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

E1004 Ref Atmosphere

ASecurity

"Use when determining which reference atmosphere model and

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythongit

Works with

claude code

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add ashfordeOU/aero-agent-skills --skill e1004-ref-atmosphere --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E1004 Ref Atmosphere?

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

Security grade badge for E1004 Ref Atmosphere
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e1004-ref-atmosphere/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e1004-ref-atmosphere)

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

Download with Pro
Files
SKILL.md
---
name: e1004-ref-atmosphere
description: "Use when determining which reference atmosphere model and
  inputs apply to a mission atmosphere lookup under ECSS-E-ST-10-04C Annex G:
  map the target body and altitude to the cataloged reference models
  (NRLMSISE-00, JB-2006, and GRAM-class planetary models), select the model
  that matches the analysis purpose (drag prediction, density reference, or
  full-profile engineering) while validating the altitude against that
  model's supported range, and verify every input the selected model needs
  (solar/geomagnetic activity or trajectory fields) is present before the
  model is run; also classifies an Earth altitude into its atmospheric
  regime for scoping. Trigger: ecss, e-st-10-04c, annex g, atmosphere model,
  nrlmsise-00, jb-2006, gram, planetary atmosphere, reference atmosphere,
  drag prediction."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: ecss
    reference-only: true
gated: false
domain: space-systems
pack: space-systems
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: space-systems
  subdomain: ecss
  tags: [ecss, e-st-10-04c, atmosphere, nrlmsise-00, jb-2006, gram, reference-atmosphere]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Space Environment — Reference Atmosphere Data (space-systems/ecss/e1004-ref-atmosphere)

Use when the task is an ECSS-E-ST-10-04C Annex G (informative) reference
atmosphere lookup -- deciding which published atmosphere model covers a
given celestial body, altitude, and analysis purpose, and confirming the
model's activity/trajectory inputs are on hand before it is run.

## Domain quick reference

- Annex G points the engineer at external reference atmosphere models
  rather than defining one: NRLMSISE-00 and JB-2006 are Earth
  thermosphere/exosphere density models used for orbital drag and
  lifetime analysis, each covering an altitude band and each needing
  current solar-activity and geomagnetic-activity inputs to run.
  JB-2006 is the higher-fidelity drag-focused option above its
  altitude floor; NRLMSISE-00 covers a broader density-reference role
  and a lower floor. GRAM-class models (Earth-GRAM, Mars-GRAM,
  Venus-GRAM) give a full surface-to-orbit engineering profile for one
  body, including trajectory-driven inputs (date, latitude,
  longitude, altitude).
- A model only applies within its cataloged altitude range for its
  body; a request outside every cataloged model's range for that body
  has no coverage and must be flagged rather than silently answered
  with the nearest model.
- Model selection follows the analysis purpose: drag prediction on
  Earth prefers JB-2006 where its floor allows, falling back to
  NRLMSISE-00 and then Earth-GRAM; a general density reference prefers
  NRLMSISE-00, falling back to Earth-GRAM; a full-profile need (or any
  non-Earth body, since JB-2006/NRLMSISE-00 are Earth-only) uses the
  GRAM-class model for that body.
- A selected model is not actually runnable until every input it
  requires (solar flux, geomagnetic index, epoch, or trajectory
  position) is on record; a missing input is a finding against the
  lookup, separate from the model-selection step itself.
- Earth altitude additionally classifies into an atmospheric regime
  (troposphere, stratosphere, mesosphere, thermosphere, exosphere),
  useful for scoping which phenomena (e.g. drag-relevant density vs.
  launch-ascent aerodynamics) are in play at a given altitude.

## Workflow

1. Identify the target body and confirm it is one the catalog covers;
   reject an unrecognized body before selecting a model for it.
2. State the analysis purpose (drag prediction, density reference, or
   full-profile engineering) and the altitude of interest; reject a
   negative altitude or an unrecognized purpose.
3. Select the model using the purpose-driven preference order for the
   body, checking each candidate's altitude range in turn; if no
   cataloged model for that body covers the altitude, flag a coverage
   gap rather than forcing the nearest model.
4. Once a model is selected, compare the inputs on hand against that
   model's required-input set; flag each missing input by name.
5. For Earth-altitude scoping, classify the altitude into its
   atmospheric regime alongside the model selection.
6. Aggregate the coverage and input findings for the lookup; the
   lookup is not ready to hand to the model until both are empty.

## Pitfalls

- Picking the nearest cataloged model when the requested altitude is
  actually outside every model's range for that body -- that is a
  coverage gap to report, not an approximation to make silently.
- Treating JB-2006 as available below its altitude floor just because
  NRLMSISE-00 would be -- each model's range is independent and the
  fallback order exists precisely because JB-2006 cannot cover that
  band.
- Using an Earth-only model (NRLMSISE-00, JB-2006) for a non-Earth
  body -- only the body's GRAM-class model applies there regardless of
  purpose.
- Reading "a model was selected" as "the lookup is ready" -- a
  selected model with missing required inputs (solar flux,
  geomagnetic index, trajectory epoch/position) cannot actually be
  run and must still be flagged.

## Behavior contract (gate 3)

The model-range lookup, altitude-in-range check, body-to-model
mapping, purpose-driven selection, required-input gap check, and
altitude-regime classification are exercised by the gate 3 contract
test: scripts/test_e1004_ref_atmosphere.py against
scripts/e1004_ref_atmosphere_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_e1004_ref_atmosphere.py

## Compliance

- ECSS standards are freely downloadable (ESA); cite the source and
  paraphrase per standards-map.yaml.
- compliance: STANDARDS-REF, gated: false.

Attribution

ashfordeOUashfordeOU
View sourceMore from ashfordeOU →
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".

1074701 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', ...

694821 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 →