CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clyde

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

Quality

67%

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/clyde/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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, concrete CLI guidance with a genuinely well-handled connection state machine (polling, client actions, error states) and a useful proxy escape hatch. Its weaknesses are padding and coherence issues: a speculative intro paragraph, an empty overview section, duplicated action-search content, and a dangling 'Step 2' reference.

Suggestions

Delete the speculative intro paragraph ('likely used by teams... probably offers') and the empty 'Clyde Overview' tree, or replace them with the two or three actual top-level objects (Meeting/Participant/Transcription) plus one example action for each.

Fix the broken step numbering: 'skip to **Step 2**' points to a step that does not exist — either label the 'Searching for actions' section as Step 2 or remove the numbered references.

Merge 'Popular actions' into 'Searching for actions' and populate it with 2-3 real example actions (id + intent + sample run command), which would also close the actionability gap.

DimensionReasoningScore

Conciseness

The bulk of the body is efficient — executable commands, a flags table, and tight state-machine descriptions — but it includes unnecessary padding: the speculative intro ('likely used by teams... It probably offers features like instant messaging'), the empty 'Clyde Overview' tree, and the 'Popular actions' section that duplicates the earlier search instructions. This matches 'Mostly efficient but includes some unnecessary explanation', not anchor 2 since the padding is a minority of the content.

3 / 5

Actionability

Nearly all guidance is executable: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://joinclyde.com/" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input ...', plus a concrete proxy flags table. It misses anchor 5 because the 'Popular actions' section contains no actual example actions or intents, and the proxy section gives flags but no example request.

4 / 5

Workflow Clarity

The install → auth → connect → poll → act sequence is clear with real checkpoints (poll with --wait, handle CLIENT_ACTION_REQUIRED by showing uiUrl and re-polling, check error on CONFIGURATION_ERROR/SETUP_FAILED). It is not a 5 because 'skip to **Step 2**' references a step that is never defined (numbering jumps to '1b'), and there is no validation of action run output before proceeding.

4 / 5

Progressive Disclosure

Sections are present and mostly navigable, but organization could be better: the 'Clyde Overview' section is an empty bullet tree, action-search instructions appear in two separate sections, and 'Popular actions' promises examples but delivers none, matching 'Some structure but could be better organized'. It is below anchor 4 because these gaps exceed 'minor organization gaps'.

3 / 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 has an explicit and well-formed 'Use when' trigger clause anchored to the Clyde product name, which gives it decent completeness and distinctiveness. However, the capability statement is generic ('Manage data, records, and automate workflows') and the trigger vocabulary is thin, relying almost entirely on the 'Clyde' name.

Suggestions

Replace generic verbs with concrete actions, e.g. 'Run Clyde actions for meetings, transcriptions, and participants via the Membrane CLI; search available actions and send direct API requests.'

Broaden trigger terms beyond the product name to include natural phrases and object nouns users would say, such as 'meetings', 'transcriptions', 'participants', and 'Clyde records'.

Tighten the 'when' clause to name concrete triggers rather than repeating 'interact with Clyde data', e.g. 'Use when the user wants to query or update Clyde meetings, transcriptions, or participant records.'

DimensionReasoningScore

Specificity

The description names the domain ('Clyde integration') but the actions are generic — 'Manage data, records, and automate workflows' names no concrete operation, matching the anchor 'Names the domain but actions are minimal or generic'. It falls below anchor 3 because no specific, concrete action is listed.

2 / 5

Completeness

Both 'what' ('Clyde integration. Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Clyde data') are explicitly present. It is not a 5 because the 'what' side is vague and lacks concrete trigger phrases beyond repeating 'Clyde data'.

4 / 5

Trigger Term Quality

'Clyde', 'data', and 'records' are relevant keywords tied to an explicit use condition ('Use when the user wants to interact with Clyde data'), but common variations and natural phrases users might say are missing, matching 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The 'Clyde' product name gives it a clear, distinct trigger, but the generic 'Manage data, records, and automate workflows' phrasing overlaps with broad data-management or database skills, matching 'Mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.

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/clyde/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.