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

—

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 with excellent trigger term coverage and clear completeness. The explicit WHEN clause with multiple natural trigger phrases and the disambiguation note for single operations are strong points. The main weakness is that the core capability description relies on jargon ('Ralph loop pattern') rather than listing concrete steps, which slightly reduces specificity.

Suggestions

Replace or supplement 'Ralph loop pattern' with a brief enumeration of the concrete steps involved (e.g., 'analyze frontmatter, identify compliance gaps, suggest fixes, verify corrections') to improve specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (skill frontmatter compliance) and some actions ('improve', 'audit', 'score', 'check tokens'), but the core action 'iteratively improve skill frontmatter compliance using the Ralph loop pattern' is somewhat abstract — 'Ralph loop pattern' is internal jargon and the specific concrete steps are not enumerated.	2 / 3
Completeness	Clearly answers both 'what' (iteratively improve skill frontmatter compliance) and 'when' (explicit WHEN clause with trigger phrases). Also includes an INVOKES clause listing tools and a FOR SINGLE OPERATIONS disambiguation note, which adds useful context for skill selection.	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 — 'sensei', 'Ralph loop pattern', 'frontmatter compliance', and 'skill compliance' are very specific terms that carve out a clear niche 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.

This skill has excellent actionability and workflow clarity with concrete commands, clear sequencing, and proper validation checkpoints. However, it is significantly bloated by redundant explanations (the 'DO NOT USE FOR' risk is stated three times nearly verbatim), an oversized ASCII help box, and inline content that belongs in the referenced files. The skill would benefit greatly from aggressive deduplication and moving detailed content to its reference documents.

Suggestions

Remove the duplicate 'DO NOT USE FOR' warnings — explain the concept once with a brief note, and put the full rationale in SCORING.md or a dedicated reference file.

Move the large ASCII help box to a reference file or significantly condense it — the invocation modes section already covers usage patterns.

Move the detailed GEPA explanation (step 5b) to a reference file like references/GEPA.md, keeping only a one-line summary with a link in the main workflow.

Consolidate the scoring criteria into a single brief reference to SCORING.md rather than having both an inline table and the help box duplicate this information.

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 content, scoring criteria appears in both the help box and a dedicated section, GEPA is explained redundantly). The large ASCII art help box alone consumes significant tokens. Much of this content could be condensed or moved to reference files.	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 GEPA command is fully specified with all flags.	3 / 3
Workflow Clarity	The Ralph Loop is clearly sequenced with 12 numbered steps, explicit validation checkpoints (step 7: VERIFY tests, step 8: VALIDATE REFERENCES), a feedback loop (step 12: REPEAT with max 5 iterations), and clear exit conditions (score >= Medium-High AND tests pass). The workflow includes error recovery paths and a user decision point before committing.	3 / 3
Progressive Disclosure	The skill references four external files (SCORING.md, LOOP.md, EXAMPLES.md, TOKEN-INTEGRATION.md) which is good structure, but the main SKILL.md contains too much inline content that should be in those reference files — particularly the repeated DO NOT USE FOR warnings, the full help box, and the detailed GEPA explanation. The scoring criteria quick reference duplicates what should be solely in SCORING.md.	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: 915f809

Reviewed: about 10 hours 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.