sensei
**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.
Install with Tessl CLI
npx tessl i github:microsoft/github-copilot-for-azure --skill sensei95
Does it follow best practices?
Evaluation — 100%
↑ 1.63xAgent success when using this skill
Validation for skill structure
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 excels across all dimensions. It uses clear third-person voice, provides explicit trigger terms in a structured WHEN clause, specifies what tools are invoked, and even includes scope guidance for when NOT to use the full workflow. The domain-specific terminology (sensei, Ralph loop, frontmatter) makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'improve skill frontmatter compliance', 'Ralph loop pattern', 'token counting', 'test runners', 'git commands'. Clearly describes what tools are invoked and distinguishes single vs iterative operations. | 3 / 3 |
Completeness | Clearly answers both what ('Iteratively improve skill frontmatter compliance using the Ralph loop pattern') and when (explicit 'WHEN:' clause with multiple trigger phrases). Also includes scope guidance for single operations. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'run sensei', 'sensei help', 'improve skill', 'fix frontmatter', 'skill compliance', 'frontmatter audit', 'score skill', 'check skill tokens'. These are explicit and varied. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific domain (skill frontmatter, sensei, Ralph loop pattern) and unique trigger terms like 'run sensei' and 'frontmatter audit'. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured workflow skill with excellent actionability and clear multi-step processes with validation checkpoints. The progressive disclosure is exemplary with appropriate references to detailed documentation. The main weakness is verbosity - the ASCII help box and some repeated explanations could be trimmed to improve token efficiency.
Suggestions
Replace the ASCII art help box with a compact markdown table or bullet list to save ~40% of those tokens
Remove the repeated 'agentskills.io specification' link mentions - link once at the top and reference 'the spec' thereafter
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly the large ASCII art help box and repeated explanations of concepts. The frontmatter template section and warnings are useful but could be tightened. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout (npm test patterns, cp commands, git commit formats). The Ralph loop steps are specific and actionable with exact file paths and command syntax. | 3 / 3 |
Workflow Clarity | The 12-step Ralph loop is clearly sequenced with explicit validation checkpoints (SCORE, CHECK, VERIFY, VALIDATE REFERENCES). Includes feedback loops (repeat until score >= Medium-High AND tests pass) and max iteration limits. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview in main file and well-signaled one-level-deep references to SCORING.md, LOOP.md, EXAMPLES.md, and TOKEN-INTEGRATION.md. Related skills are also linked appropriately. | 3 / 3 |
Total | 11 / 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.
- 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.