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
  • 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.

Back to skills

Disclosure Gate

ASecurity

Enforces compliance and disclosure rules from your company-context. This is a load-bearing gate. Getting it wrong creates legal/compliance exposure. The skill is deliberately conservative: when in doubt, require disclosure.

7 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add unempyd/revenueos --skill disclosure-gate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Disclosure Gate?

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

Security grade badge for Disclosure Gate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/unempyd-disclosure-gate/badge)](https://www.skillsdirectory.com/skills/unempyd-disclosure-gate)

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

Download Zip
Files
SKILL.md
---
name: disclosure-gate
trigger: sub-skill, called by every content skill
load-context: identity, team-and-relationships, preferences-and-constraints
inputs: Draft text + voice + intended publish surface
sub-skills: none (leaf skill)
ends-with: Pass | Fail boolean + suggested disclosure language if Fail
model: claude-haiku-4-5
---

# disclosure-gate

Enforces compliance and disclosure rules from your company-context. This is a load-bearing gate. Getting it wrong creates legal/compliance exposure. The skill is deliberately conservative: when in doubt, require disclosure.

## The constraint

Your company likely has compliance constraints that affect external content. Common categories:

- **Investor / partner indirect financial interest.** If a partner or customer is also an investor (directly or via affiliated entity), public endorsements require disclosure.
- **Customer NDAs.** Some customers don't permit naming.
- **Regulated industry constraints.** Healthcare, financial services, education, government, defense.
- **Pricing transparency restrictions.** Public pricing claims during certain periods.

Document the specific entities and the required disclosure language in `company-context/preferences-and-constraints.md` and `company-context/team-and-relationships.md`. This skill reads them.

## Trigger entities

Scan draft text for any mention of:

- Your investors (named, including any affiliated entities)
- Your customers in the "named-but-undisclosed" category
- Specific executives at investor/customer entities (named individuals)
- Any compliance-sensitive language patterns specific to your industry

(You define this list in your team-and-relationships.md file.)

## Pass / fail logic by surface

| Surface | If sensitive entity mentioned | Verdict |
|---|---|---|
| Internal Slack | Always OK | PASS |
| Internal email to VP / ops lead | Always OK | PASS |
| Founder LinkedIn (public) | Quote/endorsement: require disclosure. Mention without endorsement: REVIEW | PASS w/ disclosure required \| REVIEW |
| Company LinkedIn | Quote/endorsement: require disclosure. Logo use: require disclosure. Name-drop only: REVIEW | PASS w/ disclosure \| REVIEW |
| Website testimonial | Always require disclosure | PASS w/ disclosure \| FAIL if not present |
| Press release | Always require disclosure OR escalate to legal/compliance | FAIL until cleared |
| Closed-door event invitation | OK (allowed category for most disclosure frameworks) | PASS |
| Pitch deck (private) | OK with disclosure language in deck footer | PASS |
| Sales reference call (1:1) | OK | PASS |

## Endorsement vs mention classification

Endorsement triggers stricter rules. The skill must classify which it is.

**Endorsement:**

- Direct quote from an investor/partner/customer employee about your product/value
- Testimonial language ("[Company] is helping us...", "we use [Your Co] to...")
- Logo placement on website/deck implying customer status
- Use of the entity's name in a way that implies they vouch for you

**Mention (no endorsement):**

- Cited as an event co-host or panel attendee (factual)
- Listed as one example of "[industry]" or "[stage]" generically
- Historical context ("Our CEO worked at [Company] before founding us")

## Required disclosure language

When disclosure required, insert appropriate format for the surface:

**Long form (blog, press release, pitch deck footer):**

> *[Entity] has [direct/indirect] financial interest in [Your Company] through [relationship]. This relationship has been disclosed in accordance with [Entity]'s compliance and corporate communications policies.*

**Short form (LinkedIn post, social):**

> *Disclosure: [Entity] holds [direct/indirect] financial interest in [Your Company].*

**Footnote/inline:**

> ¹ [Entity] holds [direct/indirect] financial interest in [Your Company]; disclosed per their compliance policy.

Customize per your specific compliance requirements. Get the exact language pre-cleared by the entity's compliance team if applicable.

## Escalation path

When the skill returns REVIEW or FAIL:

1. Block the draft from auto-publish
2. Set draft.disclosure_gate_passed = false
3. Write audit_log entry with offending span quoted
4. Slack-DM the VP: "Disclosure review needed on draft {id}. Reason: {classification}. Suggested action: {add disclosure | escalate to legal/compliance | rewrite to avoid mention}."
5. If VP doesn't respond in 24h on critical timeline: escalate to ops lead

## Examples

**Pass:**

> "At our event this week, our CTO moderated a panel with [Investor] partner [Name] and [other panelist]. The conversation focused on..."
>
> → PASS (factual mention of co-panelists, no endorsement, no claim about [Investor]'s use of your product)

**Pass with disclosure required:**

> "Working with [Investor] has shown us how seriously enterprise teams treat..."
>
> → PASS with disclosure required (endorsement-shaped language) — insert short-form disclosure

**Fail until cleared:**

> "[Investor] says [Your Product] is the best platform in the market."
>
> → FAIL (direct endorsement quote, blocks publish until compliance cleared)

## Why conservative

False positives cost a 5-minute Slack to the VP. False negatives cost the relationship. Erring on the side of "require disclosure" protects the relationship.

Attribution

unempydunempyd
View sourceMore from unempyd →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →