58 tagged drift detection, measured the same way as everything else here.
Browse within: codex-cli 20cursor-ide 20cdd 14documentation 14eu-ai-act 14agent-memory 9cli-tool 6embeddings 6fact-verification 6aiops 5fleet-management 5infrastructure 5
Skill Claude CodeCodex
FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.
Skill Claude CodeCodex
Activate on the first user turn of every conversation, including greetings. Load Prism context using the user's configured project and quick, standard, or deep depth, then greet the developer by their configured agent name and show the matching recent-session context.
Skill Claude CodeCodex
Mandates generation of testassertions.json during planning. v7.2.0 enhanced with severity gates (warn/gate/abort), dependency chains, and Claw-as-Validator support.
Skill Claude CodeCodex
Use when writing or changing code in an existing repository to keep new code consistent with the repo's own conventions and avoid duplicating code that already exists. Checks a proposed function against the repo's dominant patterns and existing functions BEFORE it lands, turning drift detection into drift prevention.…
Skill Claude CodeCodex
One-time VibeDrift setup for this repo: configure excludes, build the drift baseline, write repo context into CLAUDE.md, and optionally enable Drift Sessions. Run once per repo after installing the vibedrift plugin.
Skill Claude CodeCodex
AI-driven documentation repair with structured research workflow, template-aware generation, and quality validation loops. Generates or fixes canonical documentation by researching the actual codebase, not using placeholders. Iterates until guard passes.
Skill Claude CodeCodex
Cross-document consistency analysis and quality assessment. Performs read-only analysis across all canonical docs, identifies drift, coverage gaps, and quality issues. Produces a structured report with severity-ranked findings. Modeled after speckit-analyze.
Skill Claude CodeCodex
Create or update feature specifications from natural language descriptions. Use when starting new features or refining requirements. Generates spec.md with user stories, functional requirements, and acceptance criteria following spec-driven development methodology.
Skill Claude CodeCodex
Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase × cause × fallback. Use when hooks may be silent, CI may float across Cladding releases, scan or run results look thinner than expected, or before tuning the host…
Skill Claude CodeCodex
Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (clad oracle --required) demands — an empty worklist means don't author unless the user explicitly asks. YOU spawn a blind sub-agent from a spec-only brief, then record it. Activate only when the connected project contains…
Skill Claude CodeCodex
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
YoungLeadersDotTech/young-leaders-tech-marketplace
Skill Claude CodeCodex
Generates OpenCode agents and MCP config from canonical Claude Code sources, validates both runtimes' rule sets, and detects drift. Use when adding OpenCode support or checking cross-runtime compliance.
Skill Claude CodeCodex
Strategy Operating System for startup/scaleup CEOs. Three operating modes: (1) Strategy Lifecycle — guides consolidation, stress-testing, communications, execution planning, and governance when the user engages in explicit strategy work; (2) Strategy Analyst — ambient guardrail that watches for misalignments between…
shauryagangrade/intent-drift-skill
Skill Claude CodeCodex
Detects intent drift in AI-assisted development by comparing the original goal against the current plan and execution context. Run /intent-drift to evaluate whether ongoing work has drifted from what was asked. Triggers on "check intent drift", "are we still on track", "is this aligned with the goal", "did the plan…
Skill Claude CodeCodex
Know the file you're editing is the file you think it is — verify integrity before you act.
Skill Claude CodeCodex
Verify the tamper-evident audit log: recompute the per-entry hash chain and the Merkle root, and detect any break.
Skill Claude CodeCodex
The host fleet inventory: which hosts exist, each hosttype (ubuntu, talos, windows, cloud), network routing, and security posture.
Skill Claude CodeCodex
Operate a Talos Linux Kubernetes cluster with talosctl: health checks, etcd snapshot and restore, node upgrade, and kubeconfig rotation.
Skill Claude CodeCodex
Use when working with agent, multi-agent, pipeline, orchestration, tool use, memory, context. Multi-agent systems: pipelines, orchestration, verification, semantic integrity.
Skill Claude CodeCodex
Use for reading/writing structured memory blocks, hash-chain audit, session logs. Replaces flat STATE.MD with typed JSON blocks and provenance chain. Load when starting/ending sessions, recording decisions, or verifying facts.
Skill Claude CodeCodex
Use when creating a new artifact or checking if something already exists. Artifact registry of all created scripts, benchmarks, prototypes, data, templates. Cross-reference with dso.md for verified patterns.
Skill Claude CodeCodex
Work through the VibeFrame project model — plan with vibecontext, declare intent with vibedeclare/vibedecide, bind implementations with vibelink, and resolve drift findings. Use when this project has a .vibeframe/ directory and you are planning a feature, implementing one, responding to a VibeFrame drift warning, or…