session-resume
Session state tracking and resume protocol for the multi-step agent workflow. USE FOR: resume session, persist progress, checkpoint recovery, session-state.json schema. DO NOT USE FOR: Azure infrastructure, code generation, architecture design, troubleshooting.
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 description with strong trigger terms and excellent completeness due to explicit USE FOR and DO NOT USE FOR clauses. The main weakness is that the specificity of concrete actions could be improved—it names the domain clearly but doesn't enumerate detailed operations (e.g., 'read/write session-state.json', 'restore agent context from checkpoints'). Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Reads and writes session-state.json, restores agent context from checkpoints, tracks step completion across workflow stages.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (session state tracking, resume protocol, multi-step agent workflow) and some actions (persist progress, checkpoint recovery), but doesn't list multiple concrete actions in detail—e.g., what exactly does tracking or resuming entail? | 2 / 3 |
Completeness | Clearly answers both 'what' (session state tracking and resume protocol for multi-step agent workflow) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'resume session', 'persist progress', 'checkpoint recovery', 'session-state.json schema'. The DO NOT USE clause also helps prevent false matches. These are terms a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The explicit DO NOT USE FOR clause listing Azure infrastructure, code generation, architecture design, and troubleshooting significantly reduces conflict risk. The niche of session state tracking with specific schema reference (session-state.json) is highly distinctive. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that efficiently communicates a complex session state tracking and resume protocol. It uses tables, compact flow diagrams, and concrete JSON examples to maximize information density while maintaining clarity. The progressive disclosure to reference files is well-structured, and the workflow includes proper validation checkpoints (schema version enforcement, corrupt state recovery).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a purpose — no unnecessary explanations of what JSON is, what state machines are, or other concepts Claude already knows. The tables and compact flow diagram are efficient representations. | 3 / 3 |
Actionability | Provides concrete JSON snippets, specific file paths, exact status values, a clear decision tree for resume flow, explicit atomic write protocol steps (write to .tmp, rename, keep .bak), and precise migration instructions for schema versions. Fully actionable. | 3 / 3 |
Workflow Clarity | The resume flow is clearly sequenced with a decision tree. State write moments are explicitly numbered with specific triggers. Schema version enforcement includes a mandatory validation-then-migrate-then-proceed sequence. Corrupt state recovery includes explicit fallback steps forming a proper feedback loop. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with quick reference table, then appropriately delegates detailed content (full JSON schema, per-step context budgets, recovery protocol details) to clearly signaled one-level-deep reference files in the Reference Index table. | 3 / 3 |
Total | 12 / 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.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
c9b0b16
- 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.