Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Communication Clarity Audit

ASecurity

Audits a communication for places where the message will be lost, misread, or misunderstood — before it's sent. Triggers: 'clarity audit', 'will this be understood', 'check my message', 'edit for clarity', 'where will this be misread'.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill communication-clarity-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Communication Clarity Audit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Communication Clarity Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-communication-clarity-audit/badge)](https://www.skillsdirectory.com/skills/rondoflow-communication-clarity-audit)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: communication-clarity-audit
description: "Audits a communication for places where the message will be lost, misread, or misunderstood — before it's sent. Triggers: 'clarity audit', 'will this be understood', 'check my message', 'edit for clarity', 'where will this be misread'."
---

# Communication Clarity Audit

Most clarity failures are invisible to the sender because the sender knows what they meant.
The receiver does not have that context, and the gap between what was meant and what is
read is where miscommunication lives. This audit finds that gap by reading the message as
the receiver would — without access to the sender's intent.

---

## Your Process

**Step 1: Read from the Receiver's Perspective**
Do not read this as the writer who knows what was meant. Read it as someone receiving it
cold. What is actually on the page? This requires a deliberate perspective shift — it is
the hardest step and the most important one.

**Framing check:** Confirm the specific message, audience, and goal before continuing. State what you've identified — the actual content being audited, who it's addressed to, and what it's trying to achieve — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the message, its intended audience, and its goal]. Is that right?"
- **Header:** "Framing"
- **Options:**
  - **Yes — proceed** — framing is correct
  - **Adjust** — one element is off; user will correct it before you continue
  - **Reframe** — different situation than read; incorporate the correction before proceeding

**Step 2: Structure Check**
Can the main point be identified within 10 seconds? If not, the structure is obscuring it.
Is the structure serving the reader or the writer's thinking process? The two are often
different.

**Step 3: Jargon Inventory**
List every term or acronym that requires context the reader may not have. Each one is a
potential comprehension failure. Include terms that feel obvious — "obvious" is always
relative to what the writer knows.

**Step 4: Assumption Inventory**
What must the reader already know or believe for this message to make sense? State each
assumption explicitly. For each: does this reader have this context? If not, the message
has a gap.

**Step 5: Ask — Is It Clear?**
Is there a clear action or next step? Is it clear who does what, by when? A message that
informs without directing produces nothing. A message that directs ambiguously produces
the wrong thing.

**Step 6: Name the Most Likely Misreading**
**Before narrowing:** Show the complete set of misreadings identified across all steps to the user first. Use `AskUserQuestion`:
- **Question:** "I've identified [N] potential misreadings. Before I select the most likely one, are there any you'd flag as especially important, or any I've missed?"
- **Header:** "Prioritise"
- **Options:**
  - **Proceed with your selection** — the set looks right
  - **Flag one** — user will name a specific misreading to prioritise
  - **Add a missing one** — user will describe it

State the single most plausible way this message will be misread or misunderstood by a
reasonable receiver. This is the most valuable output — it is the failure that will
actually happen if the message is sent as written.

---

## Human Check-in

Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask:

- **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
- **Header:** "Scope"
- **Options:**
  - **Full analysis** — Complete all steps, reasoning shown throughout
  - **Key findings only** — Bottom-line output, skip step-by-step detail
  - **Breakpoints only** — Where this message will be misread or lost, skip what's already clear
  - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing

Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.

## Output Format

**Issues found:**

| Category | Issue | Severity (High/Med/Low) | Edit |
|----------|-------|------------------------|------|
| Structure | | | |
| Jargon | | | |
| Assumptions | | | |
| Ask/Action | | | |

**Most likely misreading:**
> [Concrete statement of how a reasonable receiver will misread this — and what they
> will do or believe as a result]

**Priority edits:**
1. [Highest-impact change]
2. [Second highest]
3. [Third]

---

## Notes

A single clear next step with a named owner and a deadline eliminates more miscommunication
than any amount of structural or vocabulary editing. If the ask is ambiguous, fix that
before anything else.

---

## What's Next

After delivering this output, use `AskUserQuestion` to offer the next move:

- **Question:** "Clarity audited. What's next?"
- **Header:** "Next"
- **Options:**
  - `/writing-line-editing` — Fix the clarity issues the audit identified
  - `/communication-objection-mapping` — Address the objections hiding behind confusing points
  - `/writing-restructure` — Restructure if the clarity issues are structural
  - **Done** — Wrap up and synthesise what we have so far

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →