whoop
WHOOP Central - OAuth + scripts to fetch WHOOP data (sleep, recovery, strain, workouts). Use when user asks about their sleep, recovery score, HRV, strain, or workout data.
59
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/4xiomdev/whoop-central/SKILL.mdQuality
Discovery
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 identifies the specific platform (WHOOP), lists concrete data types it can fetch, and provides explicit trigger terms that match natural user language. The 'Use when...' clause covers the key scenarios well, and the WHOOP-specific terminology makes it highly distinctive from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'OAuth + scripts to fetch WHOOP data' with explicit data types '(sleep, recovery, strain, workouts)'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('OAuth + scripts to fetch WHOOP data (sleep, recovery, strain, workouts)') and when ('Use when user asks about their sleep, recovery score, HRV, strain, or workout data') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would actually say: 'sleep', 'recovery score', 'HRV', 'strain', 'workout data'. These are terms WHOOP users naturally use when asking about their health metrics. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — WHOOP is a specific wearable device platform, and the description names it explicitly along with WHOOP-specific metrics like HRV, strain, and recovery score. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, concrete commands and configuration details for accessing WHOOP data, which is its primary strength. However, it is severely bloated—the OAuth setup tutorial, multiple auth paths, and extensive troubleshooting dominate the file and should be split into separate reference documents. The duplicate 'Step 4' heading and lack of clear decision points between auth methods hurt workflow clarity.
Suggestions
Extract the Postman OAuth walkthrough and troubleshooting sections into separate files (e.g., AUTH_SETUP.md, TROUBLESHOOTING.md) and reference them from the main skill with one-line links.
Remove the duplicate 'Step 4' heading and add a brief decision guide at the top of the auth section (e.g., 'Use Postman if X, use auth.js if Y').
Trim explanatory text that Claude doesn't need—e.g., what self-signed certs are, how Postman environments work, what OAuth scopes do—and keep only the specific values and commands.
Add a validation checkpoint after saving credentials (step 2) before proceeding to authentication, such as verifying the credentials file exists and has the expected fields.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines. It includes extensive OAuth setup instructions that are more of a tutorial than a skill reference, redundant troubleshooting sections (multiple variations of redirect URI issues), and explanations Claude doesn't need (what self-signed certs are, how Postman environments work). The Postman walkthrough alone is excessively detailed for a skill file. | 1 / 3 |
Actionability | Commands are concrete and copy-paste ready throughout. Every step includes exact bash commands, specific URLs, environment variable names, and precise configuration values. The JSON output section with flag examples is particularly actionable. | 3 / 3 |
Workflow Clarity | The setup workflow has numbered steps and a verify step at the end, but there are two competing auth paths (Postman vs auth.js) presented without clear decision criteria upfront. The numbered sections have two 'Step 4' headings (a bug). No validation checkpoints between credential saving and authentication steps. | 2 / 3 |
Progressive Disclosure | Everything is in one monolithic file with no references to supporting documents. The extensive Postman setup guide, troubleshooting section, and auth.js alternative could all be separate files. The troubleshooting section alone is nearly as long as the core skill content and buries the actual usage information. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.