CtrlK
BlogDocsLog inGet started
Tessl Logo

discord-harvest

Discord content extraction and archival workflow for images, attachments, links, and conversation files. Use when the user asks to "extract Discord images", "download Discord attachments", "harvest a Discord channel", "archive a DM", or mentions scraping or preserving content from a Discord conversation.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 workflow with strong validation checkpoints and clean progressive disclosure into real reference files. Its only weakness is moderate repetition of the trust-boundary/security messaging across multiple sections.

Suggestions

Consolidate the repeated untrusted-input/sanitization messaging: state it once in the Trust Boundary section and reference it from A4 and Security Notice instead of restating the full rationale each time.

Add a copy-paste-ready bash loop example in the body (or a short inline excerpt from code-examples.md) so the download step is executable without opening the reference.

Consider a one-line "Quick reference" mapping each Path (A/B/C) to its key constraints so the branching logic is scannable without reading every subsection.

DimensionReasoningScore

Conciseness

Information-dense and assumes Claude's competence (no explanation of Discord/CDN/curl), but the untrusted-input/trust-boundary points are restated across Trust Boundary, A4, Security Notice, and code-examples, which could be tightened.

4 / 5

Actionability

Concrete REST routes, an executable curl snippet, and real implemented helper functions (sanitize_filename, validate_url, redact_cdn_url, flag_suspicious) in code-examples.md; the inline download snippet uses placeholder templates rather than copy-paste-ready code, keeping it just short of fully executable inline.

4 / 5

Workflow Clarity

A clear Step 0-1-2-3 sequence with explicit staging/validation checkpoints ("Do not download yet", wait for confirmation) and feedback loops (re-resolve stale IDs, validate redirected Location before retry, stop on permission gaps).

5 / 5

Progressive Disclosure

A lean overview body with four verified one-level-deep reference files, each signaled with contextual inline links and a "Load when" table; no nested references and easy navigation.

5 / 5

Total

18

/

20

Passed

Description

100%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 is exemplary: third-person voice, comprehensive concrete actions, natural quoted trigger phrases, and an explicit what-and-when structure. No vagueness, padding, or conflict risk.

DimensionReasoningScore

Specificity

Enumerates concrete actions (extraction, archival) across multiple object types (images, attachments, links, conversation files), giving comprehensive coverage rather than a single generic action.

5 / 5

Completeness

Explicitly answers what ("Discord content extraction and archival workflow for images, attachments, links, and conversation files") and when ("Use when the user asks to...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Quoted natural trigger phrases ("extract Discord images", "download Discord attachments", "harvest a Discord channel", "archive a DM") plus synonyms (scrape, preserve) cover the phrasings a user would actually say.

5 / 5

Distinctiveness Conflict Risk

A narrow Discord-only niche with distinct triggers (harvest a channel, archive a DM) makes overlap with unrelated skills minimal.

5 / 5

Total

20

/

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
t4sh/skills4sh
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.