grounded-generation
Skill0 starsChanged 5 days agoMITView on GitHub
Use when generating content, reports, summaries, evaluations, or code against external facts. Requires verified source data, explicit lineage, and no invented capabilities or copied answers.
In this repository108 other files it gives its agents.
- adaptive-estimationSkill
- adaptive-loop-budgetingSkill
- adopt-and-deleteSkill
- adversarial-reviewSkill
- agent-drives-uiSkill
- agentic-coding-loopSkill
- agent-otel-trajectorySkill
- agents-as-iac-modulesSkill
- ascii-ui-mockupsSkill
- authoring-html-emailSkill
- authoring-skills-vs-mcpSkill
- batched-ssh-enumerationSkill
- c4-architectureSkill
- challenge-the-premiseSkill
- codegraph-bootstrapSkill
- codegraph-worktree-startupSkill
- colocated-pod-tolerationsSkill
- command-creatorSkill
- complexity-budgetsSkill
- connector-readinessSkill
- context-anchored-patchingSkill
- continuous-issue-resolutionSkill
- credential-proxySkill
- criticality-tiered-reportingSkill
- data-connector-buildingSkill
- declarative-firstSkill
- disk-pressure-forensicsSkill
- early-return-over-elseSkill
- email-triageSkill
- enums-codify-behaviorSkill
- ephemeral-workspace-lifecycleSkill
- event-sourcingSkill
- evidence-claim-boundariesSkill
- exhaustive-matchSkill
- feature-coverage-not-just-line-coverageSkill
- full-disk-forensicsSkill
- gate-before-pushSkill
- github-pr-shepherdingSkill
- graceful-shutdown-stateful-agentsSkill
- iac-incident-responseSkill
- iac-not-ad-hocSkill
- instrumented-service-scaffoldSkill
- interface-over-conditionalsSkill
- knowledge-routingSkill
- lean-on-oss-standardsSkill
- live-money-disciplineSkill
- live-state-verificationSkill
- loop-governance-and-learningSkill
- low-level-executor-task-specSkill
- map-dispatch-over-conditionalsSkill
- merge-conflict-disciplineSkill
- mermaid-diagramsSkill
- oke-arc-runners-opentofuSkill
- orchestrate-agySkill
- orchestrate-claudeSkill
- orchestrate-codexSkill
- orchestrate-geminiSkill
- otel-emit-at-willSkill
- parameter-designSkill
- parse-dont-validateSkill
- The first 60 shown.
The file
Files
Grounded Generation
Generate only from verified inputs. Missing data is a task, not permission to invent.
Tag every datum's lineage
Mark each value the output relies on as one of:
- primary — read directly from the system of record this run.
- copied — taken from another candidate, prior output, or cache; carries that source's correctness, not independent confirmation.
- synthetic — fixture, sample, or placeholder; never a result.
- derived — computed from the above; inherits the weakest tag it draws on.
Lineage is the behavior this skill adds: an output you cannot tag is an output you cannot ground. Tags propagate — a derived claim is only as primary as its weakest input.
Apply per generation type
- For comparisons, prove each candidate is primary-sourced from the same underlying data. If one answer is copied from the control, the result validates formatting only.
- For code, build against routes, schemas, functions, and APIs that exist. Nonexistent endpoints and fabricated helpers must fail review.
- For analysis and forecasts, run leakage, lookahead, and overfit checks before trusting any performance claim.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.