your-skill-name
Replace with a clear description of what this skill does and when Claude should use it.
43
11%
Does it follow best practices?
Impact
100%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./template/SKILL.mdQuality
Discovery
0%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 not an actual skill description — it is the default placeholder/template text instructing the skill author to replace it with a real description. It provides zero useful information about capabilities, triggers, or use cases, and would be completely non-functional for skill selection.
Suggestions
Replace the placeholder text entirely with a description of the skill's concrete capabilities (e.g., 'Extracts data from CSV files, generates summary statistics, and creates visualizations').
Add an explicit 'Use when...' clause with natural trigger terms that users would say when they need this skill.
Include specific file types, domain terms, or action verbs that distinguish this skill from others in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | This is a placeholder template text with no concrete actions described whatsoever. It contains zero information about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The text is a meta-instruction telling the author to write a description, not an actual description. | 1 / 3 |
Trigger Term Quality | There are no natural keywords or trigger terms present. The text is entirely a placeholder instruction, not an actual description. | 1 / 3 |
Distinctiveness Conflict Risk | A placeholder description is maximally generic and provides no distinguishing information. It would be impossible to differentiate this from any other skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially an unfilled template/skeleton rather than a functional skill. It contains placeholder text throughout ('What to do first', 'Replace with a clear description') and provides no concrete, actionable guidance for any specific task. While the structural outline is reasonable, the complete absence of real content makes it unusable as an actual skill.
Suggestions
Replace all placeholder text with specific, concrete instructions for the actual security assessment task this skill is meant to address (e.g., specific commands to run, specific files to inspect, specific vulnerability patterns to look for).
Add executable code examples or specific tool commands that Claude can directly use, such as grep patterns for vulnerability detection or script invocations for analysis.
Include validation checkpoints in the workflow — e.g., how to verify a finding is a true positive before reporting, or how to confirm remediation steps are correct.
Either provide the referenced bundle files (plays/, templates/) or inline the essential content so the skill is self-contained and functional.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief and doesn't over-explain concepts Claude already knows, but it's essentially a template with placeholder text ('Replace with...', 'What to do first', 'What to do next') that adds no real informational value. The structure is lean but the content is hollow. | 2 / 3 |
Actionability | The skill provides entirely vague, placeholder guidance — 'What to do first', 'What to do next', 'Describe the expected output format' are not actionable instructions. There are no concrete commands, code examples, or specific steps Claude could execute. | 1 / 3 |
Workflow Clarity | While a numbered step sequence exists, the steps are generic placeholders with no real content. There are no validation checkpoints, no feedback loops, and no concrete sequencing of actual tasks. The 'Produce Findings' step mentions citing evidence but gives no specifics on how. | 1 / 3 |
Progressive Disclosure | The skill references external files (plays/tierN-category/your-play.md, templates/finding.md, templates/report.md) which suggests an intent for progressive disclosure, but no bundle files exist to support these references. The structure is reasonable but the references point to non-existent or placeholder paths. | 2 / 3 |
Total | 6 / 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
- OWASP/secure-agent-playbook
- Commit
3f4fcb6
- 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.