supplychain-overview

Supply-chain attack category — dependency confusion, typosquatting, package-registry abuse, build-pipeline poisoning, SBOM manipulation.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

93%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 tight, well-organized routing overview with executable discovery commands and strong safety guardrails. Its only gap is that, being a routing skill, it lacks an explicit multi-step validation workflow, keeping workflow_clarity just below the top anchor.

Suggestions

Add a short numbered 'Discovery -> Confirm scope -> Route to sub-skill' sequence to make the routing workflow's checkpoints explicit.

Make the cross-references (dep-confusion sub-skill, /skills/shared/opsec/SKILL.md) into clear one-level-deep links with a brief 'what you'll find there' note to aid navigation.

State explicitly how to choose between the dep-confusion sub-skill and the CI/build-pipeline path so Claude routes correctly when both apply.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what supply-chain attacks are and every section (Sub-Skills, Surface Discovery, Decision Notes) earns its tokens.	5 / 5
Actionability	Surface Discovery provides copy-paste-ready, executable grep commands covering package-lock/yarn/pnpm, requirements.txt, go.mod, and pom.xml, addressing the common discovery cases.	5 / 5
Workflow Clarity	The Decision Notes give clear safety guardrails (confirm scope authorization, beacon-only payloads) and the discovery action is unambiguous, but it is a routing skill without an explicit validate->fix->retry sequence, so it sits just below the 5 anchor.	4 / 5
Progressive Disclosure	This is a sub-50-line skill with no external references needed; it is well-organized into clearly labeled sections, which per the rubric merits a 5 for progressive disclosure.	5 / 5
	Total	19 / 20 Passed

Description

67%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 specific and distinctive, but it reads as a category enumeration rather than a trigger-friendly skill description: it lacks a 'Use when...' clause and favors jargon over natural user phrasing. Moving the rich trigger terms from metadata.when_to_use into the description itself would raise both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete user scenarios (e.g. 'Use when researching supply-chain attacks: dependency confusion, typosquatting, or registry abuse against npm/PyPI/RubyGems/Cargo').

Surface natural trigger terms (npm, pypi, rubygems, cargo, github actions, CI) into the description itself rather than only in metadata.when_to_use so users' phrasing matches the description.

State the routing purpose in the description so Claude knows it selects a sub-skill rather than executing an attack.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete techniques ('dependency confusion, typosquatting, package-registry abuse, build-pipeline poisoning, SBOM manipulation'), giving comprehensive coverage of the supply-chain attack domain.	5 / 5
Completeness	The 'what' is clearly stated via the enumerated attack categories, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It includes relevant domain keywords but leans on technical jargon ('package-registry abuse', 'SBOM manipulation') rather than the natural phrases users say (e.g. 'npm', 'pypi', 'supply chain'), which only appear in metadata.when_to_use.	3 / 5
Distinctiveness Conflict Risk	The supply-chain attack niche is sharply scoped with distinct, narrow triggers, making it unlikely to fire for unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/exploit/supplychain/SKILL.md
Commit: 0cf691e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.