analyzing-options-flow
Track crypto options flow to identify institutional positioning and market sentiment. Use when tracking institutional options flow. Trigger with phrases like "track options flow", "analyze derivatives", or "check institutional".
68
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/crypto/options-flow-analyzer/skills/analyzing-options-flow/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.
The description is well-structured with explicit trigger guidance and a clear 'Use when' clause, making it functional for skill selection. Its main weakness is that the 'what' portion is somewhat high-level—it could benefit from listing more specific concrete actions (e.g., tracking put/call ratios, identifying whale trades, monitoring open interest changes). The trigger terms and distinctiveness are strong for this niche domain.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Track put/call ratios, identify whale trades, monitor open interest changes, and analyze options volume spikes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (crypto options flow) and mentions some actions (track, identify institutional positioning and market sentiment), but doesn't list multiple concrete specific actions like specific analyses, outputs, or data sources. | 2 / 3 |
Completeness | Clearly answers both 'what' (track crypto options flow to identify institutional positioning and market sentiment) and 'when' (explicit 'Use when' clause and trigger phrases provided). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'track options flow', 'analyze derivatives', 'check institutional'. These cover reasonable variations of how users might request this functionality, though 'crypto' as a standalone trigger is missing. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'crypto', 'options flow', 'institutional positioning', and 'derivatives' creates a clear niche that is unlikely to conflict with other skills. This is a very specific domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a product requirements document than an actionable skill for Claude. It describes what should happen at each step without providing executable code or specific API calls, and it over-explains concepts Claude already understands (options terminology, what metrics mean). The structure is reasonable but bloated, with the core instructions lacking the concrete implementation details needed for Claude to actually execute the workflow.
Suggestions
Replace the descriptive instruction steps with executable code snippets showing actual API calls (e.g., Deribit REST/WebSocket endpoints with request/response examples) rather than describing what to compute conceptually.
Remove explanations of options concepts Claude already knows (put/call ratio interpretation, what max pain means, what IV term structure indicates) to significantly reduce token count.
Add validation checkpoints within the workflow, such as verifying API connection success after step 1, confirming data completeness before computing statistics in step 4, and validating output format before export in step 10.
Move the detailed output specifications and error handling table to a separate reference file, keeping only a brief summary in the main skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, explaining options terminology Claude already knows, providing lengthy descriptions of what each metric means (e.g., explaining what put/call ratio indicates, what max pain is), and including extensive output descriptions and resource links that inflate token count without adding actionable value. | 1 / 3 |
Actionability | The examples show CLI commands which are somewhat concrete, but the core instructions (steps 1-10) are largely descriptive rather than executable—they describe what to do conceptually without providing actual code, API calls, or specific implementation details. References to `Bash(crypto:options-*)` and `options_flow.py` suggest tools exist but no executable code is provided inline. | 2 / 3 |
Workflow Clarity | The 10 steps provide a clear sequence, but there are no validation checkpoints or feedback loops. For a workflow involving API connections, data retrieval, and statistical analysis, there should be explicit verification steps (e.g., confirm API connection succeeded, validate data completeness before computing statistics). The error handling table is helpful but separate from the workflow. | 2 / 3 |
Progressive Disclosure | There is one reference to `${CLAUDE_SKILL_DIR}/references/implementation.md` for the full implementation workflow, which is good. However, the main file contains too much inline content that could be split out (the extensive output specifications, the full error handling table, the resources section), making the overview heavier than it should be. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3e83543
- 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.