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

78%

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

65%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 delivers highly actionable, copy-paste-ready commands and specific API guidance, but its workflow sequencing is undermined by duplicated step numbering, and it spends tokens on pipeline internals the agent never executes. Organization is serviceable but would benefit from splitting background sections into reference files.

Suggestions

Fix the Workflow section's duplicate numbering (two '### 2' and two '### 3' subsections) so the intended sequence — resolve site/visibility, fire the event, assess monitoring, continue — is unambiguous.

Trim or move the 'What the Pipeline Does' and 'Deep Dig' background sections (agent-inactionable internals) into a separate reference file, and state the site/visibility defaults once instead of three times.

Convert the inline mentions of the 'monitor' skill, 'x-api' skill, and 'tracked-projects.ts' into clearly signaled references, and note when each should be consulted.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational, but the 'What the Pipeline Does' and 'Deep Dig' sections detail system internals the agent explicitly does not act on ('Enrichment is not manual agent work'), and the site/visibility defaults are repeated across three sections. Not a 2 because there is no generic concept explanation or padding, and not a 4 because the background sections could be cut or tightened.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready commands ('joelclaw send discovery/noted --data {...} --follow', 'joelclaw discover <url> --site joelclaw --visibility private'), an exact X API v2 call with tweet.fields and expansions parameters, and a ready-to-use MCQ template for the monitoring recommendation.	5 / 5
Workflow Clarity	The Workflow section's sequence is broken: '### 2. Canonical operator path' and '### 3. Compatibility shortcut' are followed by a second '### 2. Assess for Monitoring' and '### 3. Continue conversation', leaving the intended order ambiguous, and there are no verification checkpoints. Not a 2 because the individual steps are well defined with concrete commands; not a 4 because the duplicate numbering creates real confusion about step order.	3 / 5
Progressive Disclosure	The bundle contains only two logo assets (neither referenced in the body) with no references/ or scripts/ files, and the body's pointers to the 'monitor' and 'x-api' skills and 'tracked-projects.ts' are inline mentions rather than clearly signaled file references. Sections like Deep Dig, X/Twitter enrichment, and the gateway contract could be split into reference files, so structure is present but organization is incomplete.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

The description is explicit, third-person, and concrete, answering both what the skill does and when it fires with natural trigger phrases. Its only weaknesses are minor: a few body-listed synonyms are omitted and the downstream pipeline work is summarized vaguely.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Capture interesting finds to the Vault via Inngest', 'Fires a discovery/noted event and continues the conversation' — with minor gaps; not a 5 because everything downstream is delegated with the vague 'the pipeline handles everything else' rather than enumerated.	4 / 5
Completeness	Clearly and explicitly answers both: what it does ('Capture interesting finds to the Vault via Inngest... Fires a discovery/noted event') and when to use it with concrete trigger phrases ('Triggers when the user shares a URL, repo, or idea with signal words like... Also triggers on bare URL drops with no explicit ask').	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ('interesting', 'cool', 'neat', 'check this out', 'look at this', 'came across') plus the bare-URL-drop pattern, but several synonyms present in the skill body ('found this', 'wild', 'clever', 'save this', 'remember this') are missing from the description, keeping it below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	A clear personal-capture niche with distinct signal-word triggers; mostly distinct with minor overlap risk against generic bookmark/'save this' skills, so anchor 4 rather than 5.	4 / 5
	Total	17 / 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: aa0116c

Reviewed: 8 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.