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.
77
96%
Does it follow best practices?
Impact
—
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 terminology (session state, task progress, file changes, delegation history) while also including natural user-facing trigger terms (picking up where you left off, saving progress). The description is concise, uses third person voice, and occupies a distinct niche.
| 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
92%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 with strong actionability and workflow clarity. The trigger table, concrete template example, and numbered resumption steps make it immediately usable. The only weakness is the progressive disclosure: it references CHECKPOINT-TEMPLATE.md which isn't provided in the bundle, making it impossible to verify the reference is valid and the content split is appropriate.
Suggestions
Ensure CHECKPOINT-TEMPLATE.md is included in the bundle so the progressive disclosure reference is verifiable and functional.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a purpose—trigger table, template example, resuming steps, cleanup. No unnecessary explanations of what checkpoints are or why they matter; it assumes Claude understands the concepts and jumps straight to actionable content. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready guidance: a specific file path (.opencastle/SESSION-CHECKPOINT.md), a complete markdown template example, specific commands (git checkout, pnpm dev, git status, git log --oneline -20), and clear numbered steps for both creation and resumption. | 3 / 3 |
Workflow Clarity | Both checkpoint creation and resuming workflows are clearly sequenced with numbered steps. Includes validation (step 3 of creation: verify files exist), staleness checks (step 3 of resuming), a fallback/recovery path for missing/corrupt checkpoints, and a cleanup step. The trigger table provides clear decision points for when to checkpoint. | 3 / 3 |
Progressive Disclosure | References CHECKPOINT-TEMPLATE.md and the decomposition skill appropriately, but since no bundle files were provided, we cannot verify CHECKPOINT-TEMPLATE.md exists. The inline example is a good quick-start, but the reference to a template file that may not exist is a concern. The cross-reference to the decomposition skill is well-signaled but adds a second level of navigation. | 2 / 3 |
Total | 11 / 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
cc13aaf
- 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.