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

Q7028 Conductor Repair

ASecurity

Design the repair of a broken, cut or lifted conductor on a printed-circuit-board assembly. Use when a track is open and the method, the wire and the bonding still have to be worked out: it chooses between a lap-soldered replacement segment and an insulated jumper from the gap length and the track width, refuses a break past the reach of either, computes the overlap each lap end needs, sizes the jumper from the circuit current and a current-density derating, spaces the bonds along the unsuppo...

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

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 q7028-conductor-repair --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q7028 Conductor Repair?

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

Security grade badge for Q7028 Conductor Repair
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q7028-conductor-repair/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q7028-conductor-repair)

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

Download with Pro
Files
SKILL.md
---
name: q7028-conductor-repair
description: "Design the repair of a broken, cut or lifted conductor on a printed-circuit-board assembly. Use when a track is open and the method, the wire and the bonding still have to be worked out: it chooses between a lap-soldered replacement segment and an insulated jumper from the gap length and the track width, refuses a break past the reach of either, computes the overlap each lap end needs, sizes the jumper from the circuit current and a current-density derating, spaces the bonds along the unsupported run, and compares the replacement cross-section against the copper it replaces. Trigger: ecss, q-st-70-28c-board-repair, pcb-conductor-repair, pcb-track-lap-solder-splice, pcb-jumper-wire-sizing, pcb-jumper-bond-spacing, pcb-conductor-cross-section."
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, q-st-70-28c-board-repair, q-st-70-28c, q7028-conductor-repair, pcb-conductor-repair, pcb-track-lap-solder-splice, pcb-jumper-wire-sizing, pcb-jumper-bond-spacing, pcb-conductor-cross-section]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Board Repair — Conductor Repair (space-systems/ecss/q7028-conductor-repair)

Use when the task is the conductor method clause of ECSS-Q-ST-70-28C: a track
is open, cut or lifted, and the repair has to restore the path it carried
without becoming the next thing that fails.

## Domain quick reference

- Two things pick the method, not one. A short gap is lapped only if the
  surviving track is also wide enough to solder a replacement segment onto; a
  fine track takes a jumper however small the break, because there is nowhere
  to make the joint.
- The lap overlap scales with the track it lands on, with a floor. A wide
  track needs a proportionally longer overlap to carry the joint, and a very
  fine track still needs a minimum length of contact regardless of how narrow
  it is.
- The replacement segment is longer than the gap by both overlaps. Cutting it
  to the gap is the commonest way a lap repair ends up with no joint at either
  end.
- A jumper is sized from current, not from what is on the bench. Wire
  cross-section carries a current density, that density is derated on a
  repaired board, and the thinnest wire whose derated capacity still covers
  the circuit current is the one to use — thicker wire is stiffer and pulls on
  its terminations.
- An unsupported jumper run is a vibration problem. Bonds along the route hold
  it down, and the count follows from the length: every span up to the
  unsupported limit needs an end, so the bonds are one more than the spans.
- The repaired path must not be thinner than the original. A fine jumper
  across a wide power track restores continuity and moves the weakest point to
  the repair, which is why the two cross-sections are compared rather than
  assumed.
- A board only carries so many jumpers before it stops being a repaired board.
  The count is held per board, not per repair, so the fifth jumper is visible
  to the person approving the first.
- Past the reach of a jumper there is no method at all, and saying so is the
  output. Stretching a jumper across the board is not a longer repair, it is
  an unqualified one.

## Workflow

1. Take the gap and the track width; refuse the repair outright where the gap
   is past what a jumper may span.
2. Choose a lapped replacement segment where the gap is short and the track is
   wide enough to solder to; otherwise choose a jumper and say which of the
   two drove it.
3. For a lap joint, compute the overlap from the track width against its
   floor, and the replacement segment length as the gap plus both overlaps.
4. For a jumper, size the wire from the circuit current against the derated
   capacity of each available gauge, thinnest first.
5. Count the bonds along the jumper route from the unsupported-run limit, and
   check the route length and the board's jumper count.
6. Compare the replacement cross-section against the original track copper and
   flag a repair that would be the new weakest point.
7. Return the repair with every finding; ready only when there are none.

## Pitfalls

- Choosing the method on gap length alone. The gap is short so the repair is
  lapped, the track is too fine to hold a joint, and the splice lifts on the
  first thermal cycle.
- Cutting the replacement segment to the size of the gap. There is no overlap
  left at either end and the joint is a butt joint made with solder.
- Grabbing the wire that is already stripped on the bench. It is either too
  thin for the current or stiff enough to lever its own terminations off the
  board.
- Running a jumper point to point and bonding only the ends. The span in
  between resonates, and the failure appears in vibration testing with no
  visible cause at either termination.
- Jumpering a power track with signal wire. Continuity is restored, the board
  passes test, and the repair is now the current-limiting element in the path.
- Counting jumpers per repair event. Five separate approvals each added one,
  nobody ever saw the total, and the board is a wiring loom.

## Behavior contract (gate 3)

Method selection from gap and track width, the lap overlap floor and segment
length, gauge selection against a derated current density, bond counting over
the unsupported run, the per-board jumper count and the replacement
cross-section comparison are exercised by the gate 3 contract test:
scripts/test_q7028_conductor_repair.py against
scripts/q7028_conductor_repair_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_q7028_conductor_repair.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 →