recsys-pipeline-architect

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The content is well-organized and mostly actionable with a clear eight-step workflow and hard rules, but it is undermined by claiming bundled reference docs and runnable scaffolds that are not actually present alongside the SKILL.md.

Suggestions

Bundle the referenced reference docs (interfaces, scoring/isolation patterns, filter/scorer cookbooks) and runnable scaffolds locally under references/ and scripts/ so the load-on-demand claims are real, or reword 'Upstream contents' to clearly mark these as external-only.

Inline at least one minimal runnable scaffold snippet in the body so the actionability and hard-rule-5 ('the generated scaffold must run') claims are met without leaving the skill.

Add an explicit verification checkpoint to the workflow (e.g., 'run the generated scaffold's test suite; regenerate if a test fails') to close the workflow_clarity gap.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, but the 'Upstream contents' section reads as promotional and the trade-off and anti-pattern sections overlap, adding minor padding.	4 / 5
Actionability	It gives a concrete 8-step workflow and explicit hard rules, but no runnable scaffold code is inlined (the runnable scaffolds live only in the external upstream repo), leaving a notable execution gap despite hard rule 5 requiring runnable scaffolds.	4 / 5
Workflow Clarity	The eight steps are clearly sequenced with rationale, but there are no explicit validation or verification checkpoints for the generated scaffold, which is a minor gap for a generation workflow.	4 / 5
Progressive Disclosure	Section structure is good and the body claims load-on-demand reference docs and runnable scaffolds, but no bundle files (references/, scripts/, assets/) exist locally — the references point to an external GitHub repo rather than bundled one-level-deep files.	3 / 5
	Total	15 / 20 Passed

Description

100%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 strong, well-targeted description that concisely states what the skill does, when to use it, and the concrete trigger scenarios. It hits all four rubric dimensions cleanly with no vague fluff.

Dimension	Reasoning	Score
Specificity	The description names the domain and multiple concrete actions, plus the exact six-stage framework (Source→Hydrator→Filter→Scorer→Selector→SideEffect), giving comprehensive coverage of capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (design composable recsys/ranking/feed pipelines via the six-stage framework) and 'when' ('Use this skill whenever the user is building any system that picks the top K items...').	5 / 5
Trigger Term Quality	It enumerates natural trigger phrasing across many domains — 'social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking' — covering synonyms and natural terms a user would say.	5 / 5
Distinctiveness Conflict Risk	The niche is clear (top-K pipeline plumbing around a scorer), with distinct triggers that are unlikely to fire for unrelated skills, keeping conflict risk minimal.	5 / 5
	Total	20 / 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: affaan-m/ECC
Path: skills/recsys-pipeline-architect/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.