safe-file-deletion

Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from disk. MUST be followed for all delete operations.

Quality

92%

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

100%

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 tight, well-structured guardrail skill with concrete tool-call examples, an explicit permission-gating workflow including a validation checkpoint and denial branch, and clean section organization. It respects Claude's competence and adds only operational value.

Dimension	Reasoning	Score
Conciseness	Lean and operational with no padding or explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Names the exact tool call (request_file_permission with operation: 'delete'), provides concrete single-file and batched JSON examples, scopes specific commands, and lists explicit workarounds to avoid — fully actionable guidance.	3 / 3
Workflow Clarity	A clear 5-step sequence with an explicit validation checkpoint ('Wait for response', 'Only proceed if allowed') and an error-recovery branch ('If denied, acknowledge and do NOT delete'), meeting the feedback-loop bar for destructive operations.	3 / 3
Progressive Disclosure	Under 50 lines, single-purpose, with no need for external references and well-organized sections (Rule, Applies To, Examples, No Workarounds); per the simple-skills note this warrants a top score.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 specific, complete, and well-scoped with an explicit activation trigger. Its main weakness is trigger-term quality: it relies on technical API names rather than the natural phrasing a user would actually say when asking to delete a file.

Suggestions

Add natural-language trigger terms users would say, e.g. 'delete', 'remove', 'get rid of these files', alongside the technical names rm/unlink/fs.rm.

Consider a concise 'Use when...' framing to make the trigger clause even more recognizable as activation guidance.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Enforces explicit user permission before any file deletion') plus specific trigger operations (rm, unlink, fs.rm), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what it does ('Enforces explicit user permission before any file deletion') and when to use it via an explicit 'Activates when...' trigger clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Includes some natural terms ('file deletion', 'removes files') but leans on technical jargon (rm, unlink, fs.rm) and misses common natural user phrasings like 'delete this file'; matches 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Targets a clear, narrow niche (permission-gated file deletion) with distinct deletion-specific triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: accomplish-ai/coworker
Path: packages/agent-core/mcp-tools/safe-file-deletion/SKILL.md
Commit: 2cf74d0

Reviewed: 1 day 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.