CtrlK
BlogDocsLog inGet started
Tessl Logo

socket

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

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/socket/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is a strong, executable integration guide with clear sequencing and built-in validation around connection state transitions. Its main weaknesses are minor verbosity, inconsistent CLI invocation style, and a few dangling step references ('Step 2') that break the numbering.

Suggestions

Trim editorial padding (e.g. 'so you can focus on the integration logic rather than auth plumbing') and the marketing-style Socket overview so every sentence is instructional.

Standardize on one invocation form ('membrane' after install, or 'npx @membranehq/cli@latest' throughout) and show how to substitute CONNECTION_ID rather than leaving it as a bare placeholder.

Fix the step numbering: label the connecting section 'Step 1' and define the referenced 'Step 2' (running actions) so 'skip to Step 2' resolves to a real section.

DimensionReasoningScore

Conciseness

The body is mostly efficient with executable commands, but includes unnecessary editorial padding such as 'so you can focus on the integration logic rather than auth plumbing' and a marketing-style opener about what Socket is used for. It fits 'mostly efficient but includes some unnecessary explanation or could be tightened' — above 2 (not heavily padded) but below 4 (several sentences could be trimmed).

3 / 5

Actionability

It provides concrete, copy-paste-ready CLI commands across install, login, connection, action search/run, and proxy with flags and JSON output, matching 'mostly executable guidance; concrete code or commands with minor gaps'. It does not reach 5 because invocation is inconsistent ('membrane' vs 'npx @membranehq/cli@latest') and placeholders like CONNECTION_ID are left unsubstituted without a clear substitution step.

4 / 5

Workflow Clarity

The connect-to-ready flow is well sequenced with validation checkpoints (polling --wait, checking state: READY, handling CLIENT_ACTION_REQUIRED and error states) and a re-poll feedback loop, fitting 'clear sequence with most checkpoints present; minor validation gaps'. It is capped below 5 because the body references 'Step 2' and a '1b' sub-step without a corresponding labeled 'Step 1a'/'Step 2', leaving the sequence numbering incoherent.

4 / 5

Progressive Disclosure

No bundle files exist, so this scores the single-file organization: clear section headers (Overview, Authentication, Connecting, Searching, Popular actions, Best practices) with one level of structure and no nested references, matching 'good structure; most content appropriately placed; minor organization gaps'. It is below 5 because some inline content (the detailed clientAction field breakdown and the proxy options table) could live in a separate reference file.

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.

The description clearly identifies the Socket domain and includes an explicit 'Use when' trigger, giving it solid completeness and distinctiveness. Its weakness is generic, buzzword-leaning action verbs and thin trigger-term coverage that lack synonyms or concrete entity names.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Socket actions such as 'send and read messages, manage contacts and conversations, and transfer files'.

Expand the trigger clause with natural user phrasings and synonyms, e.g. 'Use when the user wants to send Socket messages, look up contacts, or automate Socket workflows'.

Disambiguate from network sockets by referencing the product, e.g. 'Socket (socket.dev) integration' rather than just 'Socket integration'.

DimensionReasoningScore

Specificity

The description names the Socket domain and a few actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is above a 2 because it lists multiple action verbs, but below a 4 because none are specific (e.g., no 'send messages', 'list contacts').

3 / 5

Completeness

It states both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Socket data'), matching the 'has both what and when; when could be more explicit' anchor. It does not reach 5 because the 'when' clause is broad ('interact with Socket data') rather than enumerating concrete trigger phrases.

4 / 5

Trigger Term Quality

It surfaces 'Socket', 'data', 'records', and 'workflows' plus the trigger phrase 'interact with Socket data', giving some relevant keywords, but it misses common variations, synonyms, or entity names a user would naturally say. It is not a 2 (which has only one or two generic keywords) because it pairs the product name with several task nouns, and not a 4 because no synonyms or natural alternates are covered.

3 / 5

Distinctiveness Conflict Risk

Tying the skill to the named Socket platform plus 'interact with Socket data' gives it a mostly distinct niche with minor overlap risk, fitting the 'mostly distinct; minor overlap risk' anchor. It is below 5 because the bare word 'Socket' also denotes network sockets, a generic concept that could cause occasional mis-triggering.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-skills
Reviewed

Table of Contents

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.