session-checkpoints
Saves and restores session state including task progress, file changes, and delegation history. Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a well-crafted skill description that clearly communicates what the skill does and when to use it. It uses specific, concrete language for capabilities and includes a comprehensive set of natural trigger terms that users would actually say. The description is concise, uses third-person voice, and occupies a distinct niche unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'saves and restores session state' with details on what is saved — 'task progress, file changes, and delegation history'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (saves and restores session state including task progress, file changes, and delegation history) and 'when' (explicit 'Use when' clause with saving progress, resuming interrupted work, picking up where left off, checkpointing). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'saving progress', 'resuming interrupted work', 'picking up where you left off', 'checkpointing current work'. These cover multiple natural phrasings of the same intent. | 3 / 3 |
Distinctiveness Conflict Risk | Session state management, checkpointing, and resuming interrupted work is a clear niche that is unlikely to conflict with other skills. The terms 'session state', 'delegation history', and 'checkpointing' are highly distinctive. | 3 / 3 |
Total | 12 / 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 a well-crafted skill that efficiently covers when to checkpoint, how to create one, how to resume, and how to clean up. The inline example provides immediate actionability while the full template is appropriately externalized. The workflow includes validation steps and error recovery (corrupt/missing checkpoint fallback), making it robust for real-world use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a clear purpose — trigger table, quick creation steps, example checkpoint, resumption steps, and cleanup. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready markdown template, specific file paths (.opencastle/SESSION-CHECKPOINT.md), exact commands (git checkout, pnpm dev, cat), and step-by-step instructions for both creation and resumption. | 3 / 3 |
Workflow Clarity | Both checkpoint creation and resumption are clearly sequenced with numbered steps. Includes validation (step 3 of creation: verify files exist), staleness checks (step 3 of resumption), and a fallback/recovery path if checkpoint is missing or corrupt. | 3 / 3 |
Progressive Disclosure | SKILL.md serves as a concise overview with the quick-start inline, while the full template is appropriately split into CHECKPOINT-TEMPLATE.md. Cross-references to the decomposition skill are clearly signaled and one level deep. | 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
- monkilabs/opencastle
- Commit
f5c8508
- 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.