generate-report
Save investigation findings to a markdown report file. Use after completing triage, enrichment, or investigation to create a permanent record. Generates timestamped files in ./reports/ directory.
73
67%
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 ./skills/generate-report/SKILL.mdQuality
Discovery
85%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 description that clearly communicates what the skill does and when to use it. It provides specific details about output format, directory, and timing context. The main weakness is that trigger term coverage could be broader to capture more natural user phrasings like 'write a report' or 'save results'.
Suggestions
Add more natural trigger terms users might say, such as 'write report', 'save results', 'document findings', 'incident summary', or 'case notes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: saving investigation findings, creating markdown report files, generating timestamped files in a specific directory (./reports/). Multiple concrete details are provided. | 3 / 3 |
Completeness | Clearly answers both what ('Save investigation findings to a markdown report file, generates timestamped files in ./reports/') and when ('Use after completing triage, enrichment, or investigation to create a permanent record'). | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'investigation findings', 'triage', 'enrichment', 'report', and 'markdown', but misses common variations users might say such as 'write report', 'save results', 'document findings', 'incident report', or 'summary'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to security/investigation report generation with specific output format (markdown), location (./reports/), and context (post-triage/enrichment/investigation). Unlikely to conflict with general file or document skills. | 3 / 3 |
Total | 11 / 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.
This skill provides a clear structure for generating report files with good naming conventions and a useful template, but falls short on actionability by not showing concrete tool invocation syntax. It also lacks validation steps (directory existence check, write verification) which is important for file operations, and contains some redundancy in the examples.
Suggestions
Add concrete tool invocation syntax showing exactly how to call the Write tool with the constructed path and content, rather than just saying 'Use the Write tool'.
Add a validation step after writing: verify the file was created successfully and handle the case where the target directory doesn't exist (create it first).
Remove the duplicate naming convention table at the end since the same examples already appear in Step 1, or consolidate them into a single location.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some redundancy—the naming convention table at the end repeats examples already shown in Step 1, and the report template structure section is somewhat verbose given Claude already knows how to format markdown reports. | 2 / 3 |
Actionability | The workflow describes what to do (construct filename, use Write tool) but lacks executable code or concrete tool invocation syntax. The instruction 'Use the Write tool to save REPORT_CONTENT' is vague—it doesn't show the actual tool call format or parameters. | 2 / 3 |
Workflow Clarity | The two-step workflow is clearly sequenced, but there's no validation checkpoint—no check for whether the directory exists, no verification that the write succeeded, and no error handling or feedback loop for write failures. | 2 / 3 |
Progressive Disclosure | The content is organized with clear sections and tables, but the report template structure and naming convention table could be split into separate reference files. For a skill of this length (~70 lines of content), everything is inline when some of it (especially the template) could be referenced externally. | 2 / 3 |
Total | 8 / 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
- dandye/ai-runbooks
- Commit
086cbf6
- 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.