CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloud-recon

Cloud infrastructure enumeration — AWS S3 buckets, Azure blob storage, GCP buckets, cloud metadata endpoints, IAM misconfigurations, CDN origin detection.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/recon/cloud-recon/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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-structured, highly actionable knowledge base of copy-oriented cloud recon commands with genuinely used reference files and a clear ordered workflow. The main deficiency is the absence of validation/verification feedback loops in the batch enumeration workflow, which caps workflow clarity at 3; secondary issues are comment-only stubs (ECR, origin detection) and slight duplication between inline pattern lists and the naming-patterns reference.

Suggestions

Add explicit verification checkpoints to the Section 8 workflow for batch bucket enumeration — e.g., 're-test any 200/403 bucket with ?acl and ?list-type=2 to confirm public access before reporting; treat 404 as non-existent; back off on rate-limit responses' — which would lift workflow clarity above 3.

Give the comment-only sections (AWS ECR, IMDS/SSRF, origin detection via cert SANs/Shodan) at least one executable example command each, or move them to a reference file if they're meant as pointers.

De-duplicate the inline per-provider naming lists (AWS S3 prefixes, Azure names, GCP names, Azure subdomain patterns) against references/cloud-naming-patterns.md so each pattern lives in exactly one place, tightening conciseness and progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with almost no concept explanation Claude would already know; the only padding is the opening justification ('Modern organizations run hybrid infrastructure — cloud recon is essential...') and some inline naming-pattern lists that duplicate the delegated references/cloud-naming-patterns.md. These are minor trim opportunities, matching the 4 anchor ('efficient; minor instances of over-explanation') rather than the 5 anchor's every-token-earns-its-place.

4 / 5

Actionability

Mostly executable, concrete curl/dig/python3 snippets with a complete AWS IP-range lookup. It stops short of the 5 anchor because commands rely on unresolved placeholders (<target>, <bucket>, <account>) and a few sections are comment-only descriptions with no command (AWS ECR, IMDS/SSRF note, and origin-detection sources like SecurityTrails/Shodan are named but not wired to any executable step).

4 / 5

Workflow Clarity

Section 8 provides a clear, coherent 8-step sequence (detection → storage enum → services → access testing → takeover → origin → registry → document), but validation checkpoints are only implicit. Bucket enumeration loops are batch operations over many candidate names, and the workflow never says how to verify a hit (confirm public listing, re-test anonymous access, handle 403 vs 404 vs rate limiting) before reporting — per the rubric, batch operations without feedback loops cap workflow clarity at 3.

3 / 5

Progressive Disclosure

Two real, one-level-deep reference files are clearly signaled up front ('See references/cloud-ip-ranges.md for the full CNAME → provider mapping table', 'See references/cloud-naming-patterns.md for bucket/resource naming dictionaries'), and the body stays a navigable overview. Minor gaps keep it below 5: the inline Azure subdomain-pattern block, the cloud-service-indicators table, and per-provider naming lists partially duplicate what the reference files already hold, so the split between SKILL.md and references isn't clean.

4 / 5

Total

15

/

20

Passed

Description

66%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, well-scoped cloud-reconnaissance description with strong concrete enumeration targets across AWS, Azure, and GCP. Its main weakness is the absence of an explicit 'Use when...' trigger clause in the description itself, leaving the 'when' half of the equation to a separate metadata field. Trigger-term coverage is good but misses natural synonyms that were relegated to when_to_use metadata.

Suggestions

Append an explicit trigger clause to the description itself, e.g., 'Use when doing cloud recon, checking for exposed S3/Azure/GCP buckets, finding cloud metadata endpoints, or detecting CDN origins' — this would raise completeness from 3.

Fold one or two natural synonyms ('cloud recon', 'bucket discovery') from the metadata.when_to_use field into the description so the trigger terms don't depend on a separate field being surfaced.

Mention the serverless and container-registry coverage (present in the body and tags) in the description to close the specificity gap.

DimensionReasoningScore

Specificity

The description names the domain ('Cloud infrastructure enumeration') and lists concrete, specific targets — 'AWS S3 buckets, Azure blob storage, GCP buckets, cloud metadata endpoints, IAM misconfigurations, CDN origin detection' — covering all three major clouds. It falls short of the 5 anchor because the coverage is one broad action (enumeration/detection) over targets rather than multiple distinct concrete actions, and adjacent capabilities present in the skill (serverless, container registries) are omitted from the description itself.

4 / 5

Completeness

The 'what' is clear and concrete (enumerates cloud storage, metadata endpoints, IAM misconfigurations, CDN origins), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description itself — the trigger guidance lives only in a separate metadata field. Per the rubric guideline, a missing explicit 'when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'S3 buckets', 'Azure blob storage', 'GCP buckets', 'CDN origin', 'cloud metadata endpoints'. Common synonyms a user might type — 'cloud recon', 'bucket discovery', 'cloud enum' — appear only in the metadata.when_to_use field, not in the description, so coverage is good but a few natural variants are missing relative to the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Cloud-specific triggers (S3 buckets, Azure blob, GCP buckets, CDN origin, cloud metadata) form a clear niche unlikely to collide with unrelated skills. Minor overlap risk remains with closely related reconnaissance skills — e.g., 'IAM misconfigurations' could match a dedicated IAM-audit skill, and bucket-takeover checks overlap with subdomain-takeover recon — so it fits the 4 anchor rather than 5.

4 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/recon/cloud-recon/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.