Skip to content

docs(skills): evidência do Antigravity e a bancada de prova com agy - #725

Open
melgarafael wants to merge 2 commits into
mainfrom
docs/evidencia-antigravity
Open

docs(skills): evidência do Antigravity e a bancada de prova com agy#725
melgarafael wants to merge 2 commits into
mainfrom
docs/evidencia-antigravity

Conversation

@melgarafael

Copy link
Copy Markdown
Owner

Acompanhamento do #689 (mesclado): dois commits que ficaram para trás na branch do épico.

  • scripts/skills-embutidas/provar.mjs ganha o modo agy (o CLI do Antigravity, agy --print com saída stream-json), com permissões auto-aprovadas — em modo sem interface ninguém clica "permitir", e o primeiro comando encerrava a corrida.
  • evidence/skills-embutidas/2026-09-10/: resultado das cinco perguntas no CLI do Antigravity. Ele não carrega as skills do workspace em modo sem interface (perguntado, responde "NENHUMA"); achou o guia por exploração em 2 de 5. A prova do app Antigravity segue à mão; o CLI do Cursor (agent) exige agent login.

Só docs e a bancada; nenhum código de runtime. Gates: skills-embutidas e documentacao-aponta-para-o-que-existe verdes; eslint da bancada zerado.

🤖 Generated with Claude Code

https://claude.ai/code/session_01N4qXpr9LCmXoG2KR4TBrL3

Pessoa and others added 2 commits September 11, 2026 20:27
O app instala um CLI (`agy`) com modo sem interface e saída stream-json;
a bancada passa a rodar e resumir corridas nele, com o mesmo formato dos
outros três. O Cursor também tem CLI (`agent`), mas exige `agent login`.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4qXpr9LCmXoG2KR4TBrL3
…workspace

Cinco corridas em `agy --print` (modo plano, permissões auto-aprovadas):
perguntado quais skills do workspace tem no contexto, responde "NENHUMA";
achou o guia por exploração em 2 de 5. A prova do app segue à mão.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4qXpr9LCmXoG2KR4TBrL3
@vercel

vercel Bot commented Sep 11, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated
deskcomm-crm Ready Ready Preview Sep 11, 2026 11:28pm UTC

Request Review

@ecc-tools

ecc-tools Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

ECC Tools / Security Evidence

Commit: 69c1d4e546a2a695dcc9e8f476b5ac064165ce18

Security evidence gate passed (success)

No security-sensitive scanner-evidence gap detected.

Mode: enforce

Scanned 3 changed file(s). No missing scanner-evidence signal was detected.

Check publication was denied or unavailable. An app owner must enable Checks: read and write, and the installation owner must approve the updated permission.

@ecc-tools

ecc-tools Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

ECC Tools / PR Risk Taxonomy

Commit: 69c1d4e546a2a695dcc9e8f476b5ac064165ce18

PR taxonomy clear (success)

Scanned 3 changed file(s). No taxonomy bucket signals were detected.

Scanned 3 changed file(s).

No PR taxonomy bucket signals were detected.

Check publication was denied or unavailable. An app owner must enable Checks: read and write, and the installation owner must approve the updated permission.

@ecc-tools

ecc-tools Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

ECC Tools / Reference Set Readiness

Commit: 69c1d4e546a2a695dcc9e8f476b5ac064165ce18

Reference set readiness gaps detected (neutral)

Reference evidence present for 0/7 areas (0%) across 3 changed file(s).

This check is based on files changed in this PR. Repository-level readiness is still reported by /ecc-tools analyze comments and generated manifests.

Area Status Evidence / Next Step
Deep analyzer corpus Missing Add analyzer fixture, golden, benchmark, or reference-set files that can catch analyzer regressions.
RAG/evaluator comparison Missing Add retrieval or evaluator reference-set comparison fixtures with expected ranking behavior.
PR salvage/review corpus Missing Add stale-PR, review-thread, reopen-flow, or salvage reference cases for queue cleanup automation.
Discussion triage corpus Missing Add public discussion triage fixtures, golden cases, or reference sets for informational, answered, and no-response classifications.
Harness compatibility Missing Add cross-harness, adapter-compliance, or harness-audit evidence for Claude, Codex, OpenCode, Zed, dmux, and agent surfaces.
Security evidence Missing Attach security evidence such as SBOMs, SARIF, audit reports, or AgentShield evidence packs.
CI failure-mode evidence Missing Add captured CI failure logs, dry-run fixtures, or troubleshooting docs for common workflow failure modes.

Check publication was denied or unavailable. An app owner must enable Checks: read and write, and the installation owner must approve the updated permission.

@ecc-tools

ecc-tools Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

ECC Tools / Hosted Promotion Readiness

Commit: 69c1d4e546a2a695dcc9e8f476b5ac064165ce18

Hosted promotion readiness passed (success)

No hosted promotion evidence gaps detected across 3 changed file(s); 0 corpus scenarios had matching evidence.

This check compares PR file changes against the evaluator/RAG promotion corpus in src/analyzers/fixtures/evaluator-rag-corpus.ts.
Hosted output scoring inspected 0 completed cached hosted job results.

No evaluator corpus scenarios matched this PR.

Check publication was denied or unavailable. An app owner must enable Checks: read and write, and the installation owner must approve the updated permission.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant