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

Q7026 Tool Operator Checks

ASecurity

Evaluate the operator go and no-go gauge check on a crimp tool and the logbook entry recording it under ECSS-Q-ST-70-26C, then bound the crimps made since the last good check. Use when a shift starts, or a gauge check fails and the affected production run has to be scoped. Reads the pin pair as pass, die-undersize, die-worn-open or an untrustworthy gauge set, names every missing logbook field, releases or holds the tool, and spans the quarantine back to the last passing check rather than to t...

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

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 q7026-tool-operator-checks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q7026 Tool Operator Checks?

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

Security grade badge for Q7026 Tool Operator Checks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q7026-tool-operator-checks/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q7026-tool-operator-checks)

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

Download with Pro
Files
SKILL.md
---
name: q7026-tool-operator-checks
description: "Evaluate the operator go and no-go gauge check on a crimp tool and the logbook entry recording it under ECSS-Q-ST-70-26C, then bound the crimps made since the last good check. Use when a shift starts, or a gauge check fails and the affected production run has to be scoped. Reads the pin pair as pass, die-undersize, die-worn-open or an untrustworthy gauge set, names every missing logbook field, releases or holds the tool, and spans the quarantine back to the last passing check rather than to the shift start. Trigger: ecss, q-st-70-26, crimp-go-no-go-gauge-check, crimp-tool-logbook-entry, crimp-operator-release-check, crimp-quarantine-span, crimp-tool-hold."
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-70-26-crimping-scope, q7026-tool-operator-checks, crimp-go-no-go-gauge-check, crimp-tool-logbook-entry, crimp-operator-release-check, crimp-quarantine-span, crimp-tool-hold]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Crimping — Operator Checks and Tool Logbooks (space-systems/ecss/q7026-tool-operator-checks)

Use when the task is the operator-facing half of the ECSS-Q-ST-70-26C
tooling clause — the go and no-go check made before a crimp tool is
used, the logbook entry that records it, and what a failed check does
to the crimps already produced.

## Domain quick reference

- The gauge check is two observations, not one. The go pin has to enter
  the closed die and the no-go pin has to be refused by it. Only the
  pair is a pass.
- Each single failure names a wear direction. A go pin refused means
  the die is closing undersize; a no-go pin accepted means it has worn
  open. They are different repairs, and folding them into one "failed"
  loses the only diagnosis available at the bench.
- Both pins reading wrong at once is not a very bad tool. It is a gauge
  set that cannot be trusted, and the next action is to change gauges,
  not to condemn the tool.
- A check that was not recorded did not happen. The entry carries the
  tool, the operator, the time, the gauge set and the crimp counter
  reading, and a missing field is named so the person holding it can
  supply it rather than the entry being rewritten from memory.
- Release is the conjunction of a passing gauge and a complete entry. A
  good check with no counter reading releases nothing, because the
  evidence that would bound a later failure does not exist.
- The counter reading is what makes a failed check actionable. The
  suspect crimps are the ones made since the last passing check, not
  since the shift began. Quarantining the whole shift scraps good work;
  quarantining from the last check when that check also failed misses
  bad work.
- With no earlier passing check anywhere in the run, the span is open
  at the bottom and has to say so.

## Workflow

1. Read the go and no-go pin pair into one verdict: pass, die
   undersize, die worn open, or an untrustworthy gauge set.
2. Name every required logbook field that is missing, and separately
   every one present but unusable — a blank operator, a timestamp that
   is not a timestamp, a negative counter.
3. Decide release as a conjunction: complete entry, passing gauge, tool
   not already on hold. Collect every reason; do not stop at the first.
4. Validate the run as a run: one tool, entries in time order, a
   counter that never goes backwards.
5. For each failing check, walk back to the nearest earlier passing
   check and take the counter difference as the suspect span.
6. With no earlier passing check, report the span as open at the bottom
   rather than measuring it from the first entry as if that were good.
7. Roll the shift up: releases, holds, every quarantine with the index
   that raised it, crimps affected, crimps produced and the fraction.

## Pitfalls

- Recording one pin result. A tool that passes the go pin and also
  swallows the no-go pin reads as a pass on half the evidence.
- Collapsing undersize and worn-open into a single failure, which sends
  the tool for the wrong repair.
- Condemning a tool on a gauge set that contradicted itself.
- Releasing on a good gauge with a half-filled logbook. The counter
  reading is the whole value of the entry.
- Quarantining back to the shift start by default, which scraps work
  that a passing check already covered.
- Quarantining back to a check that had itself failed, which leaves bad
  crimps outside the span.

## Behavior contract (gate 3)

Gauge pin reading, logbook gap naming, the release conjunction, run
validation for tool identity, time order and counter monotonicity,
quarantine spans bounded by the last passing check and the open case,
and the shift roll-up with its quarantine fraction are exercised by the
gate 3 contract test:
scripts/test_q7026_tool_operator_checks.py against
scripts/q7026_tool_operator_checks_logic.py (stdlib unittest, offline).
Run:
python3 scripts/test_q7026_tool_operator_checks.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 →