CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

amazon-cognito

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/amazon-cognito/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 solid, executable CLI guide with real validation checkpoints in the connection-state machine (poll until READY, branch on CLIENT_ACTION_REQUIRED, check the error field on failure). Its main flaws are padding Claude does not need (the Cognito explainer and term taxonomy), a 'Popular actions' section that substitutes a repeated command for actual examples, and dangling 'Step 2' references that break the otherwise good workflow ordering.

Suggestions

Delete the introductory paragraph explaining what Amazon Cognito is and the 14-item bullet taxonomy — Claude already knows this — and instead list 3-4 actually popular Cognito actions with example commands under 'Popular actions'.

Fix the workflow numbering: either label the sections as explicit numbered steps (1. Install, 2. Authenticate, 3. Connect, ...) and define the referenced 'Step 2', or replace 'skip to Step 2' with the target section's name.

Move detail material (the clientAction schema breakdown and the proxy flags table) into a references/ file linked from SKILL.md so the main file stays a lean overview.

DimensionReasoningScore

Conciseness

Most sections are tight, command-first blocks, but there is unnecessary padding: the opening paragraph explains what Amazon Cognito is ("a service that lets developers add user sign-up, sign-in, and access control..."), a concept Claude already knows, and the 14-item bullet taxonomy of Cognito terms adds no actionable value; the 'Popular actions' section also repeats the action-list command already shown. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') — not 2, because the padding is a minority of the document and the majority of lines are executable commands.

3 / 5

Actionability

The guidance is mostly copy-paste ready: install ("npm install -g @membranehq/cli@latest"), login ("membrane login complete <code>"), connection ("membrane connection ensure ... --json"), action discovery and execution with a JSON input example, and a proxy command with a full flag table. It is not 5 because the 'Popular actions' heading promises specific examples but only restates the discovery command — no actual Cognito action examples (e.g. listing users, managing a user pool) cover the common cases, leaving a minor gap at anchor 4.

4 / 5

Workflow Clarity

The sequence (install → login → connect → poll for readiness → discover actions → run, with proxy as fallback) is present and the connection-state handling is a genuine checkpoint ("If the returned connection has state: READY, skip to Step 2" with explicit READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR branches). However, the body twice directs the reader to 'Step 2' while no Step 1, Step 2, or numbered step structure is ever defined — a broken cross-reference that makes the sequence partially implicit, matching anchor 3 ('sequence present but checkpoints missing or implicit'). It is not 4 because the dangling 'Step 2' references and the unlabeled steps leave real gaps in the defined sequence.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the single ~150-line body mixes quick-start content with material that would fit separate files: the clientAction schema breakdown, the proxy flag table, and the agent-types note. Sections are well-labeled, which gives it structure, but content that should be separate is inline and there is no layering at all, matching anchor 3 ('some structure but could be better organized; content that should be separate is inline'). It is not 4 because the over-50-line document makes no use of one-level-deep references for its detail material.

3 / 5

Total

13

/

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 uses third person and includes an explicit 'Use when' clause anchored to a specific product, which gives it adequate completeness and distinctiveness. Its main weakness is genericness: no Cognito-specific capabilities or natural synonyms (user pool, authentication, tokens) appear, leaving both specificity and trigger coverage thin.

Suggestions

Replace the generic phrase 'Manage data, records, and automate workflows' with Cognito-specific capabilities, e.g. 'Manage users, user pools, identity pools, groups, and tokens'.

Add natural trigger synonyms to the 'Use when' clause, such as 'Use when the user mentions Cognito, user pools, sign-in/authentication, or identity federation'.

Mention 1-2 concrete operations (e.g. 'list and create users', 'configure MFA') so the 'what' is described in concrete action terms.

DimensionReasoningScore

Specificity

The description names the domain ("Amazon Cognito integration") but the actions are generic boilerplate — "Manage data, records, and automate workflows" could describe almost any integration and mentions no Cognito-specific capabilities like user pools, sign-in, authentication, or tokens. It sits between anchor 2 ('names the domain but actions are minimal or generic') and anchor 3; it does not list the 1-2 concrete domain actions anchor 3 requires, so it is not the level above.

2 / 5

Completeness

It has a 'what' ("Amazon Cognito integration. Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with Amazon Cognito data"), matching anchor 4 ('has both what and when; when could be more explicit or specific'). It is not 5 because the 'what' lacks concrete capability phrases (no user pools, authentication, or token management), and the 'when' could name concrete triggers; it is not 3 because the 'Use when' clause is explicit and the domain is clearly stated.

4 / 5

Trigger Term Quality

"Amazon Cognito" and "Cognito data" are natural terms a user would say, but the description misses common variations and synonyms such as 'user pool', 'identity pool', 'authentication', 'sign-in', or 'tokens' that users mention when needing this skill. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms') — not 4, since coverage beyond the product name itself is absent, and not 2, since 'Amazon Cognito' is a specific, natural keyword rather than generic language.

3 / 5

Distinctiveness Conflict Risk

The clear Cognito niche and explicit trigger ("interact with Amazon Cognito data") make it mostly distinct, matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills'). It is not 5 because the generic middle sentence ("Manage data, records, and automate workflows") is identical boilerplate across integration skills and could overlap with generic AWS or data-management skills; it is not 3 because the product-specific trigger term keeps conflict risk minor.

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/amazon-cognito/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.