insights
Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.
83
75%
Does it follow best practices?
Impact
99%
1.02xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/insights/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 well-crafted skill description that clearly communicates what the skill does, how it works, and when it should be triggered. It uses third person voice, lists specific capabilities, and provides a comprehensive set of natural trigger terms. It serves as a strong example of an effective skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'session analytics, learning patterns, correction trends, heatmaps, and productivity metrics' along with the method 'Computes stats from project memory and session history.' | 3 / 3 |
Completeness | Clearly answers both 'what' (show session analytics, learning patterns, correction trends, heatmaps, productivity metrics; computes stats from project memory and session history) and 'when' (explicit 'Use when...' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural keywords users would actually say: 'stats', 'statistics', 'progress', 'how am I doing', 'coding history', 'dashboard'. These cover both formal and casual phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of session analytics, learning patterns, correction trends, heatmaps, and productivity metrics creates a clear niche. The trigger terms like 'dashboard', 'how am I doing', and 'coding history' are distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a clear vision of what analytics output should look like through detailed example blocks, and includes useful bash commands for data gathering. However, it lacks executable computation logic between data gathering and output rendering, relying on Claude to infer how to parse, count, and categorize learnings and corrections. The output examples are helpful but verbose, and the skill would benefit from explicit workflow steps and handling of edge cases.
Suggestions
Add executable code (Python or bash) that actually parses LEARNED.md entries, counts corrections, and computes the metrics—don't rely solely on example output to convey the computation logic.
Add explicit workflow steps: 1) Gather data, 2) Parse/validate (handle missing files), 3) Compute metrics, 4) Format output. Include handling for edge cases like empty history or no learnings.
Consolidate the four example output blocks into a single representative example, or move detailed output templates to a separate reference file to reduce token usage.
Define what constitutes a 'correction' more precisely—the current definition ('any instance where the user redirected, fixed, or overrode') is vague and hard to programmatically detect from git/session history.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy—the 'What It Shows' section with four large example blocks is verbose, and the 'Output' section at the end largely restates what was already shown. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The data gathering section provides concrete bash commands, which is good. However, the core analytics computation is entirely described through example output rather than executable logic—there's no actual code to parse learnings, count corrections, compute rates, or generate the heatmap. Claude would need to infer all the computation logic. | 2 / 3 |
Workflow Clarity | There's an implicit workflow: gather data → compute metrics → display report. However, the steps aren't explicitly sequenced, there's no validation (e.g., what if no learnings exist, no git history), and no error handling or feedback loops for missing data sources. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's somewhat monolithic—the four detailed output examples could be in a separate reference file. No bundle files are provided, and no external references are used, though the skill is long enough that splitting would help. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- rohitg00/pro-workflow
- Commit
9fc35f5
- 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.