ai-cortex

Store, look up, or delete a personal credential (server SSH password, database password, website login, API key/token, certificate passphrase) in the macOS Keychain using a consistent <project>-<env>-<kind> naming scheme, and optionally record a pointer (never the secret itself) in the current project's Claude Code memory. Always use this skill whenever the user asks to save, store, remember, look up, rotate, or delete a password, API key, token, SSH credential, or database credential on this machine — even if they don't say "Keychain" or "security" explicitly, e.g. "save this database password so I don't lose it", "把这个数据库密码存一下", "记一条密钥", "这台服务器的密码帮我记下来", "what's the postgres password for staging again", "delete the old GitHub token from keychain". Do not use this for team-shared secret vaults, CI/CD secret injection, or anything that needs to sync across machines — those need a real secrets manager, not this skill.

Drain pending NATS messages from a producer contract via NATS MCP tools. Discovers the available NATS tool capabilities, selects exact-subject or wildcard mode from .cortex/nats.yaml, applies Tolerant Reader semantics, executes ack/nak/term decisions, and returns aggregated stats.

Audit and refactor existing SKILLs to meet spec compliance, repository asset boundaries, tool adaptation requirements, and LLM best practices.

From inside a linked worktree, deliver the current feature branch into main — merge with --no-ff, push, and optionally clean up the worktree, all without leaving CWD.

After code changes, auto-detect the project's build system and local deployment method for a given directory, then build the project and restart its locally-deployed environment (Docker Compose / systemd / process manager). Never assumes — asks only when detection is ambiguous. Caches detected commands per project in .cortex/redeploy-local.yaml; re-invocations on the same project skip re-scanning until signal files change, the cache expires (30 days), or the skill version bumps.

From the main repo on the main branch, scan all linked worktrees and local branches, let the user multi-select, then merge --no-ff + push them sequentially and clean up succeeded worktrees together.

Generate an LLM agent test suite (golden cases, mock-LLM unit tests, evaluator harness) from an agent implementation and its agent-test contract. Use when an agent has no tests, or a contract exists but the test code is missing.

Publish a NATS message conforming to a cross-team contract, using NATS MCP tools. Authors the contract on first use if missing. Reads project-level cache (.cortex/nats.yaml) to avoid re-prompting basics across sessions.

Single-step governance executor — reads plan-next routing output, executes the highest-priority action, and emits a continuation signal for /loop-driven autopilot.

Analyze governance state and suggest next actions from existing docs; read-only — never executes downstream skills.

Iteratively review changes, run automated tests, and apply targeted fixes until issues are resolved (or a stop condition is reached).

Generate lean, high-density README. Sections pruned by value threshold — not fixed count. Primary goal — reader knows what the project is, where to look, and how to use it within 30 seconds.

Archive a completed milestone by generating a snapshot summary, folding the roadmap stage, and removing the stale tasks directory.

Discover and execute repository test commands safely with evidence-based command selection and safety guardrails.

Capture requirements, bugs, or issues from free-form input into structured, persistent artifacts. Use when user wants to record a work item quickly without deep validation.

Create high-quality git commits with clear messages and logical scope. Core goal - produce reviewable commits following Conventional Commits format with pre-commit quality checks.

Convert text with private context or internal dependencies into generic, unbiased expressions that are standalone and reusable. Core goal - produce decontextualized text that preserves logic while removing organizational identifiers. Use for project handoff, open-source prep, methodology abstraction, cross-team sharing.

Create or update docs/ARTIFACT_NORMS.md from an approved proposal and establish project docs norms as canonical rules.

Define the fundamental purpose of a project or organization. Answers why the project exists; produces a single mission statement persisted to docs.

Define the single most important metric representing the core value delivered to users. Produces North Star Metric with rationale, optional supporting metrics, and anti-pattern examples; persisted to docs.

Derive a strategic roadmap from goals using milestone checkpoints, strategic bets, success metrics, and promotion criteria. Produces a decision-grade roadmap document.

Derive 3–5 strategic pillars (high-level themes) from vision and North Star that structure and guide strategic goals and roadmap. Produces a strategic pillars document; persisted to docs.

Define the long-term future the project aims to create. Answers what future we are building; produces a vision statement aligned with mission, persisted to docs.

Define 3–5 long-term strategic goals that move the project toward the vision and North Star. Produces a goals document aligned with mission, vision, and NSM; persisted to docs.

Write or revise AGENTS.md per embedded output contract to establish project identity, authoritative sources, and behavioral expectations. Use when creating Agent entry for new projects, auditing existing AGENTS.md, or adopting the AI Cortex entry format.

GitHub Actions YAML with embedded output contract: security-first, minimal permissions, version pinning. For CI, release, PR checks. Differs from generic templates by spec compliance and auditability.

Orchestrator skill — sequence atomic review-* skills (scope → language → framework → library → cognitive) and aggregate findings into a unified report.

Force a clean re-score of every backlog item with four frameworks (RICE, WSJF, MoSCoW, ICE) in parallel — ignores any existing priority, auto-detects multi-file or single-file backlog layouts, surfaces framework disagreements, and captures the user's final decision with rationale.

Promote prioritized backlog items into the roadmap's Now/Next/Later tiers based on strategic_goal capacity allocation and priority scores. Event-driven (not calendar-driven).

Review code for architecture: module and layer boundaries, dependency direction, single responsibility, cyclic dependencies, interface stability, and coupling. Cognitive-only atomic skill; output is a findings list.

Review given file/dir/repo for current-state code organization: module boundaries, design patterns, cross-module dependencies, tech debt, and interface stability. Scope-only atomic skill; output is a findings list.

Review only git diff for impact, regression, correctness, compatibility, and side effects. Scope-only atomic skill; output is a findings list for aggregation.

Review .NET (C#/F#) code for language and runtime conventions: async/await, nullable, API versioning, IDisposable, LINQ, and testability. Language-only atomic skill; output is a findings list.

Review Go code for language and runtime conventions: concurrency, context usage, error handling, resource management, API stability, type semantics, and testability. Language-only atomic skill; output is a findings list.

Review Java code for language and runtime conventions: concurrency, exceptions, try-with-resources, API versioning, collections and Streams, NIO, and testability. Language-only atomic skill; output is a findings list.

Review ORM usage patterns for N+1 queries, connection management, migration safety, transaction handling, and query efficiency. Library-level atomic skill; output is a findings list.

Review code for performance: complexity, database/query efficiency, I/O and network cost, memory and allocation behavior, concurrency contention, caching, and latency/throughput regressions. Cognitive-only atomic skill; output is a findings list.

Review PHP code for language and runtime conventions: strict types, error handling, resource management, PSR standards, namespaces, null safety, generators, and testability. Language-only atomic skill; output is a findings list.

Review PowerShell code for language and runtime conventions: advanced functions, parameter design, error handling, object pipeline behavior, compatibility, and testability. Language-only atomic skill; output is a findings list.

Review Python code for language and runtime conventions: type hints, exceptions, async/await, context managers, dependencies, and testability. Language-only atomic skill; output is a findings list.