Name: analyze-sessions
Rating: 75.2 (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

92%

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

85%

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

A well-structured, highly actionable body for a complex multi-phase skill: executable commands, a complete eval template, explicit validation, and clean one-level-deep references. The only real weakness is mild redundancy with the frontmatter and a verbose architecture diagram that could be condensed.

Suggestions

Remove the duplicated 'Trigger phrases' and 'Do NOT use for' blocks from the body since they already appear verbatim in the frontmatter description; reference them once instead.

Condense or move the large ASCII architecture diagram into references/design-rationale.md, keeping only a one-line summary of the shared-core / agent-judge split in the body.

Tighten Phase 2/3 prose (e.g. the untrusted-digest boundary is stated twice) by stating the boundary once and linking rather than restating.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient for a complex skill but repeats material already in the frontmatter (trigger phrases and the 'Do NOT use for' list) and carries a large ASCII diagram plus some explanatory prose that could be trimmed, fitting 'mostly efficient but could be tightened' rather than the fully lean level 3.	2 / 3
Actionability	Provides copy-paste-ready executable commands (pwsh -File ...Get-SessionAnalysis.ps1 with real flags), a complete vally YAML template, and a concrete validation command (npx -y @microsoft/vally-cli@0.10.0 lint --eval-spec ... --strict) with exact file paths, matching the 'fully executable / copy-paste ready' anchor.	3 / 3
Workflow Clarity	Six phases are clearly sequenced with an explicit validation checkpoint (vally lint --strict on every emitted eval) and a final completion-criteria checklist including the feedback loop of emit-eval, satisfying the 'clear sequence with explicit validation steps' anchor; not level 2 because validation is present and explicit for the batch/emit operations.	3 / 3
Progressive Disclosure	The SKILL.md is an overview that clearly signals one-level-deep, real bundle files (references/design-rationale.md and scripts/Get-SessionAnalysis.ps1, both present) and keeps rationale out of the runtime path, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong description: it names concrete actions, gives natural trigger phrases, explicitly covers both what and when, and disambiguates from neighboring skills. Minor nit is the repeated 'your' possessive, but the verb voice remains third person so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third-person voice ('Analyzes your local Copilot CLI sessions', 'ranks your worst / most-expensive sessions', 'rubric-tags recurring failure modes', 'proposes concrete repo edits', 'emits a vally guard-eval'), matching the 'multiple specific concrete actions' anchor rather than the domain-only level 2.	3 / 3
Completeness	Explicitly answers both what (the select→extract→score→judge→cluster→propose→emit-eval loop and its outputs) and when ('Triggers on:'), satisfying the level 3 'both what AND when with explicit triggers' anchor; not level 2 because the when clause is explicit, not implied.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would actually say ('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'), giving good coverage rather than the partial level 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (local dotnet/maui Copilot session analysis) with distinct triggers and explicit disambiguation ('Do NOT use for: reviewing a single PR (use pr-review), running tests, or analyzing a GitHub issue'), making conflict with sibling skills unlikely.	3 / 3
	Total	12 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dotnet/maui
Path: .github/skills/analyze-sessions/SKILL.md
Commit: 6a24ec5

Reviewed: 4 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.