Skip to content
Back to skills

Communication Doctrine

ASecurity

Bottom Line Up Front (BLUF) and Simplified Technical English (STE) communication doctrine. Enforces zero-latency verdicts in reports and unambiguous, imperative step definitions in plans.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 6, 2026
ai-agentsgosecurity

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned November 6, 2026

npx -y skills add bepaldes/heimdall-agent --skill communication-doctrine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Communication Doctrine?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Communication Doctrine
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bepaldes-communication-doctrine/badge)](https://www.skillsdirectory.com/skills/bepaldes-communication-doctrine)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: communication-doctrine
description: >
  Bottom Line Up Front (BLUF) and Simplified Technical English (STE) communication doctrine.
  Enforces zero-latency verdicts in reports and unambiguous, imperative step definitions in plans.
---

# Communication Doctrine: BLUF & Simplified Technical English (STE)

This skill governs structured communication across Google Antigravity, Claude Code, and OpenAI Codex CLI. It eliminates AI throat-clearing, hidden conclusions, and linguistic ambiguity.

---

## 1. Macro Architecture: Bottom Line Up Front (BLUF)

Always state the decision, status, verdict, or core recommendation in the **first 1–2 sentences** before presenting context, analysis, or supporting steps.

### Schema A: Subagent Scratchpad Handoff (`docs/runs/<task_id>/report.md`)
Every subagent report must open with this exact 3-line block:
```markdown
### Subagent BLUF
- **Status**: SUCCESS | FAILURE | ESCALATED
- **Blast Radius**: [Files modified, tests added/executed, zero dev servers spawned]
- **Deliverable**: [Path to diff, artifact, or commit hash]
```

### Schema B: Code Reviewer & Security Sentinel Verdict (`agents/reviewer.md`)
Every review or audit output must open with this exact verdict block:
```markdown
### Review Verdict: APPROVED | BLOCKED | REVISION_NEEDED
- **Blockers**: <count>
- **Warnings**: <count>
- **Nits**: <count>
- **Mandatory Action**: [1-sentence summary of immediate action required before merge, or "None"]
```

### Schema C: Implementation Plan Header (`docs/designs/`)
Every implementation plan must lead with:
```markdown
### Plan BLUF
- **Goal**: [1 sentence describing exactly what is built]
- **Architectural Approach**: [1-2 sentences on core mechanism]
- **Risk & Blast Radius**: [Low | Medium | High — state key failure modes]
- **Human Approval Gate**: [Required before Phase X | Autonomous non-destructive]
```

---

## 2. Micro Syntax: Simplified Technical English (STE)

Derived from ASD-STE100 principles, STE eliminates ambiguous interpretation, reduces token waste, and guarantees deterministic execution by child subagents.

### Rule 1: Imperative Verb First
Every procedural step must start with an active imperative verb:
* **Approved Verbs**: `Create`, `Modify`, `Assert`, `Verify`, `Delete`, `Run`, `Open`, `Extract`, `Replace`, `Benchmark`.
* **Prohibited**: Passive constructions (*"The file should be updated..."*), conversational requests (*"Let's go ahead and..."*), or hedged steps (*"Consider checking..."*).

### Rule 2: Strict Sentence Length Limits
* **Procedural Steps**: Maximum **20 words** per step. Each step represents exactly one checkable operation.
* **Descriptive Text**: Maximum **25 words** per sentence.

### Rule 3: Banned Ambiguous Qualifiers (The Zero-Vagueness Lexicon)
The following words mask missing specifications and are strictly prohibited in implementation steps and suggested fixes:

| Banned Word | Why Prohibited | STE Replacement Pattern |
| :--- | :--- | :--- |
| `ensure` | Does not specify the mechanism. | `Verify <condition> equals <expected>. If not, <action>.` |
| `properly` | Subjective without testable criteria. | `Assert <field> matches regex <pattern>.` |
| `appropriately` | Defers specification to executor. | State the exact configuration parameter or value. |
| `gracefully` | Vague error handling. | `Catch <ErrorType>, log warning, and return <FallbackValue>.` |
| `as needed` / `as appropriate` | Unbounded scope. | Explicitly list the conditions or omit the step. |
| `robustly` / `seamlessly` | Pure AI marketing filler. | Delete the word. |
| `etc.` | Executor cannot guess remaining items. | List all items exhaustively. |

### Rule 4: Explicit Object Naming (No Floating Pronouns)
Do not use ambiguous pronouns (*"it"*, *"this"*, *"they"*, *"that"*) when referring to code symbols, files, or error states. Always repeat the specific noun:
* *Bad*: *"Read the config and update it so it does not fail when it is missing."*
* *STE*: *"Read `config.json`. If `port` key is missing, assign default port `8080`."*

---

## 3. Communication Checklist

Before finalizing any plan, subagent report, or review output:
- [ ] Verdict or conclusion is on Line 1 (BLUF).
- [ ] Procedural steps start with an approved imperative verb.
- [ ] No procedural step exceeds 20 words.
- [ ] No banned qualifiers (`ensure`, `properly`, `appropriately`, `gracefully`, `as needed`, `etc.`).
- [ ] All code targets and file paths are explicitly named.

Attribution

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

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.