CtrlK
BlogDocsLog inGet started
Tessl Logo

gcp-cloud-run

When to use: ['Web applications and APIs', 'Need any runtime or library', 'Complex services with multiple endpoints', 'Stateless containerized workloads']

42

Quality

42%

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/AI-Agents-Safe-Coding-Skills/skills/gcp-cloud-run/SKILL.md

The canonical home for this skill is gcp-cloud-run in administrakt0r/AI-Agents-Safe-Coding-Skills

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 useful, code-heavy reference for Cloud Run services, functions and cold-start optimization, but it has malformed code fences, no sequenced deploy workflow with validation, and inlines everything with no progressive disclosure. Fixing the broken fences and adding a verified deploy/run sequence would lift the weaker dimensions.

Suggestions

Fix the malformed code fences (e.g. the ```javascript immediately followed by ```dockerfile blocks at lines 19-20 and 118-119) so examples render and are copy-pasteable.

Add an explicit numbered deploy-and-verify workflow with a validation checkpoint, e.g. build -> push -> deploy -> `gcloud run services describe` / curl the /health endpoint to confirm.

Split the per-pattern detail (Dockerfile, cloudbuild.yaml, function examples) into one-level-deep reference files linked from a concise overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly dense code with terse one-line intros ('Containerized web service on Cloud Run', 'Minimize cold start latency for Cloud Run') and little concept padding, but it carries filler like the final 'When to Use' line ('This skill is applicable to execute the workflow or actions described in the overview') and repeats the When-to-use lists already in the frontmatter, so 'mostly efficient but could be tightened'.

3 / 5

Actionability

It provides copy-paste-ready Dockerfiles, an Express app, cloudbuild.yaml, deploy gcloud commands and lazy-init code covering common cases, which is mostly executable; minor gaps (malformed/nested code fences, undefined getItem, server referenced in the SIGTERM handler before assignment) keep it just below fully executable.

4 / 5

Workflow Clarity

The cloudbuild.yaml implies a build->push->deploy sequence and the Cold Start section uses numbered sub-headings, but there is no explicit ordered deploy workflow with validation checkpoints (e.g. verify the service is healthy after deploy), matching 'steps listed but validation gaps; checkpoints missing'.

3 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and all content is inline in a ~280-line SKILL.md; section headers (Patterns, Anti-Patterns, Sharp Edges) give some structure, but content that could live in separate pattern files is inlined with no one-level-deep references, matching 'some structure but could be better organized'.

3 / 5

Total

13

/

20

Passed

Description

27%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 effectively a trigger list with no statement of what the skill does, and its triggers are too generic to distinguish Cloud Run from other container/serverless deploy skills. It needs an explicit 'what' clause and Cloud Run/GCP-specific trigger terms.

Suggestions

Add a 'what' clause stating the concrete action, e.g. 'Deploy containerized services and event-driven functions to GCP Cloud Run.'

Replace generic triggers with Cloud Run-specific terms users actually say: 'Cloud Run', 'GCP', 'container deploy', 'Cloud Run functions', 'serverless containers'.

Lead with the action and domain before the 'When to use' list, e.g. 'Deploys containerized web services and event-driven functions to GCP Cloud Run. Use when deploying stateless containers, web APIs, or Pub/Sub/Cloud Storage-triggered functions to GCP.'

DimensionReasoningScore

Specificity

The description ("When to use: ['Web applications and APIs', 'Need any runtime or library', 'Complex services with multiple endpoints', 'Stateless containerized workloads']") lists only use-case categories and names no concrete actions the skill performs (e.g. deploy, configure, build), matching the 'Entirely vague; no concrete actions' anchor.

1 / 5

Completeness

Only a 'when' clause is present; the 'what' (what the skill does) is entirely absent, matching the anchor 'only when is present without what'. It does have explicit trigger guidance so it is not a 1.

2 / 5

Trigger Term Quality

Phrases like 'Web applications and APIs' and 'Stateless containerized workloads' are reasonable natural triggers, but it omits the most common terms users would say ('Cloud Run', 'GCP', 'container', 'deploy'), placing it at 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The triggers are deployment-generic ('Web applications and APIs', 'Stateless containerized workloads') and never mention Cloud Run or GCP, creating high overlap with App Engine, GKE, Lambda and other deploy skills, matching 'very broad; high overlap risk'.

2 / 5

Total

8

/

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.

Validation15 / 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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.