Tessl • The management layer for AI agent skills

The body delivers real, executable Membrane CLI guidance with a solid connection-state handling loop, but it is padded with an encyclopedia-style app intro, a content-free overview section, an empty 'Popular actions' header, and broken internal step references. Tightening the structure and resolving the inconsistent CLI invocations would materially improve it.

Suggestions

Delete the 'Bump is a mobile app...' background paragraph and the 'Bump Overview' section ('Contact/Conversation/Task' + 'Use action names and parameters as needed'), or replace them with concrete entity-action examples.

Fix the dangling 'skip to **Step 2**' reference and '1b' numbering by defining an explicit Step 1/Step 2 (or removing the numbering), and pick one CLI invocation style ('membrane' vs 'npx @membranehq/cli') consistently.

Either populate 'Popular actions' with real example actions (e.g. contact/conversation/task operations with sample --input JSON) or remove the empty header, and de-duplicate the action-discovery guidance that currently appears twice.

Dimension	Reasoning	Score
Conciseness	The opening paragraph 'Bump is a mobile app that allows users to transfer contact information, photos, and files between smartphones...' explains what the app is (background Claude doesn't need to act), the 'Bump Overview' section reduces to 'Use action names and parameters as needed' (content-free), and discovery guidance is stated twice ('membrane action list --intent=QUERY' appears in both 'Searching for actions' and 'Popular actions'). Several sections exist mostly as padding.	2 / 5
Actionability	Commands are concrete and executable: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://bump.sh/" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input ...', plus a complete proxy flag table. Minor gaps: inconsistent invocation ('membrane' vs 'npx @membranehq/cli') and the 'Popular actions' header contains no actual actions.	4 / 5
Workflow Clarity	A rough sequence exists (install → login → connection ensure → poll state → search → run) with good connection-state checkpoints (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with follow-up polling), but 'skip to Step 2' points to a step that is never defined, section numbering ('1b') implies a structure that doesn't exist, and there is no validation guidance for action results or error recovery beyond connection setup.	3 / 5
Progressive Disclosure	Sections are organized with clear headers and no bundle files exist to reference, but the ~140-line body keeps everything inline (proxy options table, auth variants), ordering is odd ('Popular actions' header precedes 'Running actions' but is empty), and the vague 'Bump Overview' adds no navigational or content value.	3 / 5
	Total	12 / 20 Passed

Description

53%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 the right shape (domain + what + explicit 'Use when' trigger) and a distinctive app name, but its capability language is generic padding that neither tells Claude what it can actually do nor supplies the natural terms users would say. It reads like 'Processes PDF files' with a trigger clause appended.

Suggestions

Replace 'Manage data, records, and automate workflows' with the app's actual concrete capabilities (e.g. transfer contacts, share photos and files, manage conversations and tasks) to lift specificity and distinctiveness.

Expand the 'Use when' clause with concrete trigger phrases users would naturally say — e.g. 'Use when the user mentions Bump, wants to share contacts or files via Bump, or asks to manage Bump conversations or tasks.'

Drop the generic filler words 'data', 'records', and 'workflows' that cause overlap with unrelated data-management skills.

Dimension	Reasoning	Score
Specificity	'Manage data, records, and automate workflows' names the domain (Bump) but the actions are generic — no concrete operations like transferring contacts, sharing photos, or managing conversations. Matches 'Names the domain but actions are minimal or generic' ('Processes PDF files'); not 3 because nothing enumerated rises to a concrete, specific action.	2 / 5
Completeness	Both parts are present: 'what' = 'Bump integration. Manage data, records, and automate workflows.' and an explicit 'when' = 'Use when the user wants to interact with Bump data.' Fits 'Has both what and when; when could be more explicit or specific' — the when clause is circular (restates the domain) and the what is vague, so it falls short of the concrete trigger phrases of a 5.	4 / 5
Trigger Term Quality	'Bump' and 'Bump data' are relevant, distinctive keywords, but the remaining terms ('data', 'records', 'workflows') are generic and the natural phrases a user would say (contacts, photos, file transfer, conversations) are absent. Fits 'Some relevant keywords but missing common variations or synonyms'; not 4 because coverage of natural terms is thin beyond the app name.	3 / 5
Distinctiveness Conflict Risk	The 'Bump' name is distinctive and anchors triggering, but 'Manage data, records, and automate workflows' is so generic it overlaps with virtually any record/data-management integration (CRM, Notion, Airtable-type skills). Fits 'Somewhat specific but could still overlap with similar skills'; not 4 because the middle sentence broadens conflict risk considerably.	3 / 5
	Total	12 / 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/bump/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.

bump

Table of Contents

Is this your skill?