Tessl • The management layer for AI agent skills

SkillPublic

appcues

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

Quality

57%

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/appcues/SKILL.md

Quality

Content

38%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 Membrane CLI operating sections (auth, connection lifecycle, action discovery/run, proxy, best practices) are genuinely useful and executable, but they are buried under a massively duplicated 400-line keyword bullet list that wastes most of the skill's tokens. Destructive actions ship with no validation guidance, and nothing is offloaded to reference files.

Suggestions

Delete the 'Appcues Overview' bullet list entirely (or replace it with a ~10-line list of the actual API objects: flows, flow steps, users, events, accounts, segments, tags, themes, checklists), recovering ~75% of the skill's token budget.

Add validation guidance for destructive actions (delete-user-profile, delete-segment), e.g., confirm the target ID with the user and verify with get-user-profile / list-segments before deleting, and fix the dangling 'Step 2' reference by labeling the numbered workflow steps.

Provide one complete worked example with real values, e.g. `membrane action run update-user-profile --connectionId=<id> --input '{"userId": "u123", "properties": {"plan": "pro"}}' --json`, and move the full action catalog / proxy details to a references/ file if more coverage is needed.

Dimension	Reasoning	Score
Conciseness	The 'Appcues Overview' section is roughly 400 lines of bullet items (GDPR, HIPAA, NFTs, Metaverse, Braille, DevOps, ...), with the entire list duplicated in reverse order after line ~205 — pure padding unrelated to the skill's instructions, dominating the ~540-line body. This matches anchor 1 ('heavily padded'); it is not a 2 because the padding is not a few unnecessary sections but the majority of the document.	1 / 5
Actionability	Concrete, executable commands throughout: `npm install -g @membranehq/cli@latest`, `membrane login --tenant --clientName=<agentType>`, `membrane connection ensure "https://www.appcues.com/" --json`, `membrane action run <actionId> --connectionId=... --input '{"key": "value"}'`, plus a proxy flag table — matching anchor 4 (mostly executable with minor gaps). Not 5 because every example carries unresolved placeholders (CONNECTION_ID, QUERY, <actionId>) and there is no complete end-to-end worked example with real values.	4 / 5
Workflow Clarity	The install → login → connection ensure → poll state → search actions → run sequence is present, and the connection state machine (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) is a genuine feedback loop. However, the skill includes destructive operations ('Delete User Profile ... permanently, including all targeting properties', 'Delete Segment') with no validation or confirmation guidance, which caps workflow clarity at 3; the dangling 'skip to Step 2' reference (no Step 2 is labeled) also blurs the sequence.	3 / 5
Progressive Disclosure	There are no bundle files at all (no references/, scripts/, or assets/), and a ~400-line keyword catalog — content that clearly belongs in a separate reference file or nowhere — is inlined in SKILL.md, matching anchor 2 ('content that clearly belongs in separate files is inlined'). Not 3 because beyond the one dead-weight list there is no reference mechanism or larger structure to organize.	2 / 5
	Total	10 / 20 Passed

Description

61%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 is distinctive and has an explicit 'Use when' clause, but its capability statement is generic ('Manage data, records, and automate workflows') and its trigger vocabulary is limited to the product name alone. It communicates when to fire but poorly conveys what the skill can concretely do.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities, e.g. 'Create, publish, and unpublish flows; track user events; update user and account profiles; manage segments and tags.'

Expand the 'Use when' clause with natural trigger phrases users would actually say: 'Use when the user mentions Appcues, in-app tours, onboarding flows, user segments, or Appcues events and profiles.'

Avoid circular trigger phrasing ('interact with Appcues data') and instead enumerate the objects involved (flows, users, events, accounts, segments, checklists, themes).

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Appcues domain but the actions are generic buzzwords rather than concrete capabilities (e.g., publish flows, track user events, manage segments/profiles), matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because unlike 'Processes PDF files and extracts content' it never states a single concrete action.	2 / 5
Completeness	It has both a 'what' ("Appcues integration. Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with Appcues data"), matching anchor 4 ('when' could be more explicit or specific). Not 5 because the 'when' clause is circular — it restates 'Appcues' without concrete trigger phrases — and the 'what' is vague; not 3 because the 'Use when...' clause is explicitly present.	4 / 5
Trigger Term Quality	"Appcues" is a strong, relevant product-name trigger, but the description offers no other natural terms users would say (flows, product tours, onboarding, segments, events, checklists, NPS). This matches 'Some relevant keywords but missing common variations or synonyms' rather than 4, which requires good multi-term coverage.	3 / 5
Distinctiveness Conflict Risk	"Appcues" is a unique product name giving the description a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5. Not 4 because there is no meaningful overlap risk — no other skill would plausibly claim Appcues-related triggers.	5 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (559 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: membranedev/application-skills
Path: skills/appcues/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.

appcues

Table of Contents

Is this your skill?