Instructions file CodexOpenCode
Instructions for tmusser/ai-engineering-skills, covering agent instructions, route-first context loading and quality standards.
Instructions file CodexOpenCode
Instructions for tmusser/ai-engineering-skills, covering agent instructions, route-first context loading and quality standards.
Skill Claude CodeCodex
Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support a safe build decision.
Skill Claude CodeCodex
Preserve discovered bugs as BUGS.md entries.
Skill Claude CodeCodex
Implement exactly one planned slice after scope is frozen, without exceeding the spec ceiling or carrying known analysis debt into the build.
Skill Claude CodeCodex
Choose the smallest workflow that still buys back enough attention and safety for the task.
Skill Claude CodeCodex
Validate a mini-spec before planning.
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.
Skill Claude CodeCodex
Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.
Skill Claude CodeCodex
Debug failures systematically.
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.
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.
Skill Claude CodeCodex
Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.
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.
Skill Claude CodeCodex
Explicitly limit blast radius before any implementation or file changes.
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.
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.
Skill Claude CodeCodex
Add focused deterministic tests, fixtures, or smoke checks.
Skill Claude CodeCodex
Convert a mini-spec into 3-7 vertical implementation slices.
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.
Skill Claude CodeCodex
Record clear evidence that a task works, including commands, results, remaining risks, scope adherence, and whether the implementation stayed under the spec ceiling.
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.
tmusser/context-to-action-skills
Instructions file CodexOpenCode
Instructions for tmusser/context-to-action-skills, covering agents, repo model, safety rules, output rules and validation commands.
tmusser/context-to-action-skills
Skill Claude CodeCodex
Catch the user up from messy workplace context and surface what needs attention.
tmusser/context-to-action-skills
Skill Claude CodeCodex
Turn vague workplace context into a crisp ask with clear ownership and timing.