CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-filesystem

Manage Agent Filesystem through the control-plane MCP server. Use when the `agent-filesystem` MCP server is available, or when the user asks Codex to list, create, fork, checkpoint, delete, or connect AFS workspaces using a control-plane token.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is a well-structured, actionable instruction-only skill with concrete tool guidance, confirmation checkpoints for destructive operations, and clean sectioning. A few explanatory sentences could be tightened and some tool parameter details could be more explicit.

Suggestions

Trim explanatory sentences like the control-plane-token rationale in the intro to keep the body leaner.

Add explicit parameter hints for key tools (e.g. `mcp_token_issue` required fields) to push actionability higher.

Consider moving the Endpoint Configuration URLs into the plugin `.mcp.json` reference or a short reference file so the overview stays focused.

DimensionReasoningScore

Conciseness

Largely lean and efficient with concrete tool lists and a compact TOML example; a few slightly padded explanatory sentences (e.g. 'It uses a control-plane token, so the server exposes ... rather than file tools for one specific workspace') could be trimmed.

4 / 5

Actionability

Provides concrete tool names with one-line descriptions, specific token scopes (workspace-rw, workspace-ro, workspace-rw-checkpoint), and copy-paste-ready TOML and endpoint URLs; minor gaps in full parameter specs for some tools.

4 / 5

Workflow Clarity

Common flows are clearly sequenced (e.g. the 4-step 'Prepare a Workspace-Specific Agent Connection') and destructive operations carry explicit confirmation checkpoints ('Confirm first'), satisfying the destructive-op validation requirement with only minor gaps.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Before Acting, Control-Plane Tools, Common Flows, Endpoint Configuration, Key Points) with no nested references; self-contained content is appropriately placed, though slightly above the under-50-line simple-skill threshold.

4 / 5

Total

16

/

20

Passed

Description

87%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 clearly states the skill's purpose and trigger conditions with concrete, enumerated actions and a distinct niche. Minor improvements would add a few synonyms for natural phrasing.

DimensionReasoningScore

Specificity

Lists several concrete actions ('list, create, fork, checkpoint, delete, or connect AFS workspaces') plus 'Manage Agent Filesystem through the control-plane MCP server', with only minor gaps (e.g. token issuance is not enumerated as an action).

4 / 5

Completeness

Explicitly answers both 'what' ('Manage Agent Filesystem through the control-plane MCP server') and 'when' ('Use when the `agent-filesystem` MCP server is available, or when the user asks Codex to ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural request phrasing ('user asks Codex to list, create, fork, checkpoint, delete, or connect AFS workspaces') plus the server availability trigger, but lacks common synonyms/file-extension variations.

4 / 5

Distinctiveness Conflict Risk

Clear niche (AFS control-plane workspace management) with distinct triggers; unlikely to overlap with other skills.

5 / 5

Total

18

/

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.