aryaminus/controlkeel
31 skills
$npx skills add aryaminus/controlkeelSkillInstalls
agent-integrationAttach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client.agent-pattern-verificationVerify AI agent code for dangerous patterns including infinite loops, unbounded retries, tool hallucinations, and context overflow.alignInterview the user about their goal before any plan or code. Reach shared understanding of what, why, which layers, success criteria, and unknowns.architect-firstSettle types, module shape, and boundaries before implementation. Trigger: 'architect this', 'design module structure', 'settle types first'.benchmark-operatorRun, inspect, import, and export ControlKeel benchmark suites and multi-subject matrices.bounded-loopRun objective, repeatable improvement work under an immutable verifier and hard iteration, cost, time, and no-progress limits.challengeAdversarially challenge the current plan or finding. Assume the direction is wrong and build the strongest case against it.cli-for-agentsDesign/review CLIs for agent-friendliness: non-interactive flags, layered help, idempotency, dry-run, actionable errors.cloudflare-agentEnable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.communication-styleWrite concise, calm technical responses whose structure matches the decision, evidence, or sequence being communicated.compliance-auditRun a structured compliance audit against active ControlKeel policy packs and domain controls.continual-learningAuto-mine session for durable memory: user preferences and workspace facts.continuityLearn, record, audit, and apply codebase patterns consistently across a repo by comparing current code to canonical local examples stored in CK memory.controlkeel-governanceOperate inside a ControlKeel-governed session. Use this before code edits, shell execution, delegation, deploy work, or any task that needs CK validation,…cost-optimizationKeep a governed session within budget. Use this before long-running agent work, bulk processing, or any task where spend pressure could change the plan.deep-code-quality-reviewStrict maintainability review: abstraction quality, file size, spaghetti growth, code-judo simplification.deslopClean AI slop: remove narrative comments, verbosity, hallucinated patterns, padding. Also cleans AI-generated issue/PR text.domain-auditAudit a session against its domain pack, especially the regulated and operations-heavy packs such as HR, legal, marketing, sales, real-estate, government,…end-of-shiftClose a governed work session with validation, proof, findings, budget, digest, learning, and handoff checks.false-confidence-test-auditAudit tests that may pass without proving the claimed behavior.handoffPersist session state and hand off in-progress work to a background agent or delegated execution.investigateRead-only codebase Q&A: trace code paths, answer how/why/where questions without changes.orchestrate-tasksFan large tasks across parallel agents with planner/worker/verifier roles and structured handoffs.parallel-reviewRun security + code quality reviews concurrently, synthesize deduplicated findings.plan-sliceDecompose an aligned goal into independently executable vertical slices with explicit blocking relationships.proof-memoryUse ControlKeel proof bundles, typed memory, workspace snapshots, transcript summaries, and resume packets before closing or resuming work.reviewable-prPrepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance.security-reviewRun a structured security review before marking a task done. Use this for code, config, architecture, or release reviews that need OWASP, baseline pack, and…ship-readinessCheck install-to-first-finding metrics, funnel stage, findings state, proofs, and approvals before calling a session ready to ship.standup-summarySummarize work completed over a time period using git commits + CK session data. Trigger: 'what did I get done', 'standup', 'weekly summary', 'status update'.tdd-bugfixReproduce → root-cause → failing test → minimal fix → verify. Trigger: 'fix this bug', 'reproduce and fix', 'TDD fix'. Requires a local test path.