atlas-esl-hop
ESL lifecycle hop — the DISCOVER hop. When a scout mission's findings surface change-worthy signal (a defect, a spec/impl drift, or a genuine gap) in an ESL-enabled project (.spectra/ present), ATLAS proposes opening an ESL change at 'proposed' by framing the scout-report + its ECL envelope it already emits as the proposal artifact — it never calls mcp__tonberry__* itself and never implements (refusal boundary intact). SPECTRA's own esl-hop owns the actual right_size/propose/specify tonberry calls on receipt, over the existing atlas-to-spectra handoff edge. Absent .spectra/ or absent change-worthy findings → hand off the scout-report normally (ESL opt-in).
- License 许可
- Apache-2.0
- 所属仓库
- Rynaro/magicite
- 最近更新
- 2026-10-14
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- atlas-esl-hop
- metadata
- { "phase": "S", "methodology": "ATLAS" }
- description
- ESL lifecycle hop — the DISCOVER hop. When a scout mission's findings surface change-worthy signal (a defect, a spec/impl drift, or a genuine gap) in an ESL-enabled project (.spectra/ present), ATLAS proposes opening an ESL change at 'proposed' by framing the scout-report + its ECL envelope it already emits as the proposal artifact — it never calls mcp__tonberry__* itself and never implements (refusal boundary intact). SPECTRA's own esl-hop owns the actual right_size/propose/specify tonberry calls on receipt, over the existing atlas-to-spectra handoff edge. Absent .spectra/ or absent change-worthy findings → hand off the scout-report normally (ESL opt-in).
03 SKILL.md 正文
ATLAS — ESL Lifecycle Hop (the DISCOVER hop)
When to use
Load at Phase S (Synthesize), after the fold is validated and before
scout-report.md is finalized, when both hold:
- Change-worthy signal. ≥1 finding in
findings.mdasserts something is broken, drifted, or missing relative to a spec/expectation the mission surfaced — not merely descriptive topology. See "What counts as change-worthy" below. - ESL-enabled project. A
.spectra/directory exists at the consumer project root — checked with a single read-onlylist_dirprobe, never an MCP call. ATLAS has nomcp__tonberry__*tool surface and never acquires one.
If either condition is false, skip this skill silently and emit
scout-report.md the normal way (skills/synthesize/SKILL.md). ESL is opt-in;
ATLAS is EIIS-standalone-conformant and works without it.
What counts as change-worthy
A finding is change-worthy when its claim is one of:
- a defect — behavior contradicts a spec, contract, or documented invariant;
- a drift — an implementation and its governing spec/doc have diverged;
- a gap — a required capability, test, or safeguard is absent.
Purely descriptive findings ("X calls Y at path:line") are not
change-worthy on their own. When uncertain, the mission's own GAPS/RISKS
framing (scout-report §5) is the signal — anything already flagged there as
needing a decision or a fix is change-worthy by definition.
Your hop — DISCOVER (proposed), never MAKE
You are the furthest-upstream Eidolon in the ESL chain. You do not call
mcp__tonberry__* — right-sizing, opening the change.json record, and
running S→P→E→C→T→R→A belong to SPECTRA's own hop
(skills/esl-hop/SKILL.md in the SPECTRA repo), triggered when it receives your
hand-off. Your job stops at naming the change-worthy finding and handing it
off — the refusal boundary (P0 rule 1: read-only, no
edit/write/commit/deploy/migrate/refactor/fix) stays fully
intact: you never create, edit, or transition ESL state yourself.
- flag the proposal in §4. In
scout-report.md§4 "Recommended next actions", tag every change-worthyR-Nitem[→ SPECTRA]with an explicit[ESL-PROPOSAL]marker naming theFINDING-XXX/GAP-XXXit rests on, and state plainly that the item proposes opening an ESL change atproposed. This is the same artifact Phase S already emits — no new file, no new schema. - frame the envelope objective. In
scout-report.envelope.json, setperformative: "PROPOSE"(the existing default for ATLAS→SPECTRA) and wordobjectiveto name the ESL proposal intent, e.g."Deliver scout report for mission <id>, proposing an ESL change at 'proposed' for FINDING-003/FINDING-007.". Theiseblock is unchanged from the standard scout-report emission (skills/synthesize/SKILL.md"Envelope sidecar"):ise.assertion_grade: "self-attested"andise.receiver_authorization: {auto_route: true, auto_merge: false, auto_deploy: false}— SPECTRA MAY auto-route the finding into its own ESL intake without an operator confirm, but MUST NOT auto-merge or auto-deploy anything off an ATLAS-originated discovery. - hand off via the existing edge. Deliver
scout-report.md+scout-report.envelope.jsonto SPECTRA exactly asskills/synthesize/SKILL.mdalready prescribes (contracts/atlas-to-spectra.yaml,artifact.kind: scout-report, unchanged). SPECTRA'sspectra-esl-hopskill (when.spectra/and tonberry are present on its side) takes it from there: right_size → propose → specify.
Invariants
- Refusal boundary intact. ATLAS never calls a tonberry write verb
(
propose,transition,archive,verify) and never touches.spectra/changes/. This hop is discovery framing on an artifact ATLAS already emits, not a new write surface. - SPECTRA owns
proposed. The actualchange.jsonatproposedstatus is created by SPECTRA's hop, never ATLAS's. ATLAS's contribution is evidence carried across the existing roster edge (contracts/atlas-to-spectra.yaml), not a tonberry-recognized object. - No new artifact kind, no new contract. The proposal rides inside the
standard
scout-reportartifact/envelope pair — inventing a distinct ECLartifact.kindhere would require a contract change outside ATLAS's repo; this hop deliberately does not do that. - Evidence-anchored, same as every ATLAS claim. Every
[ESL-PROPOSAL]item cites aFINDING-XXX/GAP-XXX+ itspath:lineanchor (I-7). No new claims are introduced at this hop. - Graceful skip. No
.spectra/directory, or no change-worthy finding → skip silently, emitscout-report.mdnormally. ESL is opt-in.
ATLAS — ESL Lifecycle Hop (the DISCOVER hop; upstream of proposed, never a maker)
04 同仓库更多 Skills
wine-dxvk-cache-clear
Clear a stale DXVK shader cache that is causing graphical corruption in a Wine or Proton game. Use when: a game shows corrupted textures or shader flicker that started after a driver or DXVK version change.
steam-download-region-fix
Fix a Steam client stuck at very low download speed by changing its download region. Use when: Steam downloads are far below the local internet speed for every game, not just one.
proton-battleye-eac-toggle
Toggle BattlEye or Easy Anti-Cheat runtime support for a Steam Proton game. Use when: a multiplayer game refuses to launch with an anti-cheat error under Proton.
vivi-verify-incoming
Load when reading any upstream artefact handed off to Vivi that carries a sibling .envelope.json. BLOCKING per ECL §6.2.2: the orchestrator MUST have verified the envelope's SHA-256 (eidolons verify-envelope --block / eidolons run --verify) and recorded a verify_pass before dispatch. If no verify_pass exists for the message_id, or a verify_fail is present, REFUSE to process the payload and hand back to the orchestrator. Symmetric receiver gate — every Eidolon enforces it identically.
vivi-parallel-tracks
Load ONLY under TRANCE authorization when the Plan phase yields N independent, non-overlapping implementation tracks (disjoint file sets). Operationalizes the TRANCE G4 form — parallel multi-track implementation in mandatory git-worktree isolation, max 5 clean-context tracks, a per-track verifier cascade, a non-fungible per-track ≤3 reflection budget, explicit stop conditions, and a single-threaded merge/aggregation step. Absent TRANCE gating, Vivi runs exactly as today: single-track A→P→I→V→Δ/R.
vivi-methodology
Full Vivi cycle reference — A(nalyze) → P(lan) → I(mplement) → V(erify) → Δ(Delta)/R(eflect). Use when the task is a non-trivial feature implementation in a brownfield codebase and you need the complete methodology reference: complexity routing, evidence-grounded planning rules, test-anchoring requirements, and failure-escalation thresholds.