flyfission/nuclear-grade-context-engineering
29 skills
$npx skills add flyfission/nuclear-grade-context-engineeringSkillInstalls
breaking-down-the-workSplits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a…briefing-an-agentPrepares focused context for an AI agent, reviewer, verifier, or releaser at the start of a task, with a clear role, goal anchor, authority, evidence to…checking-legal-and-safety-wordingReviews public text for license, warranty, compliance, safety, security, certification, and fitness claims that go too far, then rewrites them to stay inside…checking-release-readinessRecords a ship, block, defer, or ship-with-risk decision that ties baseline, evidence status, residual risk, rollback, monitoring, and handoff together.checking-source-claimsChecks that the way you cite source families, agencies, standards, or borrowed ideas is honest and does not claim too much.checking-what-a-change-affectsScreens what a controlled change might leave out of date across docs, tests, skills, commands, templates, checkers, prompts, releases, saved versions, and…choosing-what-to-controlDecides which code, prompts, models, tools, dependencies, docs, tests, evals, releases, or claims need their approved state tracked.closing-stale-packetsBrings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it.creating-change-recordsCreates or updates Quick or Standard change records, adds the required files, and refreshes what each claim must prove for an evidence-backed pull request.deciding-who-decidesDecides who holds authority for a change — the agent at the edge or a human gate — by matching decision rights to reversibility, evidence, and consequence, and…declaring-intentStates what an agent intends to do and why before a critical or irreversible action, so a reviewer can challenge the thinking and not just the result.double-checking-before-actingChecks a critical agent action against its exact target, expected result, and stop condition before and after execution.handing-off-workHands off unfinished work with a closed-loop briefing of state, changed conditions, remaining scope, authority limits, and open evidence.learning-from-experienceTurns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards.organizing-project-foldersDesigns a clean folder and file layout as real architecture, building it from a work breakdown or an existing tree, grouping by what changes together and what…proving-claimsBuilds claim-to-evidence trace rows with statuses, gaps, tests, evals, reviews, and narrower non-claims.questioning-attitudeChallenges the assumptions behind a change before an agent builds, merges, or releases, and names the one fact that would change the decision.rating-change-riskPicks Quick, Standard, or a stronger human-reviewed mode based on consequence, how easy it is to undo, and how much is unknown.recording-a-known-good-versionRecords the version everyone agreed is correct, the evidence behind it, and what would make that record out of date.recording-what-an-agent-didCaptures an agent run's tool calls, decision points, inputs, outputs, token use, and approval steps as a clear, repeatable record linked into the packet trace…reporting-shared-defectsRoutes a defect found in a shared or supplied artifact (a shared prompt, skill, dependency, model, eval, or template) to the downstream teams, agents, and…responding-to-incidentsRuns a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive…reviewing-code-qualityReviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict.staying-on-missionTests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop.stress-testing-agent-changesAttacks your own agent change, tool grant, dependency, model, or release on purpose, across risk types such as prompt injection, gaining extra power, unsafe…tracking-deficienciesKeeps a standing register of known deficiencies so flaky tests, noisy alerts, unowned services, and recurring incidents get aged, owned, and fixed or formally…using-nuclear-gradeThe always-first router for AI-assisted work — before acting, state the mode (the administrative floor, Quick, or Standard-plus) and the one fact that sets it,…verifying-final-artifactsVerifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it…vetting-outside-code-and-modelsChecks dependencies, models, APIs, SaaS tools, generated files, and vendor claims against how you will actually use them, the proof you have, the gaps, and the…