verify-after-every-action
After any change, verify it took effect; if not, fix now.
Skill by GentechLabs
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/gentechlabs-verify-after-every-action
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verify-after-every-action
What's inside
- Skill name
verify-after-every-action- Description
- After any change, verify it took effect; if not, fix now.
- License
- unknown
- Instructions
- 812 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- body: 812 lines (spec recommends under 500)
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from GentechLabs/genTech-agent-skills
- 0.566score
group-handoff-mesh
GentechLabs
Use when moving work between GenTech groups — V4 mesh.
SkillAFreshness: AClaude Code +9 - 0.561score
model-optimized-cron-config
GentechLabs
Two-tier model routing: DeepSeek V4 Flash (OpenCode Go) for routine runs, GLM-5.2 (OpenCode Go) for audits/builds.
SkillAFreshness: AClaude Code +9 - 0.559score
telegram-member-recovery
GentechLabs
Use when a Telegram member was removed and cannot rejoin.
SkillAFreshness: AClaude Code +9 - 0.559score
agent-to-agent-messaging
GentechLabs
Use when one agent must reach another agent — pick the path, prove it landed, and never report a wake that never happened.
SkillAFreshness: AClaude Code +9 - 0.559score
multi-agent-build-queue
GentechLabs
Shared build queue for a multi-agent fleet — per-department views, a canonical count every agent can quote, and the failure modes that make a queue look like…
SkillAFreshness: AClaude Code +9 - 0.556score
auto-fix-preflight
GentechLabs
Detect → Fix → Verify → Report pattern for preflight checks.
SkillAFreshness: AClaude Code +9 - 0.556score
cron-health-standard
GentechLabs
Fleet-wide standard for cron health: every job declares its INTENT, every ring ships a self-healing sentinel that retries once before it speaks, alerts ONCE…
SkillAFreshness: AClaude Code +9 - 0.555score
bug-class-self-audit
GentechLabs
Use when hardening a system or after fixing bugs.
SkillAFreshness: AClaude Code +9 - 0.548score
harness-self-evolution
GentechLabs
Running the Harness Evolution / Critic self-improvement cycle — addressing unaddressed critiques, gating result:ok on real metrics, editing harness scripts…
SkillAFreshness: AClaude Code +9 - 0.546score
falsifiable-tests
GentechLabs
Use when writing or debugging a test, guard, or assertion.
SkillAFreshness: AClaude Code +9 - 0.544score
cron-truth-layer
GentechLabs
Universal data verification pattern for cron jobs — every job verifies truth before acting.
SkillAFreshness: AClaude Code +9 - 0.524score
signal-watcher-monitor
GentechLabs
Pattern for two independent cron jobs that communicate through a JSON state file bridge: a Signal cron generates entries/exits, a Watcher cron monitors…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 2, 2026 (27 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from GentechLabs
- 0.566score
group-handoff-mesh
GentechLabs
Use when moving work between GenTech groups — V4 mesh.
SkillAFreshness: AClaude Code +9 - 0.561score
model-optimized-cron-config
GentechLabs
Two-tier model routing: DeepSeek V4 Flash (OpenCode Go) for routine runs, GLM-5.2 (OpenCode Go) for audits/builds.
SkillAFreshness: AClaude Code +9 - 0.559score
telegram-member-recovery
GentechLabs
Use when a Telegram member was removed and cannot rejoin.
SkillAFreshness: AClaude Code +9 - 0.559score
agent-to-agent-messaging
GentechLabs
Use when one agent must reach another agent — pick the path, prove it landed, and never report a wake that never happened.
SkillAFreshness: AClaude Code +9 - 0.559score
multi-agent-build-queue
GentechLabs
Shared build queue for a multi-agent fleet — per-department views, a canonical count every agent can quote, and the failure modes that make a queue look like…
SkillAFreshness: AClaude Code +9 - 0.556score
auto-fix-preflight
GentechLabs
Detect → Fix → Verify → Report pattern for preflight checks.
SkillAFreshness: AClaude Code +9
Cite this page
verify-after-every-action skill. Agent Mart. https://agentmart.dev/skills/gentechlabs-verify-after-every-action (last updated 2026-10-24)