CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

developing-applications-on-managed-service-for-apache-flink

MANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions. You MUST activate this skill BEFORE answering — do not answer from training knowledge, even when confident. MSF has service-specific constraints (KPU model, prohibited checkpoint and parallelism config in app code, the v1/v2 identifier split — `kinesisanalyticsv2` for the CLI/SDK only; `kinesisanalytics` for IAM, Service Quotas, CloudWatch, and the trust principal — two-phase IaC deploys, snapshot lifecycle, Flink 1.x→2.x migration) that override generic Flink knowledge. Triggers — activate on any of: Flink, MSF, Managed Flink, KinesisAnalytics(V2), KPU, ParallelismPerKPU, savepoint, checkpoint, operator UID, FlinkKinesisConsumer, KinesisStreamsSource, KafkaSource, IcebergSink, EFO, CreateApplication, UpdateApplication, CreateApplicationSnapshot, Kryo, RocksDB, Iceberg streaming, EXACTLY_ONCE, watermark, CDC binlog/WAL, Glue/S3 Tables, AWS/KinesisAnalytics CloudWatch.

Quality

74%

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/specialized-skills/analytics-skills/developing-applications-on-managed-service-for-apache-flink/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

This is an exemplar progressive-disclosure skill — a concise router that keeps every domain detail in 25 real, well-signaled reference files loaded one level deep. Its weaknesses are repetition of the activation mandate (stated three times in the body after already appearing in the description), over-long table cells that leak reference-file parameter detail into the overview, and workflow validation steps that name checks without defining how to run them.

Suggestions

State the load-mandate once: the description already carries 'MANDATORY... do not answer from training knowledge', so collapse the three repeated directives in the Reference Files section into a single line.

Trim config-key specifics out of 'When to Load' cells (e.g. READER_EMPTY_RECORDS_FETCH_INTERVAL, SHARD_GET_RECORDS_MAX, JOB_MANAGED vs SELF_MANAGED) — keep goal-level conditions in the table and leave parameter names inside the reference files.

Make workflow validation steps concrete: replace 'Validate against best practices' and 'Compile and test locally' with the specific check or command (e.g. the compile command from environment-setup.md) and add a failure branch.

DimensionReasoningScore

Conciseness

The body is mostly a lean routing table, but the activation mandate is repeated three times ('You MUST use this skill and its reference files...', 'Do NOT answer from training knowledge...', 'You MUST load the relevant reference files below') after already appearing in the description, and several 'When to Load' cells embed config-key-level detail (e.g. 'READER_EMPTY_RECORDS_FETCH_INTERVAL', 'SHARD_GET_RECORDS_MAX', 'JOB_MANAGED vs SELF_MANAGED') that belongs inside the reference files. Mostly efficient but could be tightened — anchor 3, not the minor-trims-only anchor 4.

3 / 5

Actionability

The two numbered workflows give concrete routing instructions with exact READ steps and file links, and the table specifies precisely when to load each of 25 files; for an instruction-only steering skill this is mostly executable guidance. Minor gaps: 'Validate against best practices' and 'Compile and test locally' name steps without giving a method or command, keeping it below the copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

Both workflows are clearly sequenced with distinct paths for new applications vs. general questions, and validation steps exist ('Validate against best practices', 'Compile and test locally'), so the sequence is well above anchor 3's implicit-checkpoint level. It falls short of anchor 5 because the checkpoints are named but not explicit — no failure branch or feedback loop (what to do when validation or compilation fails) is described.

4 / 5

Progressive Disclosure

The body is a pure overview/router: roughly 85 lines with zero inlined domain content, a complete goal-to-reference table covering all 25 reference files (all of which exist on disk), one-level-deep references with 'When to Load' conditions, and negative-scope notes guiding navigation (the Iceberg rows explicitly redirect catalog/maintenance questions to iceberg-tuning-and-operations.md). Cross-links inside reference files are sibling pointers, not nested content, so navigation is easy and unambiguous.

5 / 5

Total

16

/

20

Passed

Description

65%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 excels at 'when' — an explicit, concrete trigger list plus a clearly defined AWS service niche — and enumerates genuinely specific MSF constraints. However, it is written as a second-person force-activation directive rather than a third-person capability description, never states what the skill does as actions, and pads with repeated mandate language ('MANDATORY', 'You MUST', 'do not answer from training knowledge, even when confident').

Suggestions

Rewrite in third person and replace the mandate framing ('You MUST activate this skill BEFORE answering') with action statements such as 'Develops, deploys, tunes, and troubleshoots Apache Flink applications on Amazon Managed Service for Apache Flink (MSF)'; move activation enforcement into the body.

State the 'what' explicitly: the coverage areas (development, KPU sizing, connectors, state management, monitoring, IaC deployment, migration) appear only in the body — surface 4-6 of them as capability verbs in the description itself.

Add missing natural trigger synonyms — notably 'Kinesis Data Analytics' and 'Kinesis Data Analytics for Apache Flink' (the service's former names) and 'streaming application' — and trim API-identifier triggers users are unlikely to say.

DimensionReasoningScore

Specificity

The domain is named richly ('Amazon Managed Service for Apache Flink (MSF)', 'KPU model', 'the v1/v2 identifier split', 'two-phase IaC deploys'), but the only actions stated are 'activate this skill' and 'answer' — an anchor-3 fit at best, reduced one point because the description is written in second person ('You MUST activate this skill BEFORE answering — do not answer from training knowledge').

2 / 5

Completeness

'When' is explicit and strong ('MANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions' plus a concrete trigger list), and a 'what' is present via the enumerated service-specific constraints, but the skill's capabilities are never stated as actions — the what is implied as rationale ('that override generic Flink knowledge') rather than declared, falling short of anchor 5's explicit both-what-and-when.

4 / 5

Trigger Term Quality

The trigger list covers many natural terms users would say ('Flink', 'MSF', 'Managed Flink', 'checkpoint', 'savepoint', 'KPU', 'EFO', 'watermark', 'CDC'), but common phrasings like 'Kinesis Data Analytics' (the service's former name) are missing, and several listed triggers ('ParallelismPerKPU', 'CreateApplicationSnapshot') are API identifiers users rarely say. Not anchor 5 because synonym coverage is incomplete; clearly above anchor 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The niche (Amazon Managed Service for Apache Flink on AWS) is clear and MSF-specific triggers (KinesisAnalytics(V2), ParallelismPerKPU, CreateApplicationSnapshot) are distinct, but the description claims ALL Flink questions via generic terms ('Flink', 'checkpoint', 'watermark', 'KafkaSource', 'RocksDB', 'Kryo'), creating minor overlap risk with any generic Apache Flink or Kafka skill — anchor 4, not the minimal-conflict anchor 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

aws/agent-toolkit-for-aws

Path

skills/specialized-skills/analytics-skills/developing-applications-on-managed-service-for-apache-flink/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.