capture

Capture a web link, summarize it, and save to Obsidian vault. Use when the user wants to save a URL to their knowledge base.

Install with Tessl CLI

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

What are skills?

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

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

SKILL.md

Review

Evals

Quality

Discovery

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is functional with a clear 'Use when' clause and distinct purpose targeting Obsidian users. However, it could benefit from more specific action details and additional trigger terms that users might naturally say when wanting to save web content.

Suggestions

Add more natural trigger terms to the 'Use when' clause such as 'bookmark', 'save article', 'clip webpage', or 'save link'

Expand specificity by detailing what 'capture' includes (e.g., 'extracts title, content, and metadata') and what format the summary takes

Dimension	Reasoning	Score
Specificity	Names the domain (web links, Obsidian) and some actions (capture, summarize, save), but lacks comprehensive detail about what 'capture' entails or what format the summary takes.	2 / 3
Completeness	Clearly answers both what (capture, summarize, save to Obsidian) and when (user wants to save a URL to their knowledge base) with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes 'URL' and 'knowledge base' as natural terms, but misses common variations like 'bookmark', 'article', 'webpage', 'link', 'clip', or 'Obsidian' in the trigger clause.	2 / 3
Distinctiveness Conflict Risk	The combination of web links + summarization + Obsidian vault creates a clear niche that is unlikely to conflict with generic note-taking or web scraping skills.	3 / 3
	Total	10 / 12 Passed

Implementation

77%

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-structured, highly actionable skill with excellent workflow clarity and concrete examples throughout. The main weakness is that it's a monolithic document that could benefit from splitting detailed reference material (type classification rules, view generation specs, template structures) into separate files. Some verbosity in explanations could be trimmed.

Suggestions

Extract type classification rules and topic categories into a separate reference file (e.g., `TYPES.md`) and link to it from the main skill

Move view generation specifications (Step 11) to a separate `VIEWS.md` file since they're detailed implementation specs

Consolidate the intent detection logic (Step 5 and auto-detection fallback) into a single, more concise section

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some redundancy (e.g., explaining intent detection twice with auto-detection fallback, verbose step descriptions). Some sections could be tightened without losing clarity.	2 / 3
Actionability	Provides concrete, executable guidance throughout: specific file paths, JSON structures, exact command formats, wiki-link syntax examples, and clear bash commands for git sync. Copy-paste ready.	3 / 3
Workflow Clarity	Excellent multi-step workflow with 12 clearly numbered steps, explicit validation points (Step 7b for connections, Step 9 for index updates), and error handling section. Includes feedback loops for failed fetches.	3 / 3
Progressive Disclosure	All content is inline in a single file despite being 200+ lines. Templates, view generation logic, and type/topic classification rules could be split into referenced files. The skill mentions external files (templates, CLAUDE.md) but doesn't leverage them for content organization.	2 / 3
	Total	10 / 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.