CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clay

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

Quality

66%

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/clay/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 delivers strong executable guidance for the Membrane CLI workflow — auth, connection lifecycle with explicit state handling, action discovery/run, and proxy fallback — with a clear options table. Its weaknesses are filler (a malformed Clay overview and a duplicated command section), a broken 'Step 2' cross-reference that disrupts workflow sequencing, and a 'Popular actions' section that contains no actual actions.

Suggestions

Fix the dangling 'skip to Step 2' reference — either label the section it points to (Searching/Running actions) as Step 2 or remove the reference; also rename '1b' to match a labeled '1a'

Delete or make substantive the 'Clay Overview' bullet list ('People / Enrichment / Companies / Enrichment' with 'Use action names and parameters as needed') and the intro sentence explaining what Clay is

Merge the duplicated `membrane action list` guidance and either populate 'Popular actions' with 3-5 example action names/intents or fold it into 'Searching for actions'

DimensionReasoningScore

Conciseness

Mostly efficient command-first writing, but it includes unnecessary content: a malformed filler overview ('People / Enrichment / Companies / Enrichment', 'Use action names and parameters as needed'), an intro paragraph explaining what Clay is, and the `action list` command duplicated in both 'Searching for actions' and 'Popular actions'. Fits anchor 3 ('Mostly efficient but includes some unnecessary explanation or could be tightened'); not 4 because several sections need trimming.

3 / 5

Actionability

Concrete executable commands throughout: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://www.clay.com/" --json', 'membrane action run <actionId> --input \'{"key": "value"}\'' plus a full proxy flag table. Fits anchor 4 ('Mostly executable guidance'); not 5 because 'Popular actions' promises actions but delivers only a discovery command with no example action ids or intents.

4 / 5

Workflow Clarity

The install → login → connect → discover → run sequence exists with good state-based checkpoints (poll until READY, handle CLIENT_ACTION_REQUIRED, check error field), but 'If the returned connection has state: "READY", skip to Step 2' references a Step 2 that never exists, and section '1b' has no labeled '1a'. Fits anchor 3 ('Steps listed but validation gaps; sequence present but checkpoints missing or implicit') — the broken cross-reference makes the primary workflow's transitions incoherent; not 4 because the gaps go beyond minor.

3 / 5

Progressive Disclosure

No bundle files exist and the single-file body is organized into clearly labeled sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with no nested references. Fits anchor 4 ('Good structure; most content is appropriately placed; minor organization gaps') — the empty 'Clay Overview' section and duplicated action-listing sections are minor gaps; not 5 because the body exceeds the simple-skill threshold and its structure is imperfect.

4 / 5

Total

14

/

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 correctly names the Clay domain and includes an explicit 'Use when...' trigger clause, avoiding the worst failure modes. However, its capability list is generic ('manage data, records, automate workflows') and it misses Clay-specific vocabulary like people, companies, contacts, and enrichment, limiting both specificity and trigger coverage.

Suggestions

Name concrete Clay capabilities, e.g. 'Manage people and company records, run enrichment, and automate Clay workflows'

Add natural trigger variations users would actually say: contacts, networking, CRM, enrichment, Clay tables

Broaden the 'when' clause, e.g. 'Use when the user mentions Clay, wants to enrich contacts, or manage relationship data'

DimensionReasoningScore

Specificity

The description names the domain ("Clay integration") but the actions — "Manage data, records, and automate workflows" — are generic with no Clay-specific concrete capabilities (people, companies, contacts, enrichment). It matches anchor 2 ('Names the domain but actions are minimal or generic') rather than 3, which would require 1-2 genuinely concrete actions.

2 / 5

Completeness

Both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Clay data") are present, matching anchor 4. Not 5 because the trigger is a single generic phrase rather than concrete comprehensive triggers, and the 'what' is vague.

4 / 5

Trigger Term Quality

"Clay", "data", "records", and "workflows" give some relevant keywords, but common natural variations users would say are missing (contacts, people, companies, networking, CRM, enrichment). Fits anchor 3 ('Some relevant keywords but missing common variations or synonyms'); not 4 because coverage is thin beyond the app name.

3 / 5

Distinctiveness Conflict Risk

"Clay integration" and "interact with Clay data" name a specific app with distinct triggers, giving minimal conflict risk — anchor 4. Not 5 because the generic 'manage data / automate workflows' phrasing could overlap with other data-automation skills.

4 / 5

Total

13

/

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.

Validation — 15 / 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

Path

skills/clay/SKILL.md

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.