Menu
SkillsMP a collecté 19 skills depuis KurtLehnardt/agentic-tools. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 19 skills collectés sur 19.
Wrap a worker loop so smaller or local models actually finish — response validation, rescue parsing, corrective nudges, step enforcement, and context compaction. The model proposes the next action; the harness makes the loop survivable. Trigger: make the loop…
Langue du texte source : anglais
Instrument an agent or LLM feature with structured spans per model and tool call, tracking the four reliability signals — P95 latency, cost per run, tool error rate, and eval pass rate — so runs can be replayed, alerted, and scored. Start with one critical…
Langue du texte source : anglais
Bound an agent's blast radius with a deny-by-default sandbox policy — read allowed, writes whitelisted, egress denied — plus a per-server policy for each MCP server and violation telemetry. Contains a prompt-injected, trojaned, or rug-pulled agent; it does…
Langue du texte source : anglais
Orchestrate a spec-driven implementation pipeline: spec intake, requirements ledger, plan, architect gate, product gate, task decomposition with model tiering, parallel ralph-loop workers, a deterministic mechanical gate plus an opus judge, and verified…
Langue du texte source : anglais
Zero-trust gatekeeper. Validates a deliverable claim-by-claim by re-running everything firsthand — refetch the diff from source, rerun the suite, re-execute the eval, rescore — never trusting the worker's say-so. Cycles work back when the letter passes but…
Langue du texte source : anglais
Turn a failure — a bug, a bad output, a prod incident, a verdict FAIL — into a minimal, reproducible eval level added permanently to the suite, so the same failure can never silently return. Builds the eval flywheel. Trigger: capture this failure, add a…
Langue du texte source : anglais
Compute compounding-error risk for a multi-step or multi-agent pipeline — per-step success rate raised to step count — and show where cumulative reliability falls below target, so you know where to place gates and checkpoints. Trigger: chain risk, compounding…
Langue du texte source : anglais
Pin a north-star constitution for a multi-agent system and protect the prompt layer from tampering — detect and block unauthorized system-prompt mutation and prompt-injection that tries to redirect downstream agents. Trigger: pin the constitution, north star,…
Langue du texte source : anglais
Turn a task into a declarative contract — objective/intent plus machine-checkable acceptance criteria and a stub-proof gate. Refuses prompt-as-wish and imperative pseudocode. Trigger: write a contract, define the contract, spec this task, contract for,…
Langue du texte source : anglais
Generate an executable gate for a contract or task, then prove it is stub-proof by writing a hollow stub and confirming the gate rejects it. If a stub can pass your eval, the eval is the bug. Trigger: build a gate, make the gate, stub-proof, executable…
Langue du texte source : anglais
Route each task to the cheapest model and effort that can pass its gate, escalating on failure (small/local -> haiku -> sonnet -> opus; low -> medium -> high effort). Right-sizes ambiguous tasks and prefers local small-dense models for narrow work. Trigger:…
Langue du texte source : anglais
Go-to-market engine for apps and products. Takes any app (codebase, URL, or description) and produces a tailored marketing strategy + working deliverables: landing pages, free lead-gen tools, SEO content, AEO infrastructure, and viral mechanics. Trigger:…
Langue du texte source : anglais
Cron supervisor that checks on worker subagents every ~5 minutes, compares their progress against the original plan, and writes NUDGE.md into drifting worktrees. Trigger: babysit, supervise workers, watch agents.
Langue du texte source : anglais
Deploy merged code to staging or production, run migrations, verify health, and roll back on failure. Trigger: deploy this, ship it, push to production, go live.
Langue du texte source : anglais
Transform a raw idea into a structured Product Requirements Document with acceptance criteria, tech requirements, and service manifest. Trigger: I have an idea, new app, new feature, build me something, product idea.
Langue du texte source : anglais
Detect required services, check credential vaults, generate .env files, and guide account creation for missing services. Trigger: set up environment, configure project, set up credentials, prepare for build.
Langue du texte source : anglais
Show factory dashboard: active builds, worktree status, review scores, blockers, and project health. Trigger: status, dashboard, what's running, factory status, show progress.
Langue du texte source : anglais
Clean up completed builds: remove worktrees, delete merged branches, archive plan files, and reset factory state. Trigger: clean up, teardown, remove worktrees, clean factory.
Langue du texte source : anglais
Generate comprehensive test suites for existing code without modifying implementation. Trigger: add tests, test coverage, write tests for, test this module.
Langue du texte source : anglais