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.
81
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/discovery/SKILL.mdQuality
Discovery
89%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 with excellent trigger term coverage and clear completeness. Its main weakness is that the 'what it does' portion is somewhat thin — it captures finds and fires an event, but doesn't elaborate on multiple concrete actions. The trigger guidance is exceptionally well-crafted with natural language patterns that would reliably match user intent.
Suggestions
Add more specific concrete actions beyond 'fires a discovery/noted event' — e.g., 'extracts metadata from URLs, categorizes discoveries, tags content for later retrieval' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (capturing finds to the Vault via Inngest) and describes the core action (fires a discovery/noted event), but the actual capabilities are limited to one action rather than listing multiple concrete operations. The description focuses more on triggers than on what it concretely does. | 2 / 3 |
Completeness | Clearly answers both 'what' (captures interesting finds to the Vault via Inngest, fires a discovery/noted event) and 'when' (explicit trigger conditions including signal words, bare URL drops, and content shared with minimal context). The 'Triggers when...' clause serves as an explicit 'Use when' equivalent. | 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', bare URL drops, sharing a URL/repo/idea. These are highly natural phrases that match real user behavior. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: capturing interesting finds to a specific system (Vault via Inngest) with very specific signal words. The combination of casual sharing language + URL/repo/idea content type + the Vault destination makes this unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
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 decision trees. However, it suffers from verbosity in background/pipeline sections that the agent doesn't need to act on, broken step numbering in the workflow, and inline content that would be better referenced externally. Tightening the content and fixing structural issues would significantly improve it.
Suggestions
Fix the duplicate step numbering (two '2' and '3' steps) in the Workflow section to create a clear, unambiguous sequence.
Move 'What the Pipeline Does', 'Deep Dig', and 'Tracked projects' to a separate reference file — the agent only needs to know to fire the event, not how the pipeline works internally.
Add error handling guidance: what to do if `joelclaw send --follow` times out or doesn't return a finalLink.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some useful detail but is verbose in places — the 'What the Pipeline Does' section explains background that the agent doesn't need to act on, and the 'Deep Dig' section repeats that enrichment is automatic multiple times. The tracked projects list and video handling section add bulk that could be referenced externally. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for both the canonical operator path and the compatibility shortcut, with specific flags and data payloads. The trigger detection patterns are explicit, the MCQ template for monitoring is copy-paste ready, and the X/Twitter API endpoint is fully specified. | 3 / 3 |
Workflow Clarity | The workflow has a clear sequence but the step numbering is broken (two steps labeled '2' and '3'), which creates confusion. The monitoring assessment step is well-structured with decision logic, but there's no validation or error handling for when the `joelclaw send` command fails or the pipeline doesn't return a finalLink. | 2 / 3 |
Progressive Disclosure | References to external skills (monitor, x-api) are well-signaled, but substantial background content (pipeline internals, tracked projects, deep dig details) is inlined rather than referenced from separate files. The skill would benefit from moving the 'What the Pipeline Does' and 'Deep Dig' sections to a reference doc. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
ce9ca8e
- Reviewed
Table of Contents
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.