# Bootstrap Evidence App

> Implement an evidence-backed application from one product prompt with authorized context reuse, data curation, tracing, calibrated evaluation, UI proof and governed harness improvement.

- Skill: `homenshum/bootstrap-evidence-app` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add homenshum/bootstrap-evidence-app`
- Raw SKILL.md: https://api.skillmd.com/api/skills/homenshum/bootstrap-evidence-app/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: HomenShum (https://skillmd.com/u/homenshum)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/homenshum/bootstrap-evidence-app

---


# Bootstrap evidence app

## Trigger and refusal

Use for a complete application bootstrap, not merely installing coding tools.
Do not publish private context, invent proof, grant access or activate a harness
without separate authority. Synthetic examples prove contracts, not applications.

## Workflow

Before implementation, copy `templates/harness/outcome-contract.json` and declare
the trigger, current/candidate envelope, target, exact cases, expected before/after,
invariants, owner and stop criteria. Unknown baseline means DISCOVERY. Use
`scripts/outcome_review.py` to validate, route and record one append-only history;
derive HTML/ASCII from it. Keep failures, budgets and approvals across handoffs.
Profile enterprise data, model, telemetry and operator boundaries when applicable.

1. Inspect instructions, manifests, history, schemas, tests and existing services.
   Search only authorized local and organizational sources. Inventory provenance,
   scope, freshness, duplication, conflicts and incomplete searches. Decide
   REUSE, EXTEND, BUILD or BLOCKED for each capability before implementing it.
2. Define one persona, decision and end-to-end proof. Keep measured facts outside
   model judgment and human approval outside model authority.
3. Implement bounded, authenticated data sourcing with timeouts and privacy.
   Curate source-linked versioned cases with group-disjoint visible/heldout
   splits. Keep heldout contents outside candidate access, not merely labeled.
4. Reuse the runtime and add request/tool/result/score trace correlation.
   Start locally; configure Langfuse only with authorized credentials. Verify
   hosted record readback, not just SDK flush. Avoid raw private-input export.
5. Implement the actual UI journey using assistant-ui when compatible. Render
   validated results and citations from the same backend receipts. Exercise
   streaming, cancellation, errors, retry, denied access and durable reload.
   Capture real viewport evidence and inspect console/network failures.
6. Define descriptive boolean hard gates and five text-anchored ordinal grades,
   each with rationale. Calibrate on reviewed examples and negative controls.
   Provider failures are missing evidence, not scores. Freeze dataset, rubric,
   model and evaluator identities before comparing runs.
7. Distinguish current-run repair from future harness improvement. Mine trace-linked weaknesses. Propose one bounded harness change with source,
   scores and execution traces. Keep policy, judges and heldout cases outside
   candidate edit scope. Reject hard-gate failures and split regressions.
8. Numerical eligibility is not acceptance. Require a distinct human acceptance
   receipt and rollback path before activation. Report unresolved access gaps.

## Mechanisms and receipt

Apply task/meta improvement separation, weakness/proposal/validation loops,
source-plus-score rollout feedback, and task-specific capability assembly within
the existing runtime. Do not create a competing orchestration platform.

Return source/reuse inventory, implemented slice, versioned evaluation inputs,
baseline/candidate results, real trace/UI proof and a promotion decision.
Validate the generic skill receipt with `references/contract.json`; passing
receipt validation does not prove the application works.

Read [the execution contract](references/contract.json) before starting. Validate
the final receipt with its parameterized `verification.argv`, replacing
`{python}`, `{skill_dir}`, and `{receipt}` with concrete local values.