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.
This is a solid description that clearly communicates both what the skill does and when to use it, with a distinctive niche around session log analysis. Its main weaknesses are moderate specificity (it could enumerate what kinds of insights or analyses the report includes) and limited trigger term coverage (missing natural variations of how users might ask for session reviews).
Suggestions
Add more specific concrete actions the report includes, e.g., 'identifying recurring blockers, tracking progress trends, summarizing decisions made'
Expand trigger terms to include natural variations like 'session summary', 'session review', 'what happened in previous sessions', 'session history'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It 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' and 'analyzing logs'. What the report contains or what specific analyses are performed is not detailed. | 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', 'retrospectives', 'patterns across sessions', and the specific path '.github/sessions/'. However, it misses common variations users might say such as 'session summary', 'session review', 'what happened last session', or 'session history'. | 2 / 3 |
Distinctiveness Conflict Risk | The specific focus on cross-session insights from '.github/sessions/' logs and retrospectives creates a clear niche that is unlikely to conflict with other skills. The combination of session logs analysis and retrospective preparation is quite distinctive. | 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.
This skill suffers primarily from extreme verbosity — the massive inline report template with placeholder data dominates the file and is something Claude could generate independently. The actual instructional content (Steps 1-3) is reasonable but could be much more concise. The workflow structure is logical but lacks validation steps for parsing and error handling for malformed session data.
Suggestions
Extract the full report template into a separate TEMPLATE.md file and reference it from the main skill, reducing the SKILL.md to ~50-60 lines of actual instructions.
Remove placeholder/example data from the template (fake dates, session counts, file paths) — Claude can generate contextually appropriate content without these examples.
Add validation checkpoints: verify session files parse correctly before proceeding to analysis, and handle malformed or incomplete session logs gracefully.
Add a brief note about expected session file format/structure rather than listing every possible field to extract — Claude can discover fields by reading the files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with the vast majority being a massive template/example report that Claude could generate on its own. The detailed markdown template with placeholder data (fake dates, fake session counts, fake file paths) is unnecessary padding. Claude knows how to format markdown reports and doesn't need a 200-line example showing every possible section with sample data. | 1 / 3 |
Actionability | Step 1 provides a concrete PowerShell command for file discovery, and Step 2-3 give specific field names and analysis categories. However, the parsing instructions are descriptive rather than executable (no actual parsing code), and the bulk of the content is a template rather than actionable guidance on how to perform the analysis. | 2 / 3 |
Workflow Clarity | The 4-step workflow (Discover → Parse → Analyze → Generate) is clearly sequenced and logical. However, there are no validation checkpoints — no verification that parsing succeeded correctly, no handling of malformed session files, and no feedback loop for when session files don't match the expected format. The 'no sessions found' check in Step 1 is good but insufficient. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The massive report template (which constitutes ~70% of the content) should be in a separate template file. There's no bundle structure to support this, and the content that should be split out (the full report template, analysis categories) is all inline. | 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
a5309ae
- 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.