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.

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/sensei/SKILL.md

Quality

Discovery

89%

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-structured skill description that excels at trigger term coverage and completeness, with explicit WHEN clauses and disambiguation guidance. The main weakness is that the specificity of concrete actions could be improved — 'iteratively improve skill frontmatter compliance' is somewhat abstract and could benefit from listing the specific steps or checks performed. The inclusion of the 'FOR SINGLE OPERATIONS' boundary clause is a nice touch for reducing skill conflicts.

Suggestions

Add more specific concrete actions to the description, e.g., 'validates required fields, checks token limits, scores compliance, suggests fixes' instead of the abstract 'iteratively improve skill frontmatter compliance'.

Dimension	Reasoning	Score
Specificity	Names the domain (skill frontmatter compliance) and mentions some actions like 'improve', 'audit', 'score', 'check tokens', but doesn't list concrete specific actions in detail — 'iteratively improve skill frontmatter compliance using the Ralph loop pattern' is somewhat abstract and doesn't enumerate what specific improvements or checks are performed.	2 / 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 disambiguation guidance with 'FOR SINGLE OPERATIONS' to clarify scope boundaries.	3 / 3
Trigger Term Quality	Includes a strong set of natural trigger terms that users would actually say: 'run sensei', 'sensei help', 'improve skill', 'fix frontmatter', 'skill compliance', 'frontmatter audit', 'score skill', 'check skill tokens'. These cover multiple natural phrasings and variations.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — targets a very specific niche (skill frontmatter compliance via the 'Ralph loop pattern' and 'sensei' workflow). The trigger terms like 'run sensei' and 'frontmatter audit' are unique and unlikely to conflict with other skills. The disambiguation note about single operations further reduces conflict risk.	3 / 3
	Total	11 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability and workflow clarity with a well-defined iterative loop, concrete commands, and explicit validation checkpoints. However, it is significantly undermined by extreme verbosity — key warnings are repeated 2-3 times, the ASCII help box duplicates the workflow section, and detailed scoring criteria are inlined despite having a dedicated SCORING.md reference. The content would benefit greatly from aggressive deduplication and pushing detail into the referenced files.

Suggestions

Remove duplicate explanations of 'DO NOT USE FOR' risk — explain it once with a reference to SCORING.md for details instead of repeating it three times.

Move detailed GEPA explanation to a reference file (e.g., references/GEPA.md) and keep only a 2-3 line summary with a link in the main SKILL.md.

Trim the ASCII help box significantly — it duplicates the workflow steps and scoring criteria already present in the body. Keep it as a brief usage/examples reference only.

Move the detailed scoring table and frontmatter template to SCORING.md since it's already referenced, keeping only the target score (Medium-High) and a link in the main file.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~200+ lines. It repeats the same information multiple times (e.g., 'DO NOT USE FOR' risk is explained three separate times with nearly identical wording, scoring criteria appear in both the help box and the scoring section, GEPA is explained redundantly). The large ASCII art help box alone consumes significant tokens duplicating information found elsewhere in the document.	1 / 3
Actionability	The skill provides concrete, executable commands throughout: specific CLI invocations (`cd tests && npm test -- --testPathPatterns={skill-name}`), exact file paths, copy-paste ready bash commands for scaffolding, specific YAML templates, and clear commit message formats. The guidance is highly specific and actionable.	3 / 3
Workflow Clarity	The Ralph Loop is a well-sequenced 12-step workflow with explicit validation checkpoints (step 7: VERIFY tests, step 8: VALIDATE REFERENCES), a clear feedback loop (step 12: REPEAT, max 5 iterations), and conditional branching (step 3: CHECK if score sufficient). The workflow includes error recovery patterns and a clear termination condition.	3 / 3
Progressive Disclosure	The skill references four external documents (SCORING.md, LOOP.md, EXAMPLES.md, TOKEN-INTEGRATION.md) which is good structure, but the main SKILL.md itself contains too much inline detail that should be in those reference files (e.g., full scoring criteria, detailed GEPA explanation, repeated DO NOT USE FOR warnings). The help box duplicates the workflow steps. Content that belongs in references is kept inline.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: microsoft/github-copilot-for-azure
Commit: 771a666

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.