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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 body is highly actionable with executable commands and good decision-branch checkpoints, but a duplicate step-numbering error and a monolithic, unsplit structure hold back workflow clarity and progressive disclosure.

Suggestions

Fix the duplicate step numbering in the Workflow section (it currently runs 1, 2, 3, then repeats 2 and 3 for 'Assess for Monitoring' and 'Continue conversation').

Move the 'Deep Dig — Inngest Enrichment Pipeline (ADR-0150)' detail and tracked-projects list into a referenced file (e.g. ENRICHMENT.md) and link to it, keeping the body as an overview.

Add a brief step to confirm the `discovery/noted` event fired before 'continue conversation', giving the fire-and-forget path a lightweight verification checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence without explaining Inngest/defuddle/OTel, but a few passages (the venue-routing explanation and 'fire-and-forget; Slack handling must not block' elaboration) could be trimmed.	4 / 5
Actionability	Copy-paste-ready commands (`joelclaw send discovery/noted --data '...' --follow`, `joelclaw discover <url> --site ...`) and a fully-specified X API GET with query params cover the common cases (tweet, repo, article, video) with concrete file paths and defaults.	5 / 5
Workflow Clarity	A clear multi-step workflow with explicit decision checkpoints (monitorable+relevant -> MCQ, low-relevance -> brief mention, not monitorable -> skip), but duplicate step numbering (1, 2, 3 then 2, 3 again) breaks sequence readability and no fire-verification checkpoint is given.	4 / 5
Progressive Disclosure	Clear section headers and reasonable organization, but no reference files exist and heavier background content (the Deep Dig enrichment pipeline, tracked-projects list) is inlined rather than split into one-level-deep signaled references.	3 / 5
	Total	16 / 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 description that crisply states what the skill does and when to invoke it, anchored by concrete systems and natural trigger phrases. Minor specificity and overlap refinement could push it higher.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Capture interesting finds to the Vault via Inngest', 'Fires a discovery/noted event and continues the conversation', 'the pipeline handles everything else') with named systems, leaving only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (capture to Vault via Inngest, fire discovery/noted, pipeline handles the rest) and when (triggers on signal words, minimal-context shares, and bare URL drops) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive verbatim natural-language signal words ('interesting', 'cool', 'neat', 'check this out', 'look at this', 'came across') plus 'bare URL drops' and 'shares a URL, repo, or idea' cover the natural phrases users actually say.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Inngest/Vault discovery capture with discovery/noted events) and distinct triggers keep conflict risk low, though a generic 'save this' intent creates minor overlap with related skills.	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: d952451

Reviewed: 4 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.