How do I install the Skill Common Sense Engineering skill?

Run npx skillmds@latest add grtninja/skill-common-sense-engineering in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skill Common Sense Engineering safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill Common Sense Engineering?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill Common Sense Engineering free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skill Common Sense Engineering?

grtninja (@grtninja) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill Common Sense Engineering by grtninja

Name: Skill Common Sense Engineering
Rating: 4.2 (5 reviews)
Author: grtninja

Skill Common Sense Engineering

Apply practical sanity checks before and after coding work to prevent avoidable mistakes. Use when verifying dependency surfaces, cleaning generated artifacts, checking privacy policy compliance, auditing artifact hygiene, or ensuring multi-skill chain guardrail evidence is present before claiming readiness.

grtninja Updated Sep 10, 2026

File contents

Common-Sense Engineering

Lightweight sanity layer for day-to-day coding work. Prevents avoidable mistakes by enforcing pre/post checks on every change.

Workflow

Clarify the goal — state the objective in one sentence before choosing tools or edits.
Audit dependency surface — trace related contracts, dependents, and operator-facing surfaces before deciding the implementation boundary.
Execute the change — prefer existing scripts/workflows over ad hoc steps.

Run common-sense checks before concluding:

git status --short
python3 scripts/check_private_data_policy.py
python3 "$CODEX_HOME/skills/skill-arbiter-lockdown-admission/scripts/artifact_hygiene_scan.py" . --fail-on-found

Verify guardrail evidence for multi-skill chains:

test -f /tmp/usage-analysis.json && test -f /tmp/usage-plan.json
test -f /tmp/skill-cost-analysis.json && test -f /tmp/skill-cost-policy.json
test -f /tmp/cold-warm-analysis.json && test -f /tmp/cold-warm-plan.json

Capture evidence — summarize what was checked, what was fixed, and any unresolved risks.
If a repeatable issue appeared, update the relevant skill or checklist in the same change.

Decision Heuristics

Between two fixes, choose the one that leaves the dependency graph clearer.
If a change cannot be explained in one sentence, document the scope rather than under-fixing.
If a failure can recur, codify it in a skill/workflow instead of relying on memory.
If evidence is missing, do not claim success.

Scope Boundary

Use this skill only for common-sense engineering checks.

Do not use this skill for unrelated lanes; route those through $skill-hub and the most specific matching skill.

References

references/common-sense-checklist.md — full before/during/after checklist.

Loopback

If this lane is unresolved, blocked, or ambiguous:

Capture current evidence and failure context.
Route back through $skill-hub for chain recalculation.
Resume only after the updated chain returns a deterministic next step.

---name: skill-common-sense-engineeringdescription: Apply practical sanity checks before and after coding work to prevent avoidable mistakes. Use when verifying dependency surfaces, cleaning generated artifacts, checking privacy policy compliance, auditing artifact hygiene, or ensuring multi-skill chain guardrail evidence is present before claiming readiness.---# Common-Sense EngineeringLightweight sanity layer for day-to-day coding work. Prevents avoidable mistakes by enforcing pre/post checks on every change.## Workflow1. **Clarify the goal** — state the objective in one sentence before choosing tools or edits.2. **Audit dependency surface** — trace related contracts, dependents, and operator-facing surfaces before deciding the implementation boundary.3. **Execute the change** — prefer existing scripts/workflows over ad hoc steps.4. **Run common-sense checks** before concluding: ```bash git status --short python3 scripts/check_private_data_policy.py python3 "$CODEX_HOME/skills/skill-arbiter-lockdown-admission/scripts/artifact_hygiene_scan.py" . --fail-on-found ```5. **Verify guardrail evidence** for multi-skill chains: ```bash test -f /tmp/usage-analysis.json && test -f /tmp/usage-plan.json test -f /tmp/skill-cost-analysis.json && test -f /tmp/skill-cost-policy.json test -f /tmp/cold-warm-analysis.json && test -f /tmp/cold-warm-plan.json ```6. **Capture evidence** — summarize what was checked, what was fixed, and any unresolved risks.7. If a repeatable issue appeared, update the relevant skill or checklist in the same change.## Decision Heuristics1. Between two fixes, choose the one that leaves the dependency graph clearer.2. If a change cannot be explained in one sentence, document the scope rather than under-fixing.3. If a failure can recur, codify it in a skill/workflow instead of relying on memory.4. If evidence is missing, do not claim success.## Scope BoundaryUse this skill only for common-sense engineering checks.Do not use this skill for unrelated lanes; route those through `$skill-hub` and the most specific matching skill.## References- `references/common-sense-checklist.md` — full before/during/after checklist.## LoopbackIf this lane is unresolved, blocked, or ambiguous:1. Capture current evidence and failure context.2. Route back through `$skill-hub` for chain recalculation.3. Resume only after the updated chain returns a deterministic next step.

Frequently asked questions