tmusser/ai-engineering-skills

Portable AI-engineering skills for Claude Code, Codex, and coding agents: bounded scope, mini-specs, vertical slices, verification, ship gates, and handoff.

4Stars on the repository
21Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

analyze-mini

01

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support a safe build decision.

not rated 4 5d ago A 27 tokens original MIT

ceremony-budget

03

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Choose the smallest workflow that still buys back enough attention and safety for the task.

not rated 4 5d ago A 20 tokens original MIT

constitution-lite

05

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Define a tiny set of stable, non-negotiable agent authority boundaries for repeated or delegated work without duplicating CLAUDE.md, AGENTS.md, or task specs.

not rated 4 5d ago C 38 tokens original MIT

context-check

06

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.

not rated 4 5d ago A 34 tokens original MIT

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, separating evidence from decisions, assumptions, and blockers before contract language is written.

not rated 4 5d ago A 47 tokens original MIT

handoff

09

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Compress project context into HANDOFF.md with workflow state, analysis checkpoint, next gate, verification, current hypothesis, freshness anchors, optional gotcha references, and a resume packet for the next agent session.

not rated 4 5d ago A 43 tokens original MIT

lean-mode

10

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.

not rated 4 5d ago A 29 tokens original MIT

mini-spec

11

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Create a compact, reference-first SPEC.md that defines the task-specific delta, non-goals, likely failure modes, spec ceiling, and verification target without paraphrasing richer authoritative sources.

not rated 4 5d ago A 40 tokens original MIT

ship-mini

12

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Run a lightweight activation GO or NO-GO gate only when verified work is about to gain material real-world side effects, autonomy, permissions, or production/shared-state impact.

not rated 4 5d ago A 37 tokens original MIT

teach-back

13

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Transfer ownership of a verified implementation by testing and repairing the human's understanding of its behavior, decisions, and failure modes without turning every task into a tutorial.

not rated 4 5d ago A 34 tokens original MIT

tool-noise-guard

16

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Passive guardrail that compacts repetitive tool-result envelopes, preserves decision-relevant anchors and deltas, and suppresses redundant re-fetches without pretending prior context disappeared.

not rated 4 5d ago A 39 tokens original MIT

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Reactivate the smallest set of decision-governing constraints immediately before a consequential action, without introspection, full-context summarization, or a new durable artifact.

not rated 4 5d ago A 36 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: