discovery

Capture interesting finds to the Vault via Inngest. Triggers when the user shares a URL, repo, or idea with signal words like "interesting", "cool", "neat", "check this out", "look at this", "came across", or when sharing content with minimal context that implies it should be remembered. Also triggers on bare URL drops with no explicit ask. Fires a discovery/noted event and continues the conversation — the pipeline handles everything else.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/discovery/SKILL.md

Quality

Content

57%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.

Actionable and well-supplied with concrete commands, but the body is weakened by a section-numbering bug that muddies the workflow and by inlined background material that would benefit from separate reference files.

Suggestions

Fix the duplicate workflow numbering: 'Compatibility shortcut' is labeled `### 3` while 'Assess for Monitoring' reuses `### 2`, and 'Continue conversation' reuses `### 3` — renumber the Workflow steps sequentially.

Move the background detail blocks ('What the Pipeline Does', 'Deep Dig — Inngest Enrichment Pipeline', 'X/Twitter URL Enrichment', 'Video/Media Handling') into reference files under ./references/ and link to them from SKILL.md to improve progressive disclosure.

Dedupe the overlap between 'What the Pipeline Does' and the 'Deep Dig' enrichment steps so the pipeline behavior is described once.

Dimension	Reasoning	Score
Conciseness	Mostly lean operational detail that assumes Claude's competence, but "What the Pipeline Does" and "Deep Dig — Inngest Enrichment Pipeline" overlap, and the body carries some redundancy that could be tightened.	3 / 5
Actionability	Provides concrete, executable commands (`joelclaw send discovery/noted --data '...' --follow`, `joelclaw discover … --site … --visibility …`) and a real Twitter API call, with only placeholder gaps in a few examples.	4 / 5
Workflow Clarity	Steps are sequenced with a useful monitoring decision-tree checkpoint, but duplicate section numbering (two `### 2` and two `### 3` headings) breaks the intended sequence and makes the workflow order ambiguous.	3 / 5
Progressive Disclosure	Clear section headers give decent structure, but no bundle reference files exist and substantial background sections (Deep Dig, X/Twitter enrichment, Video handling) are inlined in SKILL.md rather than split into one-level-deep references.	3 / 5
	Total	13 / 20 Passed

Description

91%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, trigger-rich description that clearly states both capability and activation conditions with natural user phrasing. It is mostly distinct, with only minor overlap risk from its broad bare-URL trigger.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Capture interesting finds to the Vault via Inngest", "Fires a discovery/noted event", "continues the conversation") with minor gaps, though "capture interesting finds" is somewhat abstract and "pipeline handles everything else" defers rather than specifies.	4 / 5
Completeness	Explicitly answers both what (capture finds to the Vault, fire discovery/noted event) and when ("Triggers when the user shares a URL, repo, or idea…", "Also triggers on bare URL drops with no explicit ask") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases a user would actually say — "interesting", "cool", "neat", "check this out", "look at this", "came across" — including synonyms and the bare-URL-drop pattern.	5 / 5
Distinctiveness Conflict Risk	The Vault/Inngest/discovery framing is a clear niche, but "bare URL drops with no explicit ask" and "sharing content with minimal context" are broad enough to create minor overlap risk with a generic bookmark/save skill.	4 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/discovery/SKILL.md
Commit: 7094ced

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.