Name: analyze-sessions
Rating: 77.60000000000001 (1 reviews)
Author: dotnet

analyze-sessions

Analyzes your local Copilot CLI sessions for dotnet/maui to drive iterative improvements to the PR-review agent (and other agents, skills, and instruction files). Runs a select → extract → score → judge → cluster → propose → emit-eval loop: a deterministic core ranks your worst / most-expensive sessions, then the agent rubric-tags recurring failure modes, proposes concrete repo edits, and emits a vally guard-eval per failure mode so each one becomes a regression test. Triggers on: "analyze my recent maui sessions", "what's making my agent runs expensive", "find failure modes in my Copilot sessions", "turn my session failures into guard evals". LOCAL-ONLY — never uploads, shares, or posts transcripts. Do NOT use for: reviewing a single PR (use pr-review), running tests, or analyzing a GitHub issue.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

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

The body is highly actionable and well-structured with concrete commands, tables, a validation gate, and a checklist, and it correctly offloads detail to a one-level-deep reference file. The only weakness is repetition of the privacy contract, emit-eval path, and exclusion list across multiple sections.

Suggestions

Consolidate the privacy contract into the 'Privacy & safety' section and reference it once from the intro blockquote instead of restating the full terms in three places.

State the emit-eval target path (.github/skills/analyze-sessions/tests/eval.<short-mode>.vally.yaml) once in Phase 6 and reference it from the Outputs section rather than repeating the full path and the '.github/evals/ is invalid' caveat multiple times.

Trim the duplicated 'Do NOT use for' / 'When NOT to use' content to a single section to reduce token cost without losing the boundary guidance.

Dimension	Reasoning	Score
Conciseness	Content assumes Claude's intelligence (no basic-concept padding) and is mostly high-signal, but the privacy contract, emit-eval target path, and 'Do NOT use for' list are each restated across multiple sections and could be trimmed to a single canonical statement.	4 / 5
Actionability	Provides copy-paste-ready pwsh commands with exact paths and flags, an explicit scoring formula, concrete rubric and proposal tables, and a complete vally YAML template — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 6-phase loop with an explicit validation gate ('npx vally lint --strict'), guardrails ('do not silently apply edits', untrusted-digest boundary), and a completion-criteria checklist that acts as a feedback loop for the batch/emit operation.	5 / 5
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to a real references/design-rationale.md and scripts/Get-SessionAnalysis.ps1 (both present in the bundle), with content appropriately split and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concrete, and explicit about both capabilities and triggers, with clear disambiguation from sibling skills. Voice and trigger guidance fully meet the rubric anchors. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'select → extract → score → judge → cluster → propose → emit-eval loop', 'ranks your worst / most-expensive sessions', 'rubric-tags recurring failure modes', 'proposes concrete repo edits', 'emits a vally guard-eval per failure mode' — covering the full workflow comprehensively.	5 / 5
Completeness	Explicitly answers what ('Analyzes your local Copilot CLI sessions... Runs a select → ... → emit-eval loop') and when ('Triggers on: ...' with concrete phrases), plus a 'Do NOT use for' boundary clause — both what and when are concretely present.	5 / 5
Trigger Term Quality	Four natural user phrasings are given — 'analyze my recent maui sessions', 'what's making my agent runs expensive', 'find failure modes in my Copilot sessions', 'turn my session failures into guard evals' — covering synonyms and the way a user would actually ask.	5 / 5
Distinctiveness Conflict Risk	Narrow niche (local Copilot CLI session analysis for dotnet/maui) with distinct triggers and an explicit 'Do NOT use for' list that separates it from pr-review, test running, and issue analysis, minimizing conflict risk.	5 / 5
	Total	20 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dotnet/maui
Path: .github/skills/analyze-sessions/SKILL.md
Commit: 90afade

Reviewed: ~18 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.