CtrlK
BlogDocsLog inGet started
Tessl Logo

discord-reader

Read Discord for financial research through opencli connected to the Discord desktop app: servers, channels, members, recent messages in the active channel, and message search. Use this skill whenever the user wants to check their Discord, list servers or channels, read or search messages in trading, crypto, or market communities, or gauge what a Discord community is saying about a ticker or coin. Read-only: it cannot send, react to, edit, or delete messages.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

73%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, highly actionable skill body with excellent workflow sequencing and validation. Its main weaknesses are redundancy — substantial duplication both within the file and against references/commands.md — and one non-executable status-check template.

Suggestions

De-duplicate: keep setup, output-format, and error tables in references/commands.md only, and reduce the in-file 'Common setup issues' and 'Error Reference' tables to one to cut the body roughly in half.

Replace the non-executable `!`(...)` status block in Step 1 with a plain runnable command, e.g. `command -v opencli && opencli discord-app status`.

State the read-only restriction once prominently (e.g. in the intro) and remove the repeated restatements in Step 3 and the reference pointer.

DimensionReasoningScore

Conciseness

The command-first style is generally tight, but setup instructions, the output-format table, and the error table are duplicated — "Common setup issues" and "Error Reference" overlap within the file, and all three reappear nearly verbatim in references/commands.md. The read-only caveat is also repeated at least four times, so the body could be meaningfully tightened.

3 / 5

Actionability

Nearly all guidance is copy-paste-ready (install command, CDP launch flags, export line, concrete search queries like "AAPL earnings"), covering the common cases. The Step 1 "Current environment status" block uses a non-executable `!`(...)` template construct instead of a runnable check, which is the main gap.

4 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint ("Check connection first — run opencli discord-app status before any other command"), a dedicated diagnostics section with check-then-fix loops, and an error table mapping symptoms to fixes. The skill is read-only, so the destructive-operation validation cap does not apply.

5 / 5

Progressive Disclosure

The body is a genuine overview and references/commands.md is real, one level deep, and clearly signaled ("Read the reference file when you need exact command syntax"). However, setup, output formats, and error handling are inlined in SKILL.md as well as in the reference file, so content placement is only mostly appropriate.

4 / 5

Total

16

/

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 description: comprehensive capability enumeration, explicit use-when triggers in natural language, a clear read-only boundary, and consistent third-person voice. Only minor trigger-synonym gaps keep it from full marks.

DimensionReasoningScore

Specificity

Enumerates every concrete capability of the read-only skill — "servers, channels, members, recent messages in the active channel, and message search" — and explicitly bounds scope with "it cannot send, react to, edit, or delete messages". Third-person voice throughout, so no voice penalty applies.

5 / 5

Completeness

Answers both questions explicitly: the what is the full capability list, and "Use this skill whenever the user wants to..." provides a concrete when-clause with specific trigger scenarios. Matches the anchor for clearly and explicitly answering both.

5 / 5

Trigger Term Quality

Natural trigger phrasings like "check their Discord", "list servers or channels", "read or search messages in trading, crypto, or market communities", and "what a Discord community is saying about a ticker or coin" map well to what a user would actually say. A few natural variants (e.g. "Discord messages", "market sentiment") are absent, so it falls just short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

A distinct niche — read-only Discord access for financial research via opencli/CDP — with triggers ("trading, crypto, or market communities", "ticker or coin") that no generic messaging or research skill would claim. Minimal conflict risk.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
himself65/finance-skills
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.