CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-filesystem

Use when agents need persistent shared storage, when saving or restoring workspace state, or when coordinating file access across multiple agents and machines. Creates Redis-backed workspaces, checkpoints and restores agent state, mounts shared filesystems locally, searches workspace contents, and forks workspaces for parallel work.

78

Quality

89%

Does it follow best practices?

Impact

100%

Average score across 1 eval scenario

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A well-structured, actionable skill body with executable commands and verification comments on every flow. It could tighten the redundant intro and add an explicit error-recovery loop for the restore step, but otherwise reads cleanly.

Suggestions

Trim or repurpose the opening paragraph, which restates the frontmatter description, to save tokens.

Add an explicit error-recovery feedback loop for `afs cp restore` (e.g., 'if restore fails, re-check `afs cp list` output before retrying').

Consider folding the small 'Preferred Interfaces' mode notes into the relevant Common Flows steps to reduce back-and-forth navigation.

DimensionReasoningScore

Conciseness

Mostly lean with tight inline `# verify` comments and code blocks; the opening paragraph lightly restates the description and could be trimmed, but overall every section earns its place.

4 / 5

Actionability

Copy-paste-ready `./afs` commands cover the common cases — create, mount, status, grep, checkpoint create/list/restore, and fork — with executable flags and example patterns.

5 / 5

Workflow Clarity

Flows are clearly sequenced with verification checkpoints (`# verify the workspace exists`, `# confirm the restore completed`); it stops short of an explicit error-recovery feedback loop, so it is not a 5.

4 / 5

Progressive Disclosure

The body is a well-organized overview with clearly signaled one-level-deep 'Further Reading' references to docs/guides and docs/reference files, with no nested reference chains; no bundle files are present to evaluate.

5 / 5

Total

18

/

20

Passed

Description

92%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.

A strong, third-person description that pairs concrete capabilities with explicit 'Use when' triggers and a distinct Redis-backed agent-workspace niche. Only minor room to grow on synonym/extension coverage in trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Creates Redis-backed workspaces, checkpoints and restores agent state, mounts shared filesystems locally, searches workspace contents, and forks workspaces' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both: the 'what' (the concrete verb list above) and the 'when' via a clear 'Use when agents need…' clause with concrete trigger scenarios.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'persistent shared storage', 'saving or restoring workspace state', and 'coordinating file access across multiple agents and machines' are present, but it lacks synonym/file-extension variants that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

The Redis-backed agent-workspace niche with checkpoints, mounts, and forks is clearly distinct from other skills and unlikely to trigger for the wrong skill.

5 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
redis/agent-filesystem
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.