knowledge-ops

Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is tdg-personal/knowledge-ops

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and actionable with concrete tool names and paths, but it carries redundancy (a restated Memory Patterns section and repeated rules) and lacks an explicit error-recovery feedback loop for batch git syncs. As a longer single-file skill it would also benefit from splitting detailed reference material into separate files.

Suggestions

Remove or consolidate the 'Memory Patterns' section, which restates the layer architecture, and de-duplicate the repeated 'do not treat the KB/archive as a live workspace' rule to tighten conciseness.

Add an explicit validate->fix->retry feedback loop for batch git sync operations (e.g. 'if a commit fails or unredacted sensitive data is detected, abort, redact, and re-commit before pushing').

Split the detailed per-layer specifications and sync-operation steps into one-level-deep reference files (e.g. LAYERS.md, SYNC.md) and link them from a leaner SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic concept explanations, but the 'Memory Patterns' block restates the layer architecture and the 'do not treat the KB as a live workspace' rule is repeated across sections (e.g. lines 16, 103, 57), so it could be tightened.	2 / 3
Actionability	Gives concrete, executable guidance for an instruction skill: exact MCP tool names (create_entities, create_relations, search_nodes), concrete paths (~/.claude/projects/*/memory/), and explicit per-type storage targets in the Classify step.	3 / 3
Workflow Clarity	The Ingestion Workflow is clearly sequenced (Classify, Deduplicate, Store, Index) and a Quality Gate checklist exists, but batch/destructive git sync operations lack an explicit validate->fix->retry feedback loop, capping the score at 2 per the rubric's destructive-operations note.	2 / 3
Progressive Disclosure	Content is well-organized into clear sections but everything is inline in one ~150-line SKILL.md with no bundle files; the detailed per-layer specs and sync-operation details could be split into one-level-deep reference files for a skill this size.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 description: it states concrete capabilities, lists specific storage layers, and provides an explicit 'Use when' trigger clause with natural user-facing verbs. It is concise without padding and clearly differentiated.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'management, ingestion, sync, and retrieval' — across enumerated storage layers (local files, MCP memory, vector stores, Git repos), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (manage/ingest/sync/retrieve across storage layers) and 'when' via a clear 'Use when the user wants to...' trigger clause.	3 / 3
Trigger Term Quality	The 'Use when' clause covers natural user phrasings — 'save, organize, sync, deduplicate, or search across their knowledge systems' — terms a user would plausibly say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The multi-layer knowledge-ops niche with named stores (MCP memory, vector stores, Git repos) and sync/dedup triggers is a clear, distinct scope unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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/knowledge-ops/SKILL.md
Commit: 754b8dd

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.