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

82%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

64%

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

This is a functional skill with strong actionability — concrete commands, clear trigger patterns, and specific defaults make it easy for Claude to execute. However, it's moderately verbose with background pipeline details that don't affect agent behavior, has a numbering error in the workflow steps, and inlines reference material (tracked projects, pipeline internals) that would be better in supporting files. Tightening the content to focus on agent-actionable steps would significantly improve it.

Suggestions

Fix the duplicate step numbering (two '### 2' and two '### 3' sections) to create a clear, unambiguous sequence.

Move 'What the Pipeline Does' and 'Deep Dig' background sections into a separate reference file (e.g., PIPELINE.md) since the agent's job is explicitly just to fire the event.

Add a brief error/failure handling note for when `joelclaw send` or `joelclaw discover` fails — what should the agent do or tell Joel?

Dimension	Reasoning	Score
Conciseness	The skill contains useful operational detail but is verbose in places — the 'What the Pipeline Does' section explains background internals that the agent doesn't need to act on, the Deep Dig section repeats that enrichment is automatic, and the tracked projects list is configuration data that could live in a reference file. Some sections earn their tokens (trigger detection, workflow steps), but overall it could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready CLI commands (`joelclaw send discovery/noted --data '...' --follow`, `joelclaw discover <url> --site ...`), specific URL patterns for trigger detection, explicit default values for site/visibility, and clear decision trees for monitoring assessment. The guidance is specific and executable.	3 / 3
Workflow Clarity	The workflow has clear steps but the numbering is broken (two sections labeled '### 2' and '### 3'), which creates confusion. The monitoring assessment step is well-structured with a decision tree, but there's no explicit validation/error handling for the event firing itself — what if `joelclaw send` fails? The 'when NOT to trigger' boundary is good, but the overall sequencing suffers from the numbering error and lack of failure recovery at the agent level.	2 / 3
Progressive Disclosure	References to other skills (`monitor` skill, `x-api` skill) and external config files (`tracked-projects.ts`) are mentioned but there are no bundle files to support them. The background pipeline details and tracked projects list are inlined when they could be in separate reference files. The structure has clear sections but the content split between 'what the agent does' and 'what the pipeline does' could be better delineated.	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.

This is a strong skill description that clearly defines its purpose, provides extensive natural trigger terms, and explicitly describes both what it does and when it should activate. The description is specific about the technical pipeline (Inngest, Vault, discovery/noted event) while also being rich in natural language triggers that users would actually use. It also handles edge cases like bare URL drops, showing thoughtful design.

Dimension	Reasoning	Score
Specificity	Lists specific concrete actions: capturing URLs, repos, or ideas to the Vault via Inngest, firing a discovery/noted event, and continuing the conversation. The description names the specific integration (Inngest), the destination (Vault), and the event type.	3 / 3
Completeness	Clearly answers both 'what does this do' (captures finds to the Vault via Inngest, fires a discovery/noted event) AND 'when should Claude use it' (explicit trigger words listed, behavioral patterns like bare URL drops described). The trigger guidance is thorough and explicit.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would actually say: 'interesting', 'cool', 'neat', 'check this out', 'look at this', 'came across', plus behavioral triggers like bare URL drops and sharing content with minimal context. These are highly natural phrases.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: capturing interesting discoveries to a specific system (Vault via Inngest). The specific signal words and behavioral triggers (bare URL drops, 'interesting', 'cool') create a well-defined activation boundary that is unlikely to conflict with other skills.	3 / 3
	Total	12 / 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

Repository: joelhooks/joelclaw
Commit: 2ca3686

Reviewed: 10 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.