Trade decision audit trail and statistics
43
30%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/ledger/SKILL.mdQuality
Discovery
22%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 description is too terse and vague to effectively guide skill selection. It names a domain (trade decisions) and two broad concepts (audit trail, statistics) but fails to specify concrete actions or provide any trigger guidance for when the skill should be used. It would benefit significantly from listing specific capabilities and adding explicit 'Use when...' conditions.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user asks to review trade history, generate trade performance reports, or audit past trading decisions.'
List specific concrete actions the skill performs, e.g., 'Logs trade decisions with timestamps and rationale, calculates win/loss ratios, tracks P&L, and generates performance summaries.'
Include natural trigger terms users might say, such as 'trade log', 'trading history', 'trade performance', 'P&L report', 'trade journal'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract language ('audit trail and statistics') without listing any concrete actions. It does not specify what operations are performed—no verbs like 'generate', 'track', 'analyze', or 'export' are present. | 1 / 3 |
Completeness | The description weakly addresses 'what' (audit trail and statistics for trades) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | It includes some relevant domain keywords like 'trade', 'audit trail', and 'statistics' that a user might mention, but lacks common variations or natural phrasing (e.g., 'trading log', 'trade history', 'performance metrics', 'P&L'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'trade' and 'audit trail' provides some domain specificity, but 'statistics' is very generic and could overlap with many analytics or reporting skills. Without more precise scoping, conflict risk remains moderate. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely concise but lacks substance. It reads more like a help menu than an instructional skill — it tells Claude what commands exist but not how to implement them, what outputs to produce, or how the ledger data is structured. Without actionable implementation details, Claude cannot meaningfully execute these commands.
Suggestions
Add concrete examples showing expected input and output for each command (e.g., what `/ledger stats 7d` should display, including sample data format)
Define the data schema for decision records — what fields exist, how they're stored, and how confidence calibration is calculated
Add a workflow section explaining how decisions get recorded into the ledger and how the audit trail connects to trading actions
Include at least one end-to-end example showing a decision being recorded and then queried via the ledger commands
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean content with no unnecessary explanation. Every line serves a purpose — command syntax with brief descriptions. No padding or concepts Claude already knows. | 3 / 3 |
Actionability | The skill only lists command signatures with brief descriptions but provides no concrete guidance on implementation, expected outputs, data formats, how decisions are stored, or what the commands actually do under the hood. There's no executable code or specific examples. | 1 / 3 |
Workflow Clarity | There is no workflow described — no sequencing of steps, no validation checkpoints, no explanation of how these commands relate to each other or to the broader trading decision process. It's just a command reference with no context on usage patterns. | 1 / 3 |
Progressive Disclosure | The content is well-organized with a clear commands section, but there are no references to additional documentation for details like data schemas, output formats, or implementation specifics. For such a brief skill, some inline examples or links to detailed docs would improve navigation. | 2 / 3 |
Total | 7 / 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 | |
e71a5f6
Table of Contents
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.