insights-report
Generate a comprehensive cross-session insights report by analyzing all captured session logs in `.github/sessions/`. Use when reviewing patterns across sessions or preparing retrospectives.
67
51%
Does it follow best practices?
Impact
99%
1.62xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/insights-report/SKILL.mdQuality
Discovery
75%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 a clear 'Use when' clause and a distinctive niche that makes it easy to select from a pool of skills. Its main weakness is moderate specificity—it could better enumerate the concrete outputs or analyses included in the report. Trigger terms are adequate but could include more natural user phrasings.
Suggestions
Add more specific concrete actions, e.g., 'identifies recurring blockers, tracks decision patterns, summarizes progress trends, and highlights knowledge gaps'
Expand trigger terms with natural user phrasings like 'session summary', 'what did I work on', 'review past sessions', or 'session history'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (cross-session insights report) and a key action (analyzing captured session logs), but doesn't list multiple specific concrete actions beyond 'generate a report by analyzing logs'. What does the report contain? What patterns are analyzed? | 2 / 3 |
Completeness | Clearly answers both 'what' (generate a comprehensive cross-session insights report by analyzing session logs) and 'when' (use when reviewing patterns across sessions or preparing retrospectives) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'session logs', 'patterns across sessions', 'retrospectives', and the specific path '.github/sessions/', but misses common variations users might say like 'session summary', 'what happened last session', 'session history', or 'review past work'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: cross-session analysis from a specific directory (.github/sessions/). The combination of session logs, cross-session patterns, and retrospectives creates a unique trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a clear purpose and logical workflow structure, but is severely bloated by an exhaustive output template that constitutes ~70% of the content. Claude doesn't need every section header, placeholder paragraph, and example data point spelled out—a concise structural outline would suffice. The actionable guidance is front-loaded in Steps 1-2 but becomes purely descriptive in Steps 3-4.
Suggestions
Replace the massive Step 4 template with a concise section outline (just section names and 1-line descriptions of what each should contain), saving ~150 lines of token budget.
Extract the report template into a separate file (e.g., REPORT_TEMPLATE.md) and reference it from the skill, or reduce it to a 10-15 line structural skeleton.
Add concrete parsing guidance in Step 2—show an example session file snippet and the expected extracted data structure, rather than just listing field names.
Add validation checkpoints: verify parsed session count matches discovered files, handle malformed/incomplete session logs gracefully, and confirm report output was written successfully.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with the vast majority being a massive template/example report that Claude doesn't need spelled out in such detail. Claude already knows how to generate markdown reports, aggregate statistics, and format sections. The entire Step 4 template could be reduced to a brief structural outline with key section names. | 1 / 3 |
Actionability | Step 1 provides a concrete PowerShell command and Step 2 gives specific field extraction targets, which is useful. However, Step 3 is entirely descriptive ('aggregate across all sessions') without concrete code or algorithms, and Step 4 is just a massive template rather than executable guidance. The parsing logic for session files lacks concrete examples of the expected file format. | 2 / 3 |
Workflow Clarity | The 4-step sequence (Discover → Parse → Analyze → Generate) is clear and logical, and there's a good early-exit check for no sessions found. However, there are no validation checkpoints after parsing (e.g., handling malformed session files, verifying parsed data completeness), and no error handling for partially-formed session logs. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The enormous output template dominates the skill and should be in a separate template file or significantly condensed. Everything is inline with no structure to help Claude navigate between the instruction logic and the output format. | 1 / 3 |
Total | 6 / 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
- 0xrabbidfly/eric-cartman
- Commit
1e34e1c
- 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.