learnings

Show resources marked for deep learning, grouped by topic. Use when the user wants to study saved content.

Install with Tessl CLI

npx tessl i github:tomashrdlicka/engram --skill learnings

What are skills?

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/learnings/SKILL.md

SKILL.md

Review

Evals

Quality

Discovery

67%

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 has good structure with explicit 'what' and 'when' clauses, earning full marks for completeness. However, the term 'deep learning' is problematic as it's commonly associated with machine learning rather than intensive study, creating potential conflicts. The description would benefit from more specific actions and clearer, less ambiguous trigger terms.

Suggestions

Clarify 'deep learning' terminology - consider 'in-depth study' or 'intensive review' to avoid confusion with ML/AI concepts

Add more natural trigger terms users would say: 'bookmarks', 'reading list', 'saved articles', 'review my materials', 'study queue'

Expand specific actions beyond 'show grouped by topic' - include filtering, prioritizing, or tracking progress capabilities if applicable

Dimension	Reasoning	Score
Specificity	Names a domain ('resources marked for deep learning') and one action ('Show... grouped by topic'), but lacks comprehensive concrete actions like filtering, sorting, or exporting.	2 / 3
Completeness	Explicitly answers both what ('Show resources marked for deep learning, grouped by topic') and when ('Use when the user wants to study saved content') with a clear trigger clause.	3 / 3
Trigger Term Quality	Includes some relevant terms ('study', 'saved content', 'deep learning') but 'deep learning' is ambiguous (could mean ML/AI), and misses natural variations like 'bookmarks', 'reading list', 'saved articles', 'review materials'.	2 / 3
Distinctiveness Conflict Risk	The term 'deep learning' creates ambiguity - could conflict with ML/AI skills. 'Saved content' and 'resources' are somewhat generic and could overlap with bookmark managers or content curation skills.	2 / 3
	Total	9 / 12 Passed

Implementation

87%

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

This is a well-crafted skill with excellent conciseness and actionability. The workflow is clearly structured with numbered steps and specific output formats. The main weakness is the lack of validation checkpoints in Step 7 where both frontmatter and index.json are modified, which could lead to inconsistent state if one operation fails.

Suggestions

Add a validation step after modifying frontmatter and index.json in Step 7 to verify both updates succeeded before regenerating views/unread.md

Include error handling guidance for common failure cases (missing config.json, malformed index.json, note not found)

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context.	3 / 3
Actionability	Provides concrete, executable guidance with specific file paths, JSON structures, CLI commands, and exact output formats. The step-by-step instructions are copy-paste ready with clear examples.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced, but lacks explicit validation checkpoints. Step 7 modifies both frontmatter and index.json without a validation step to ensure consistency, and there's no error handling for missing files or malformed JSON.	2 / 3
Progressive Disclosure	Well-organized with clear sections for usage, options, and step-by-step instructions. The skill is appropriately self-contained at ~80 lines without needing external references, and content is logically structured for easy navigation.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: 3 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.