 4.	3 / 5
Trigger Term Quality	The only keywords are "Bud", "data", and "records" — one app name plus generic terms; the natural phrases a finance-app user would say (budget, spending, transactions, accounts, money) are all missing. It matches anchor 2 ('one or two generic keywords; missing the natural phrases users say') rather than 3, which would require some genuinely relevant natural keywords.	2 / 5
Distinctiveness Conflict Risk	The trigger is anchored to the specific app name "Bud", giving it a clear niche with low overlap risk against generic skills. It is not a 5 because the action phrases ('manage data, records, automate workflows') are generic and could overlap with other data-integration skills if 'Bud' is absent from the query.	4 / 5
	Total	11 / 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/bud/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.

bud

Table of Contents

Is this your skill?