Hum Discourse

What it does

When your agent uses it

• The user needs to analyze how a text frames an issue
• Uncover hidden assumptions in language
• Examine power dynamics in communication
• Deconstruct media/corporate/political messaging — even if they say whats really being said here

Example prompts

• “s really being said here”
• “how is this framing the issue”
• “analyze the language in this document”
• “/hum-discourse”

Workflow steps

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

1. 1Framing: How is the issue defined? What metaphors are used? What's included/excluded?
2. 2Subject positions: Who is positioned as agent (active doer) vs patient (passive receiver)?
3. 3Presupposition: What is taken for granted without being stated?
4. 4Intertextuality: What other texts/discourses does this reference or draw upon?
5. 5Power relations: Whose voice is amplified? Whose is silenced?

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. 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 (its code samples are markdown).

  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

Hum Discourse loads about 1.3k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 122 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~122

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.1k

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

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 asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 446 words, ~1,326 tokens.

name

hum-discourse

description

Apply discourse analysis to examine how language constructs meaning, power relationships, and social reality in texts and communications. Use this skill when the user needs to analyze how a text frames an issue, uncover hidden assumptions in language, examine power dynamics in communication, or deconstruct media/corporate/political messaging — even if they say 'what's really being said here', 'how is this framing the issue', or 'analyze the language in this document'.

metadata.category

WP-19 文學院/人文

metadata.tags

humanities, discourse-analysis, critical-analysis, language

IRON LAW: Language Constructs Reality, Not Just Describes It

The choice of words is never neutral. "Restructuring" vs "layoffs",
"enhanced interrogation" vs "torture", "undocumented workers" vs
"illegal aliens" — same events, different realities constructed.

Discourse analysis examines WHAT language does, not just what it says.

# Discourse Analysis: {Text/Document}

## Context
- Producer: {who created this text}
- Audience: {intended recipients}
- Purpose: {stated and unstated goals}
- Genre: {press release / policy doc / speech / ad}

## Framing Analysis
| Element | In the Text | Alternative Framing | Effect |
|---------|------------|-------------------|--------|
| {key term} | "{actual language}" | "{what could have been said}" | {how this shapes perception} |

## Subject Positions
- Agent (active): {who does things}
- Patient (passive): {who has things done to them}
- Absent: {who is not mentioned}

## Presuppositions
- {what the text assumes without stating}

## Power Analysis
- This framing benefits: {who}
- This framing disadvantages: {who}

## Key Findings
{What the discourse analysis reveals that a surface reading misses}

© asgard-ai-platform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in hum-discourse of asgard-ai-platform/skills.

• SKILL.md
• examples/sample_scenario.md
• references/cda-framework.md

Open the folder on GitHubat commit 4e7f4f8