CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setting-up-continuum

Guide a developer through connecting a repository to AWS Continuum, granting least-privilege access, creating an environment, learning the real deployment, and observing its automatic first scan.

Quality

77%

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 ./plugins/aws-continuum/skills/setting-up-continuum/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 rigorous, highly actionable AWS setup workflow with excellent sequencing, validation checkpoints, and error-recovery loops. Its weaknesses are redundancy (quota and patch-delivery rules stated multiple times), commands that defer required flags to an out-of-bundle prelude, and cross-skill references that cannot be resolved from the bundle.

Suggestions

State the quota policy once in setup-details.md and reference it from SKILL.md, removing the near-verbatim repetition between safety item 10 and the WAITING_FOR_SCAN handling.

Resolve or inline the missing out-of-bundle references, especially the shared AWS safety prelude that the '...' in every command implicitly depends on.

Move version-pinned host behavior (e.g. 'Codex 0.167') into a reference file or describe it without the version number so the skill body does not go stale.

DimensionReasoningScore

Conciseness

The body is dense and directive with no explanation of concepts Claude already knows, but safety-contract item 10 is a ~300-word paragraph that repeats itself internally (the higher-limit rule is stated twice), the quota remediation trio appears nearly verbatim in both item 10 and the WAITING_FOR_SCAN handling (and again in setup-details.md), and host-version pins like 'Codex 0.167' are time-sensitive details. It fits 'mostly efficient but could be tightened' rather than 2, which requires padded or unnecessary explanation sections.

3 / 5

Actionability

Concrete, executable guidance dominates: real CLI invocations ('aws continuum list-environments --max-results 100 --no-paginate'), exact guards ('--expected-bucket-owner <caller-account>'), a bounded wait loop ('timeout 580 bash -c 'until <read-only-completion-check>; do sleep 30; done''), exact record paths ('<codePrefix>.continuum/uploads/v<N>.json' with status transitions), cadence values ('P1D', 'P7D', 'PT0H'), and a record schema. It stops short of 5 because the discovery commands end in '...' eliding required flags delegated to an external prelude file, and '<read-only-completion-check>' is an unspecified placeholder, so commands are not fully copy-paste ready.

4 / 5

Workflow Clarity

The process is clearly sequenced (safety contract, execution contract, four numbered phases) with explicit end conditions, approval gates, and pervasive validation checkpoints: 'Re-read every created resource and verify ownership and configuration', 'Read back the record', 'verify that exact scan has started', and the quota preflight before any write. Feedback loops are explicit (failed STS call 'stops before writes', bounded-loop re-runs, WAITING_FOR_SCAN failure remediation), matching the anchor for clear sequence with explicit validation and error recovery.

5 / 5

Progressive Disclosure

The two in-bundle references ('references/setup-details.md', 'references/deployment-profile.md') exist and are well-signaled one level deep, but three of the five links point outside the bundle to files not present ('../../references/aws-safety.md', '../reporting-continuum-security/references/packaging.md', '../fixing-continuum-issues/references/local-plan.md') — including the load-bearing safety prelude. Additionally, the quota policy is inlined in SKILL.md and duplicated in setup-details.md, so content that should live in the reference is inline. This fits 'some structure but could be better organized' better than 4, where gaps would be minor.

3 / 5

Total

15

/

20

Passed

Description

75%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 specific, third-person description with concrete actions and a distinct niche. Its main weakness is the missing explicit 'when to use' trigger clause and the absence of common synonyms like 'set up', which limit discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the developer asks to set up, connect, or onboard a repository to AWS Continuum.'

Include common trigger variations such as 'set up Continuum', 'onboard a repo', and 'first scan' phrasing users would naturally say.

Mention the outcome users search for (e.g. 'get Continuum scanning my repository') to strengthen the when-portion.

DimensionReasoningScore

Specificity

The description lists five concrete actions — 'connecting a repository', 'granting least-privilege access', 'creating an environment', 'learning the real deployment', 'observing its automatic first scan' — which comprehensively cover the setup workflow in a named domain. This matches the anchor for multiple specific concrete actions with comprehensive coverage, and is not 4 because coverage of the workflow's phases is complete rather than showing gaps.

5 / 5

Completeness

The 'what' is clear and multi-part, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is only weakly implied by the mention of AWS Continuum, so it does not reach 4.

3 / 5

Trigger Term Quality

Natural phrases a user would say include 'connecting a repository', 'creating an environment', 'least-privilege access', and 'first scan', giving good keyword coverage. It falls short of 5 because common variations such as 'set up', 'onboard', or 'integrate' are missing, but exceeds 3 since several relevant natural terms are present rather than only a few generic keywords.

4 / 5

Distinctiveness Conflict Risk

'AWS Continuum' plus setup-specific actions (connect repository, create environment, observe first scan) carves out a clear niche with distinct triggers and minimal conflict risk with other skills. Even closely related skills (reporting, fixing) target different lifecycle stages, so 4's 'minor overlap risk' understates the separation.

5 / 5

Total

17

/

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

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

aws/agent-toolkit-for-aws

Path

plugins/aws-continuum/skills/setting-up-continuum/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.