Agent skill

Process Discord Suggestions

by deadlock-mod-manager in deadlock-mod-manager/deadlock-mod-manager

Fetches forum suggestion threads from the Deadlock Mod Manager Discord via the user-discord-mcp, classifies each as MOD/SKINREQUEST, MODMANAGERFEATURE, or OTHER, writes one markdown file per thread…

GPL-3.0Auto-check passedAgent Workflows

Install Process Discord Suggestions

skills CLI
$ npx skills add deadlock-mod-manager/deadlock-mod-manager --skill process-discord-suggestions -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install deadlock-mod-manager/deadlock-mod-manager process-discord-suggestions --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/deadlock-mod-manager/deadlock-mod-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/process-discord-suggestions .claude/skills/process-discord-suggestions && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
process-discord-suggestions
GitHub stars
477
Token cost
~1.7k tokens
SKILL.md length
818 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
GPL-3.0

At a glance

Fetches forum suggestion threads from the Deadlock Mod Manager Discord via the user-discord-mcp, classifies each as MOD/SKINREQUEST, MODMANAGERFEATURE, or OTHER, writes one markdown file per thread…

  • Works in 3 steps: A single # heading with the thread title… → The text of the first message (starter… → If follow-up messages add material…
  • The user runs a suggestion sweep
  • SKILL.md covers Constants, Prerequisite IDs, Classification (exactly one… and Output layout (repository root), plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Process Discord Suggestions is an agent skill from deadlock-mod-manager/deadlock-mod-manager. Fetches forum suggestion threads from the Deadlock Mod Manager Discord via the user-discord-mcp, classifies each as MOD/SKINREQUEST, MODMANAGERFEATURE, or OTHER, writes one markdown file per thread under .suggestions/ with author metadata, and applies the processed forum tag. Use when the user runs a suggestion sweep, "process Discord suggestions", "export suggestions from Discord", "tag processed suggestions", or when integrating the Discord MCP with the suggestions backlog workflow.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Discord and Model Context Protocol. The repository describes itself as: A mod manager for the Valve game Deadlock. The licence is GPL-3.0.

When your agent uses it

  • The user runs a suggestion sweep
  • Process Discord suggestions
  • Export suggestions from Discord
  • Tag processed suggestions

Example prompts

  • “process Discord suggestions”
  • “export suggestions from Discord”
  • “tag processed suggestions”
  • “/process-discord-suggestions”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. A single # heading with the thread title (same as title is fine).
  2. The text of the first message (starter post) as the main content.
  3. If follow-up messages add material constraints or acceptance criteria, add a ## Thread notes section with a short bulleted summary only…

What it can do on your machine

Read from SKILL.md and the folder at commit e5a8f5e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Process Discord Suggestions loads about 1.7k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 818 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from deadlock-mod-manager/deadlock-mod-manager at commit e5a8f5e, republished under its GPL-3.0 licence (© deadlock-mod-manager). 818 words, ~1,703 tokens.

Download SKILL.mdSave it as .claude/skills/process-discord-suggestions/SKILL.md (or your agent's skills folder).
name
process-discord-suggestions
description
Fetches forum suggestion threads from the Deadlock Mod Manager Discord via the user-discord-mcp, classifies each as MOD/SKIN_REQUEST, MOD_MANAGER_FEATURE, or OTHER, writes one markdown file per thread under .suggestions/ with author metadata, and applies the processed forum tag. Use when the user runs a suggestion sweep, "process Discord suggestions", "export suggestions from Discord", "tag processed suggestions", or when integrating the Discord MCP with the suggestions backlog workflow.

Process Discord Suggestions (MCP)

End-to-end workflow for an agent with access to user-discord-mcp (call_mcp_tool with server user-discord-mcp). Read each tool’s JSON schema under the MCP tools/ folder before calling it.

Constants

KeyValue
Processed tag ID1497626100849840250

Do not change this ID unless the server’s forum tag is recreated.

Prerequisite IDs

You need the guild (server) ID and the forum channel ID for the suggestions board.

  • If the user does not pass IDs: find_channel with guildId (if known) and channelName matching the forum; or list_forum_channels with guildId and pick the correct channel.
  • If tools require channelId / guildId and the user can provide them from Discord (Developer Mode: copy ID), prefer those to avoid name collisions.

Classification (exactly one per thread)

ValueMeaning
MOD/SKIN_REQUESTIn-game visuals, models, VPK/GameBanana content, sound packs, map/mod content for Deadlock itself.
MOD_MANAGER_FEATUREDMM / Deadlock Mod Manager app: UI, install flow, API, Tauri, settings, mod library, sync, error handling.
OTHEROff-topic, meta Discord, unparseable, or not fitting the two above (still export and tag if processed).

Rules

  • If the first message mixes topics, pick the primary user ask.
  • When uncertain between mod content and app feature, use MOD_MANAGER_FEATURE if the text is about how the manager works; otherwise MOD/SKIN_REQUEST for what to add in-game.

Output layout (repository root)

Create the directory tree on first use:

text
.suggestions/
  mod-skin-request/     # maps to category MOD/SKIN_REQUEST
  mod-manager-feature/  # maps to category MOD_MANAGER_FEATURE
  other/                # maps to category OTHER

Files: one file per thread, path:

.suggestions/<subfolder>/{threadId}.md

Use the Discord thread (post) ID as the filename stem so re-runs do not duplicate.

File format

Each file is valid Markdown with YAML front matter, then the thread body for humans to edit later.

Front matter (required fields)

  • title: Thread name as shown in Discord.
  • thread_id: Snowflake of the thread / forum post.
  • forum_channel_id: Parent forum channel ID.
  • guild_id: Guild ID, if available from the tool context.
  • author_username: Display name or username at time of export (best effort).
  • author_id: Author snowflake of the first (parent) post.
  • parent_message_id: ID of the first message in the thread, if returned by read_messages.
  • category: One of MOD/SKIN_REQUEST, MOD_MANAGER_FEATURE, OTHER (match table above, not the folder slug).
  • processed_tag_id: 1497626100849840250
  • exported_at: ISO-8601 UTC timestamp when the file was written.

Body

  1. A single # heading with the thread title (same as title is fine).
  2. The text of the first message (starter post) as the main content.
  3. If follow-up messages add material constraints or acceptance criteria, add a ## Thread notes section with a short bulleted summary only when it changes meaning; do not dump full history by default to keep files reviewable.
Show full SKILL.md (407 more words)Show less

Fetch workflow

  1. List threads: list_forum_posts with channelId (forum). If the result is known to be active-only, note that archived threads may be missing. Optionally list_active_threads with guildId to cross-check, then only process IDs that belong to the suggestions forum.
  2. Filter: For each candidate thread, determine if it is already “processed”:
    • If the list payload includes applied_tags / tag IDs, skip when 1497626100849840250 is already present.
    • If tag membership is not visible, read_messages is still used for export; before tagging, merge tag IDs with care (see next section).
  3. Read content: read_messages with channelId set to the thread ID, count as needed (max 100 per call; paginate with before if the thread is long; include enough to classify the starter and optional notes for ## Thread notes).
  4. Classify using the table above; assign the category and target subfolder.
  5. Write the file under .suggestions/... as specified.
  6. Tag the thread: modify_forum_post with postId equal to the thread ID and tagIds a comma-separated list of tag snowflakes. Merging tags: the API sets the full set. If the listing response for the thread includes existing tag IDs, set tagIds to the union of those IDs and 1497626100849840250 (de-duplicated). If existing tags are unknown, prefer asking the user before applying a tag that might clear other tags; if the user has confirmed replace-with-processed-only is OK, you may set tagIds: "1497626100849840250" only.
  7. Idempotency: If a file for {threadId}.md already exists in the correct subfolder and the thread already has the processed tag, skip writing and re-tagging unless the user asked for a full refresh.

Ordering and rate limits

Process threads in a stable order (e.g. ascending thread_id or as returned). Space MCP calls reasonably; on failures, log which threadId failed and continue or retry that ID once.

Privilege note

modify_forum_post requires the bot account behind user-discord-mcp to have Manage Threads and permission to set forum tags in that channel. If tagging fails, still write the export file and report the error so a moderator can tag manually.

What not to do

  • Do not store bot tokens in the repo or in front matter.
  • Do not replace this skill with raw instructions that bypass MCP tool schemas; always read the tool descriptor before the first use in a session.

Optional follow-up (not automatic)

  • Add .suggestions/ to .gitignore if exports should stay local and contain PII.
  • Reconcile OTHER and misclassified files after human review (move file + update front matter category if needed).

© deadlock-mod-manager, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/process-discord-suggestions of deadlock-mod-manager/deadlock-mod-manager.

Open the folder on GitHubat commit e5a8f5e

Compare with similar skills

Process Discord Suggestions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Process Discord Suggestions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Process Discord Suggestions this skilldeadlock-mod-manager/deadlock-mod-manager477—~1.7kAutomated safety check: PassGPL-3.0
Frontmcp Channelsagentfront/frontmcp146—~3.7kAutomated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • Frontmcp Channels

    agentfront/frontmcp

    A skill your agent uses when pushing real-time notifications or events into Claude Code (or another MCP client) sessions, or building two-way chat bridges.

    146 GitHub stars~3.7k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from deadlock-mod-manager/deadlock-mod-manager

All 24 skills in this repo
  • Skill Creator

    deadlock-mod-manager/deadlock-mod-manager

    Create new agent skills following the Agent Skills specification.

    477 GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Create Auth Skill

    deadlock-mod-manager/deadlock-mod-manager

    Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth.

    477 GitHub starsUsed in 4 repos~3.4k tokens
    Auto-check passed
  • Opensrc

    deadlock-mod-manager/deadlock-mod-manager

    Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs.

    477 GitHub stars~910 tokensUpdated today
    Auto-check passed
  • Security Review

    deadlock-mod-manager/deadlock-mod-manager

    Security code review for Tauri/Rust/TypeScript desktop apps and Hono/oRPC APIs.

    477 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Babysit

    deadlock-mod-manager/deadlock-mod-manager

    Stay on one pull request until it is merge-ready, fixing the highest-priority blocker and telling the user when it is green.

    477 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Changeset

    deadlock-mod-manager/deadlock-mod-manager

    Generate a changeset file describing the current PR's changes.

    477 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Process Discord Suggestions

What does Process Discord Suggestions do?

Fetches forum suggestion threads from the Deadlock Mod Manager Discord via the user-discord-mcp, classifies each as MOD/SKINREQUEST, MODMANAGERFEATURE, or OTHER, writes one markdown file per thread…. Process Discord Suggestions is an agent skill from deadlock-mod-manager/deadlock-mod-manager.suggestions/ with author metadata, and applies the processed forum tag.

When should I use Process Discord Suggestions?

Process Discord Suggestions fits situations like: the user runs a suggestion sweep; process Discord suggestions; export suggestions from Discord; tag processed suggestions.

How do I install Process Discord Suggestions in Claude Code?

Run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill process-discord-suggestions -a claude-code`. Or copy the skill folder (.agents/skills/process-discord-suggestions in deadlock-mod-manager/deadlock-mod-manager) into .claude/skills/process-discord-suggestions in your project. Claude Code loads it when a task matches its description.

How do I install Process Discord Suggestions in Codex?

Run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill process-discord-suggestions -a codex`. Or copy the skill folder (.agents/skills/process-discord-suggestions in deadlock-mod-manager/deadlock-mod-manager) into .agents/skills/process-discord-suggestions in your project. Codex loads it when a task matches its description.

Can I use Process Discord Suggestions in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill process-discord-suggestions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/process-discord-suggestions, .gemini/skills/process-discord-suggestions, .github/skills/process-discord-suggestions and .opencode/skills/process-discord-suggestions in your project.

What does Process Discord Suggestions need to run?

SKILL.md names no scripts, command-line tools or credentials: Process Discord Suggestions is instructions for the agent only.

Does Process Discord Suggestions access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Process Discord Suggestions safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Process Discord Suggestions use?

Process Discord Suggestions is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Process Discord Suggestions use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Process Discord Suggestions?

Skills that share tags, products or a category with Process Discord Suggestions: Frontmcp Channels (agentfront/frontmcp, 146 stars), MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Process Discord Suggestions?

deadlock-mod-manager (a GitHub organization) maintains it in deadlock-mod-manager/deadlock-mod-manager, which has 477 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

Source: deadlock-mod-manager/deadlock-mod-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.