CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

file-security-toolkit

Encrypt/decrypt local files, redact sensitive information in documents, and validate password strength when handling private data or preparing files for sharing.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/file-security-toolkit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 command documentation is excellent — executable examples for every subcommand with a real script — but the body is bloated by a duplicated set of generic template sections, broken boilerplate grammar, a dated hard-coded path ('20260316/scientific-skills/Others/...'), and contradictory/unpinned dependency notes. Workflow guidance also lacks verification steps for destructive operations.

Suggestions

Delete the unnumbered duplicate section block (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) and keep only the substantive numbered versions.

Add an explicit validation step to the run plan, e.g., after encrypting, verify a decrypt roundtrip on a copy; after redacting, confirm the output opens and no target patterns remain.

Remove the dated hard-coded 'cd 20260316/scientific-skills/Others/...' path and reconcile the contradictory Python version notes into one pinned dependency block.

DimensionReasoningScore

Conciseness

The body duplicates its entire section set — an unnumbered 'When to Use / Key Features / Dependencies / Example Usage / Implementation Details' block followed by numbered equivalents of the same five sections — plus template boilerplate ('Use this skill when a others task needs a packaged method') and meta-commentary ('Repository baseline for current packaged skills', 'Add pinned versions if this skill needs stricter environment control', 'Python version is not specified in the source document').

2 / 5

Actionability

Section 4 provides fully executable, copy-paste-ready CLI commands for every subcommand (check-password, file-encrypt/decrypt, zip-encrypt/decrypt, redact) with concrete flags and example values, and the referenced 'scripts/file_security.py' exists in the bundle.

5 / 5

Workflow Clarity

The 'Example run plan' gives a rough sequence (confirm inputs, run script, review output) and per-command usage is clear, but destructive/batch operations (redaction overwrites documents, encryption produces archives) lack explicit validation checkpoints such as verifying a decrypt roundtrip or confirming redacted output integrity, which caps this at 3.

3 / 5

Progressive Disclosure

Structure exists (numbered sections, a single one-level-deep bundle script referenced by path that actually exists), but the wholesale duplication of five sections is more than a 'minor organization gap' and the redaction-rule details could live in a separate reference file.

3 / 5

Total

13

/

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.

A strong description that clearly and concisely states concrete capabilities with an explicit use-when clause. It would benefit from naming the archive mechanism (ZIP AES-256) and supported formats to sharpen triggers and distinctiveness.

Suggestions

Mention the concrete mechanisms in the description (e.g., 'password-protected ZIP archives (AES-256)' and supported formats like docx/csv) to strengthen specificity.

Add common synonyms or file extensions (e.g., 'zip', 'archive', '.docx') to widen natural trigger coverage.

DimensionReasoningScore

Specificity

Names three concrete actions — 'Encrypt/decrypt local files', 'redact sensitive information in documents', and 'validate password strength' — but omits concrete mechanism details like ZIP/AES-256 archives, single-file encryption, and supported document formats, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (the three named actions) and 'when' via the concrete trigger phrase 'when handling private data or preparing files for sharing', matching the top anchor rather than the weaker 'when could be more explicit' anchor at 4.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('encrypt', 'decrypt', 'redact', 'sensitive information', 'password strength', 'private data', 'sharing') that users would plausibly say, but misses common synonyms and extensions such as 'zip', 'AES', 'archive', or '.docx'.

4 / 5

Distinctiveness Conflict Risk

The encryption/redaction/password-strength niche is mostly distinct with specific triggers, but broad terms like 'documents' and 'preparing files for sharing' create minor overlap risk with general document-handling skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Other/file-security-toolkit/SKILL.md

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.