CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apideck

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

Quality

72%

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/apideck/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body delivers strongly actionable, well-structured CLI guidance with good connection-state feedback loops. Its weaknesses are consistency details: a dangling 'Step 2' reference, mixed membrane/npx invocations, and a 'Popular actions' section that promises but lacks named actions.

Suggestions

Fix the dangling workflow references: label the steps explicitly (e.g., '### Step 2: Discover actions') or remove the 'skip to Step 2' mentions, and unify CLI invocation to one form ('membrane' vs 'npx @membranehq/cli').

Populate 'Popular actions' with 2-3 concrete examples (action id, intent query, and a sample --input payload) or remove the section, since it currently duplicates the discovery command from 'Searching for actions'.

Trim the marketing-flavored intro ('saving time and resources') and the filler line 'Use action names and parameters as needed.' to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is dominated by lean, command-driven sections, but the marketing intro ('saving time and resources'), the filler line 'Use action names and parameters as needed.', and a duplicated action-discovery command between 'Searching for actions' and 'Popular actions' could be trimmed. This matches anchor 4 ('minor instances of over-explanation') rather than 5, where every token would earn its place.

4 / 5

Actionability

Concrete, copy-paste-ready CLI commands cover install, login, connection setup, action discovery/execution, and proxy requests, plus a clear options table. It stops short of anchor 5 because 'Popular actions' never names an actual action or example intent, leaving the common cases without specific examples.

4 / 5

Workflow Clarity

The sequence (install, login, connection ensure, poll state, discover, run, proxy fallback) is clear with strong state-handling checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED with re-poll instructions). It misses anchor 5 due to broken sequencing details: 'skip to Step 2' references a step that is never labeled, and CLI invocation is inconsistent between 'membrane' and 'npx @membranehq/cli'.

4 / 5

Progressive Disclosure

This is a single-file skill with no bundle files, and the body is organized into clear, appropriately sized sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices). Minor gaps — the redundant 'Popular actions' section and the module-overview tree that duplicates discovery output — keep it at anchor 4 rather than 5.

4 / 5

Total

16

/

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 includes an explicit 'Use when...' clause and leverages a distinctive product name, but its capability statement is generic. Replacing buzzword actions with concrete Apideck operations would lift specificity and trigger coverage.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities, e.g., 'List and sync invoices, CRM contacts, companies, opportunities, products, orders, and files across SaaS apps via Apideck's unified API'.

Broaden trigger coverage with natural variations users would say, such as 'Use when the user mentions Apideck, unified APIs, or cross-app SaaS data (accounting, CRM, e-commerce, files)'.

Tighten the 'when' clause to name the concrete scenarios (syncing records, pulling invoices, managing connections) instead of the vague 'interact with Apideck data'.

DimensionReasoningScore

Specificity

"Manage data, records, and automate workflows" names the Apideck domain but the actions are generic buzzwords with no concrete operations (e.g., no 'sync invoices' or 'list CRM contacts'). It matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires at least one genuinely concrete action.

2 / 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 Apideck data"). It falls short of anchor 5 because neither the what nor the when includes concrete trigger phrases or specific capabilities.

4 / 5

Trigger Term Quality

"Apideck" is the key natural trigger term and "data"/"records" add some relevance, but the description misses common variations and synonyms such as "unified API", "cross-app", or "SaaS integrations". This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') rather than 4, which expects broader natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

The product name "Apideck" carves out a clear niche with distinct triggers, but the broad phrasing "Manage data, records, and automate workflows" creates minor overlap risk with generic data-management and automation skills. This sits at anchor 4 rather than 5, where triggers would be uniformly distinct.

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/apideck/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.