Tessl • The management layer for AI agent skills

SkillPublic

alphasense

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

Quality

74%

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/alphasense/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.

A well-structured, command-driven skill body that gives Claude executable guidance for connecting to and acting on AlphaSense, with good polling/error checkpoints for the connection lifecycle. Its main flaws are a dangling 'Step 2' reference, an empty 'Popular actions' section that duplicates the discovery command, and missing error-handling guidance for action runs and proxy requests.

Suggestions

Fix the broken step numbering: the body says 'skip to **Step 2**' twice but no Step 1/Step 2 headings exist — either label the sequence steps explicitly or reword to 'skip to Running actions'.

Make '## Popular actions' earn its title: list 3-5 actual common AlphaSense actions (e.g., search documents, get a note, list dashboards) with example commands, or merge the section into 'Searching for actions' to remove the duplicated command.

Add brief validation for action/proxy execution, e.g., check the `output`/`error` fields of the `--json` response and retry guidance, closing the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands with brief, relevant explanations (e.g., 'membrane connection ensure "https://www.alpha-sense.com/" --json'), but has minor trimmable redundancy: the 'action list' command appears twice ('### Searching for actions' and '## Popular actions') and the bare AlphaSense Overview bullet list adds little. The short platform intro is justified since AlphaSense is niche knowledge.	4 / 5
Actionability	Nearly all guidance is copy-paste-ready CLI commands with concrete examples (install, login, connection ensure, action list/run, proxy flag table), but '## Popular actions' promises specific actions and delivers only the generic discovery command, and placeholders like <actionId>/QUERY are never instantiated. Not fully at the 'specific examples cover the common cases' anchor.	4 / 5
Workflow Clarity	The install → login → connection → poll-until-READY → discover/run sequence is clear and includes explicit checkpoints (state polling, CLIENT_ACTION_REQUIRED handling, CONFIGURATION_ERROR/SETUP_FAILED branches). Minor gaps: the instruction 'skip to Step 2' references a step that is never labeled (numbering jumps to '1b'), and there is no validation/error-handling guidance after running an action or proxy request.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inline, but at ~150 lines with clear sections (Overview, Working with AlphaSense, Best practices) the placement is mostly appropriate. Minor organization gaps: 'Running actions' and 'Proxy requests' are nested confusingly under '## Popular actions', and 'Searching for actions' overlaps with it.	4 / 5
	Total	16 / 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.

The description correctly names the platform, uses third person, and includes an explicit 'Use when' trigger clause, so it answers both what and when and is unlikely to fire for the wrong skill. Its weakness is generic capability language — 'manage data, records, and automate workflows' — that neither enumerates concrete AlphaSense capabilities nor captures the natural vocabulary (market intelligence, expert calls, filings) users would actually use.

Suggestions

Replace the generic action list with concrete AlphaSense capabilities, e.g., 'Search company filings, expert call transcripts, and news; manage notes and dashboards; automate AlphaSense workflows.'

Broaden the trigger clause to natural user phrasing, e.g., 'Use when the user mentions AlphaSense, market intelligence, expert calls, company filings, or earnings research.'

Drop the buzzword 'automate workflows' or ground it in a concrete example (e.g., 'run saved searches on a schedule') so it doesn't read as over-claim.

Dimension	Reasoning	Score
Specificity	'Manage data, records, and automate workflows' names the domain and 2-3 actions, matching the anchor for 1-2 concrete-but-not-comprehensive actions, but the verbs are generic ('manage', 'automate workflows' is a buzzword) and no concrete capabilities like search, documents, notes, or dashboards are stated. It sits above anchor 2 ('actions are minimal or generic', e.g., 'Processes PDF files') only because 'records' gestures at a real AlphaSense object.	3 / 5
Completeness	Both parts are present: the what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with AlphaSense data'). The 'when' is explicit but narrow — it only fires on 'interact with AlphaSense data' — and the 'what' is thin, so it falls short of the concrete-trigger anchor 5.	4 / 5
Trigger Term Quality	'AlphaSense', 'data', and 'records' are relevant keywords and users would naturally say 'AlphaSense', but common variations and synonyms are missing — 'market intelligence', 'expert calls', 'company filings', 'earnings transcripts', 'search documents'. This matches the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'AlphaSense' is a unique brand name giving a clear niche, and the trigger requires AlphaSense, so conflict risk is low. However, the generic 'Manage data, records, and automate workflows' phrasing could weakly overlap with generic data-management or workflow-automation skills, keeping it at 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor.	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/alphasense/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.

alphasense

Table of Contents

Is this your skill?