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

E2008 Electrical Continuity Check

ASecurity

Use when a continuity run has to be accepted, sentenced or repeated. Verify that every circuit on a photovoltaic assembly control drawing actually conducts, under ECSS-E-ST-20-08C clause 5.5.3.3.2: check each reading against the test current, temperature and probe technique the drawing imposes, strip the probe leads from a two-wire reading or refuse to grade it, refer the resistance back to the reference temperature before comparing it with the circuit limit, separate a degraded joint from a ...

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

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 e2008-electrical-continuity-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E2008 Electrical Continuity Check?

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

Security grade badge for E2008 Electrical Continuity Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e2008-electrical-continuity-check/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e2008-electrical-continuity-check)

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

Download with Pro
Files
SKILL.md
---
name: e2008-electrical-continuity-check
description: "Use when a continuity run has to be accepted, sentenced or repeated. Verify that every circuit on a photovoltaic assembly control drawing actually conducts, under ECSS-E-ST-20-08C clause 5.5.3.3.2: check each reading against the test current, temperature and probe technique the drawing imposes, strip the probe leads from a two-wire reading or refuse to grade it, refer the resistance back to the reference temperature before comparing it with the circuit limit, separate a degraded joint from a true open circuit, and account for every drawing circuit nobody probed. Trigger: ecss, e-st-20-electrical-scope, photovoltaic-assembly-continuity-check, control-drawing-circuit-limit, four-wire-continuity-measurement, continuity-temperature-correction, open-circuit-versus-degraded-joint, continuity-coverage-accounting."
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-20-electrical-scope, e2008-electrical-continuity-check, photovoltaic-assembly-continuity-check, control-drawing-circuit-limit, four-wire-continuity-measurement, continuity-temperature-correction, open-circuit-versus-degraded-joint, continuity-coverage-accounting]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Photovoltaic — Electrical Continuity Check (space-systems/ecss/e2008-electrical-continuity-check)

Use when the task is the continuity check of ECSS-E-ST-20-08C clause
5.5.3.3.2 -- showing that every circuit of a photovoltaic assembly conducts,
with each reading taken under the conditions the control drawing puts on the
measurement rather than under whatever the bay happened to offer.

## Domain quick reference

- The control drawing is the circuit list. A circuit it declares and nobody
  probed is not a pass; it is missing evidence, and it belongs in the coverage
  accounting next to the readings rather than being silently dropped.
- The drawing's conditions are part of the requirement. Test current,
  temperature and probe technique are stated because the number moves with
  them, so a reading taken outside the stated bands is reported as such even
  when the value itself looks comfortable.
- A two-wire probe measures its own leads. Against a milliohm-class limit the
  leads are the same size as the thing being graded, so such a reading is
  usable only when the lead resistance was measured and declared, and is
  otherwise carried as not evaluated rather than as a pass.
- Metallic resistance moves with temperature, so a reading is referred back to
  the drawing's reference temperature before the comparison. A warm bay
  otherwise turns a compliant harness into a finding, and a cold one hides a
  joint that is already degrading.
- Conducting badly and not conducting at all are different defects. A reading
  over the limit is a joint losing section or a contact going resistive; a
  reading above the declared open threshold, or no reading at all, is a break.
  They lead to different repairs, so they are reported separately.
- Limit edges are inclusive. A circuit landing exactly on its drawing limit is
  a pass, so the comparison absorbs representation error instead of moving the
  limit to make the arithmetic tidy.

## Workflow

1. Validate the control drawing: a non-empty circuit list, unique circuit ids,
   two distinct endpoints per circuit and a positive resistance limit on each.
2. Validate the conditions the drawing imposes -- conductor, reference
   temperature, temperature band, test current band and open threshold -- and
   refuse an inverted band or a reference sitting outside its own band.
3. Match the readings to the drawing: record circuits never probed, circuits
   probed twice with no stated reason, and readings taken on circuits the
   drawing does not list.
4. For each reading, raise the condition findings first: test current or
   temperature outside the declared band, or a two-wire probe against a limit
   it cannot resolve.
5. Strip the probe leads from a two-wire reading using the declared lead
   resistance, and refuse a declared lead resistance larger than the reading.
6. Refer the resistance back to the reference temperature with the conductor
   coefficient, then grade it: continuous, above limit, or open.
7. Roll the circuits up into a campaign verdict -- verified only when every
   declared circuit was probed once and every one of them conducts inside its
   limit -- and report the grouped verdicts, the coverage and every finding.

## Pitfalls

- Calling a buzzed-out circuit a pass because the instrument beeped. The
  drawing sets a resistance limit, and a joint that conducts through ten times
  that limit beeps exactly the same way.
- Grading a milliohm limit from a two-wire reading. The leads and the contact
  are inside the number, so the result says more about the probe than about
  the assembly.
- Comparing a warm reading with a limit written at the reference temperature.
  The correction is small per kelvin and the bands are wide enough that the
  uncorrected comparison flips verdicts near the limit.
- Reporting an open circuit and a high-resistance joint as the same finding.
  One is a break to be re-made, the other a contact to be investigated, and
  merging them sends the wrong technician.
- Treating coverage as an administrative detail. A campaign that probed most
  of the drawing and passed everything it probed is not a verified assembly,
  so unprobed circuits hold the verdict at not evaluated.
- Widening a limit so a reading exactly on it counts as a pass. Edges are
  already inclusive; the tolerance belongs inside the comparison, not in the
  limit.

## Behavior contract (gate 3)

The drawing and condition validation, the probe-technique and lead-resistance
handling, the temperature referral, the three circuit verdicts, the coverage
accounting and the campaign roll-up are exercised by the gate 3 contract test:
scripts/test_e2008_electrical_continuity_check.py against
scripts/e2008_electrical_continuity_check_logic.py (stdlib unittest, offline).
Run: python3 scripts/test_e2008_electrical_continuity_check.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 →