session-checkpoints

Saves, restores session state including task progress, file changes, delegation history. Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work.

Quality

81%

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

80%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 content is concise and largely actionable with concrete commands and a clear resume workflow including verification and a recovery fallback. Its main weakness is progressive disclosure: it references bundle files (CHECKPOINT-TEMPLATE.md, a decomposition skill) that are not actually present, leaving navigation partially unresolved.

Suggestions

Include the CHECKPOINT-TEMPLATE.md file in the bundle (or inline the canonical template) so the reference in 'Creating a Checkpoint' resolves to a real file.

Add an explicit verification checkpoint before the destructive cleanup step (e.g., confirm all issues are Done and work is committed before deleting .opencastle/SESSION-CHECKPOINT.md).

Verify the relative path to the decomposition skill (../../skills/decomposition/SKILL.md) exists or replace it with a path that resolves within the bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: a compact trigger table, short numbered procedures, and concrete commands with no padding or explanations of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Provides concrete executable commands (git status, git branch, git log --oneline -20, cat .opencastle/SESSION-CHECKPOINT.md) and a specific file path, but the checkpoint-creation step relies on a referenced template rather than fully inline copy-pasteable content, leaving a minor gap.	4 / 5
Workflow Clarity	The Creating and Resuming sections are clearly sequenced and include a verification step (cat the file; confirm listed files exist) plus a fallback recovery path, but the batch/destructive-ish cleanup step lacks an explicit validation checkpoint before deletion, capping it just below 5.	4 / 5
Progressive Disclosure	Structure is reasonable with clear section headers, but the body references external paths (CHECKPOINT-TEMPLATE.md and a decomposition skill) that are not present in the bundle, so the actual bundle structure does not back the referenced navigation; references are not clearly resolvable.	3 / 5
	Total	16 / 20 Passed

Description

83%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 strong: it states concrete capabilities and provides explicit 'Use when' trigger guidance with multiple natural phrases. It is concise without being vague, with only minor gaps in synonym coverage and slight overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Saves, restores session state', 'task progress, file changes, delegation history') covering the core capabilities, though the action vocabulary is somewhat minimal compared to a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both 'what' (saves/restores session state, task progress, file changes, delegation history) and 'when' ('Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work').	5 / 5
Trigger Term Quality	Includes several natural user-facing trigger phrases ('saving progress', 'resuming interrupted work', 'picking up where you left off', 'checkpointing current work') but omits synonyms like 'restore session' or common shorthand users might say.	4 / 5
Distinctiveness Conflict Risk	The session-checkpoint/checkpointing niche is fairly distinct and unlikely to trigger for unrelated skills, though the broad terms 'saving progress'/'resuming' carry minor overlap risk with general task-management skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/session-checkpoints/SKILL.md
Commit: fa0c341

Reviewed: 5 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.