CtrlK
BlogDocsLog inGet started
Tessl Logo

timestream-influxdb

Retrieves authoritative guidance on Amazon Timestream for InfluxDB across its supported engine variants. Applicable to any InfluxDB-on-AWS request including engine variant and licensing selection, provisioning and IAM, encryption at rest (AWS-owned and customer-managed KMS keys, key policies, and key lifecycle), schema design (tags vs fields, cardinality, HTTP/sensor/metric data modeling), migration from LiveAnalytics, Processing Engine plugins, connectivity (database endpoints and private or public access), and write/query errors.

67

Quality

81%

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

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.

A well-constructed overview for a complex multi-variant service: it defers detail to real, appropriately-scoped reference files, embeds concrete commands and exact API contracts, and includes genuine validation checkpoints and feedback loops (creation polling, KMS ARN verification, artifact validation). The recurring costs are repetitive verify-before-asserting guard clauses that could be consolidated, meta-directive rather than executable steps in places, and an undiscoverable scripts/ directory.

Suggestions

Add a short section (or inline mentions) documenting the four scripts in `scripts/` (get_token.sh, health_check.sh, input_validator.py, instance_types.py) so that bundle content is discoverable from the overview; also surface s3-vpc-endpoint-troubleshooting.md directly from the Troubleshooting section instead of leaving it two levels deep.

Consolidate the repeated "verify in the documentation / do NOT assert X" guard clauses (roughly ten bullets in section 2) into one global verification rule followed by a short exception list, cutting token cost without losing the contracts.

For the core provisioning path, either inline the minimal executable command sequence (create → poll → verify) as a numbered checklist, or state explicitly in which order to load which reference file for the most common request (new V3 workload), so the workflow reads as one sequence rather than a topic catalog.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — it never explains what InfluxDB or time-series data is, and tags/fields guidance is stated as contract ("**Tags** (indexed, used in WHERE/GROUP BY): **MUST** be low-cardinality like `method`, `region`, `status_code`") rather than tutorial prose. However, the "verify-before-asserting / do NOT say X" guard pattern is repeated across roughly ten bullets (e.g. "Before asserting S3 log-delivery availability... verify the create and update API request parameters", "Do NOT invent CloudWatch metric names", "Do NOT say the service is exclusively VPC-only"), which could be condensed into a single global rule plus exceptions. That matches anchor 4 — efficient with minor instances that could be trimmed — rather than anchor 5's "every token earns its place".

4 / 5

Actionability

Concrete, executable material is present: `aws timestream-influxdb list-db-instances --region us-east-1`, a copy-paste tag example (`--tags Key=created_by,Value=timestream-skill Key=generation_model,Value={your-model-id}`), exact parameter values (`InfluxDBV3Core` parameter group, port 8181, `Authorization: Bearer <token>` vs `Authorization: Token <token>`), and a 4-step decision flow. The gaps keeping it below anchor 5: much of the guidance is meta-directive ("verify in the Timestream for InfluxDB documentation", "inspect the Create API model") rather than executable steps, and the actual provisioning/token commands live in the referenced files rather than inline. It is clearly above anchor 3 because what is inline is specific and executable, not pseudocode.

4 / 5

Workflow Clarity

Tasks are sequenced (1. Verify Dependencies → 2. Select variant → 3. Schema → 4. Migrate → 5. Plugins → 6. Monitor) with explicit validation checkpoints and feedback loops: "poll `get-db-cluster` until it reports `AVAILABLE` or a terminal failure. Do not report creation complete... while the cluster remains `CREATING`", the kmsKeyId ARN re-check "MUST be checked again at `AVAILABLE`", and a 5-step handoff protocol with "Validate it against... schema.json. If malformed or unreadable, tell the user and proceed without it." This satisfies anchor 4 (clear sequence, most checkpoints, feedback loops). It falls short of anchor 5 because the sections read partly as a topic catalog — the interleaving of Common Tasks, Troubleshooting, Security, and Handoff for a given request is implicit, and several sequences (e.g. the full creation procedure, triage steps) are deferred to reference files rather than fully spelled out with error-recovery loops in the body.

4 / 5

Progressive Disclosure

Scored against the actual bundle: the body is a clear overview with well-signaled, load-bearing references — every section instructs "Load [X](references/x.md)" (e.g. "load the [schema-design guide](references/schema-design-guide.md)", "You MUST load and follow [security best practices](references/security-best-practices.md) for every deployment"), and all nine cited files exist. References are effectively one level deep (reference files cross-link siblings like encryption.md and getting-started.md, but primary content is not buried). Two organization gaps keep it at anchor 4 rather than 5: the `scripts/` bundle (get_token.sh, health_check.sh, input_validator.py, instance_types.py) is never mentioned anywhere in the body, making it undiscoverable; and s3-vpc-endpoint-troubleshooting.md is reachable only through a second-level link inside troubleshooting-runbook.md rather than from the overview.

4 / 5

Total

16

/

20

Passed

Description

87%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.

A strong description: it states a clear action, scopes it to a specific AWS service, and provides an explicit applicability clause enumerating concrete trigger scenarios. The main weaknesses are that the primary verb is a single generic action ("retrieves authoritative guidance") supported by a topic catalog rather than distinct action verbs, and a few high-frequency user synonyms ("time series", "Flux", "InfluxQL") are missing.

Suggestions

Add the natural user phrases "time-series database", "Flux", and "InfluxQL" to the trigger list — these are among the most common words InfluxDB users say and would round out trigger coverage.

Consider replacing some topic-catalog phrasing with distinct action verbs (e.g. "selects engine variants, provisions instances and clusters, designs schemas, migrates from LiveAnalytics") to make the capability list read as concrete actions.

DimensionReasoningScore

Specificity

Quotes: "Retrieves authoritative guidance on Amazon Timestream for InfluxDB" plus a concrete enumeration — "engine variant and licensing selection, provisioning and IAM, encryption at rest (AWS-owned and customer-managed KMS keys, key policies, and key lifecycle), schema design (tags vs fields, cardinality...), migration from LiveAnalytics, Processing Engine plugins, connectivity... and write/query errors." This lists several specific capability areas with minor gaps, matching anchor 4. It is not a 5 because the only true action verb is "retrieves guidance" — the remainder is a topic catalog rather than multiple distinct concrete actions (contrast the anchor-5 example's four distinct verbs: extract, fill, merge, convert). It is above anchor 3 because coverage goes well beyond 1-2 actions and is comprehensive in topic scope.

4 / 5

Completeness

What: "Retrieves authoritative guidance on Amazon Timestream for InfluxDB across its supported engine variants" — a clear statement of what the skill does. When: "Applicable to any InfluxDB-on-AWS request including [concrete list]" — an explicit trigger clause equivalent to "Use when...", with concrete trigger phrases (variant selection, provisioning, encryption, schema design, migration, plugins, connectivity, errors). Both halves are explicit and concrete, matching anchor 5. Not anchor 4, because the "when" clause is not merely present but enumerates the specific request types that should activate the skill.

5 / 5

Trigger Term Quality

Quotes: "any InfluxDB-on-AWS request", "migration from LiveAnalytics", "Processing Engine plugins", "KMS keys", "tags vs fields", "cardinality", "write/query errors", "private or public access" — these are phrases users would naturally say when they need this skill. Anchor 4 fits: good keyword coverage with a few natural terms missing — notably "time series" / "time-series database", "Flux", and "InfluxQL", which are among the most common words InfluxDB users actually say. Not anchor 5 because those high-frequency synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Quotes: "Amazon Timestream for InfluxDB", "its supported engine variants", "any InfluxDB-on-AWS request", "migration from LiveAnalytics" — a clear niche with distinct triggers and minimal conflict risk, matching anchor 5. The only conceivable overlap is with a generic InfluxDB (self-managed/cloud) skill, but the explicit AWS scoping and Timestream-specific terms (LiveAnalytics, DbInstance/cluster concepts) keep that risk minimal.

5 / 5

Total

18

/

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
aws/agent-toolkit-for-aws
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.