CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/knowledge-ops/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

38%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 skill provides a clear conceptual architecture and a high-level ingestion sequence, but it stays abstract and verbose without concrete executable guidance, validation checkpoints, or progressive disclosure into reference files.

Suggestions

Add concrete, executable examples for the most common operations — e.g., exact mcp__memory__ tool call signatures, a real memory-file frontmatter template, and a sample Git commit/redaction command.

Insert explicit validation checkpoints in the Ingestion and Sync workflows (e.g., verify dedup before write, confirm redaction before committing) with retry-on-failure feedback loops.

Move the layer architecture and sync-operation details into separate reference files (e.g., ARCHITECTURE.md, SYNC.md) and keep SKILL.md as a concise overview with one-level-deep, clearly signaled links.

DimensionReasoningScore

Conciseness

The body is well-organized but runs ~150 lines with repeated guidance (e.g., layer rules restated across Ingestion, Sync, and Best Practices) that assumes little of Claude's competence; it could be tightened without losing clarity.

3 / 5

Actionability

Guidance is largely abstract (e.g., 'Use mcp__memory__create_entities for permanent structured data') with only a generic non-executable code block; it lacks concrete copy-paste commands, file paths beyond the memory dir, or worked examples for common operations.

2 / 5

Workflow Clarity

A sequenced Ingestion Workflow (Classify -> Deduplicate -> Store -> Index) is present, but it lacks explicit validation checkpoints or feedback loops for destructive/batch operations like dedup or Git commits, which the rubric caps at 3.

3 / 5

Progressive Disclosure

No bundle files exist and the body inlines what would naturally be separate references (full layer architecture, sync procedures, memory patterns) under one file with no signaled one-level-deep references, leaving it monolithic.

2 / 5

Total

10

/

20

Passed

Description

96%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 strong and well-structured, clearly stating capabilities, storage layers, and explicit user-facing trigger phrases. Its only weakness is slight breadth that creates minor overlap with generic memory/file skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the knowledge lifecycle — 'save, organize, sync, deduplicate, or search' — mapped to specific storage layers (local files, MCP memory, vector stores, Git repos), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (knowledge base management across multiple stores) and 'when' with a concrete 'Use when...' clause listing trigger conditions.

5 / 5

Trigger Term Quality

Includes natural user phrases such as 'save this to KB', 'sync knowledge', 'what do I know about X', and 'ingest this', covering common synonyms for triggering the skill.

5 / 5

Distinctiveness Conflict Risk

The multi-layer knowledge-management niche is fairly distinct, but the broad 'save/organize/search' framing has some overlap with generic memory or file-management skills, leaving minor conflict risk.

4 / 5

Total

19

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.