session-execution
Use when working on or reviewing session execution, command handling, shell state, FIFO-based streaming, or stdout/stderr separation. Relevant for session.ts, command handlers, exec/execStream, or anything involving shell process management. (project)
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/session-execution/SKILL.mdQuality
Discovery
72%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 excels at trigger term coverage and distinctiveness, providing highly specific technical keywords that clearly define its niche. However, it lacks concrete action verbs describing what the skill actually does (e.g., guides implementation, reviews code, debugs issues), and the 'what' component is essentially absent—only the domain/context is specified, not the skill's capabilities.
Suggestions
Add explicit action verbs describing what the skill does, e.g., 'Guides implementation and debugging of session execution, command handling, and shell process management.'
Clarify the skill's purpose beyond just the domain—does it help write code, review code, debug issues, or explain architecture? State this explicitly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (session execution, command handling, shell state) and mentions some specific concepts (FIFO-based streaming, stdout/stderr separation, exec/execStream), but doesn't list concrete actions the skill performs—it describes topics rather than actions like 'parses', 'manages', or 'debugs'. | 2 / 3 |
Completeness | The 'when' clause is explicit ('Use when working on or reviewing...'), but the 'what' is weak—it describes the domain/topics but not what the skill actually does (e.g., does it guide implementation, review code, debug issues?). The 'what' is only implied through the 'when'. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that a developer would use: 'session.ts', 'command handlers', 'exec/execStream', 'FIFO-based streaming', 'stdout/stderr separation', 'shell process management'. These are specific technical terms a user working in this domain would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche—session execution, FIFO-based streaming, stdout/stderr separation, and specific files like session.ts. This is unlikely to conflict with other skills due to its narrow technical focus. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%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 communicates a complex system's architecture and provides structured guidance for both development and review. Its greatest strength is the race condition analysis section, which prevents common review mistakes with a clear decision tree. The main weakness is the lack of executable code examples, though for a review-oriented skill this is a minor gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude understands shell concepts, FIFOs, mutexes, and file operations without explaining them. Every section adds domain-specific knowledge that Claude wouldn't already know about this particular system's architecture. | 3 / 3 |
Actionability | The skill provides concrete guidance for reviewing (specific correctness checks, false positive patterns, actual concerns) and developing (specific test scenarios), but lacks executable code examples or commands. The guidance is specific to this codebase but remains at the instructional level rather than providing copy-paste ready snippets. | 2 / 3 |
Workflow Clarity | The reviewing workflow is clearly sequenced with explicit checkpoints: the race condition analysis section provides a 3-step verification process (check same session → check cross-session → refer to concurrency docs). The distinction between false positives and actual concerns serves as a validation checklist for reviewers. For a review/development skill, this level of structured guidance is appropriate. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear overview that points to `docs/SESSION_EXECUTION.md` for detailed architecture and `docs/CONCURRENCY.md` for the concurrency model — one level deep, clearly signaled. Key files are listed for navigation. Content is appropriately split between this overview and the referenced docs. | 3 / 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
- cloudflare/sandbox-sdk
- Commit
f03920a
- 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.