ramza-esl-hop
ESL lifecycle hop — when the cortex routes a non-trivial change to RAMZA in an ESL-enabled project (tonberry MCP available), RAMZA owns the proposed→specify hop: right-size, propose the change folder, emit the spec into it. Absent tonberry → produce the spec 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
- ramza-esl-hop
- metadata
- { "methodology": "RAMZA" }
- description
- ESL lifecycle hop — when the cortex routes a non-trivial change to RAMZA in an ESL-enabled project (tonberry MCP available), RAMZA owns the proposed→specify hop: right-size, propose the change folder, emit the spec into it. Absent tonberry → produce the spec normally (ESL opt-in).
03 SKILL.md 正文
RAMZA — ESL Lifecycle Hop
Use this skill in an ESL-enabled project (mcp__tonberry__* tools available)
when the cortex routes a non-trivial change to you. You own the
proposed → specify hop of the Eidolons Spec Lifecycle (ESL).
For the full lifecycle, stage definitions, and role bindings, see the nexus
cortex methodology/cortex/esl-protocol.md.
Your hop
-
right_size — run your own RS gate first (
ramza-rightsize, seePERSONA.md/SPEC.md) — this sets RAMZA's own planning tier (trivial/lite/full: how much of your cycle runs). Separately, score complexity through the tool —echo '{"scope":2,"ambiguity":2,"dependencies":2,"risk":2}' \ | ramza-score --rubric complexity --state <state>— and call
mcp__tonberry__right_sizewith that score, your files-touched estimate, and the trade-off rationale. Tonberry returns the ESL-level tier — a distinct classification from your own RS tier; ESL decides whether the change routes to Kupo at all. Trivial ESL-level work routes to Kupo, not you; you take lite or full. -
propose — call
mcp__tonberry__propose --change_id <id> --maker vivi --checker <kupo|vigil> --has_code <bool>. This scaffolds.spectra/changes/<id>/change.json. -
specify — run your normal RS → S → P → E → C → T → (R) → A cycle (every gate through
bin/ramza-*, seeskills/methodology/SKILL.md) and emit the spec into the change folder:- lite → one-page
spec.md(GIVEN / WHEN / THEN + acceptance_checks). - full →
spec.{md,yaml}(the standard dual-format RAMZA spec), with a recorded critic (ramza-gate critic, seeskills/critic/SKILL.md) before Assemble.
- lite → one-page
-
compose_manifest — call
mcp__tonberry__compose_manifestto settierandacceptance_checks(ids referencing your GIVEN / WHEN / THEN) inchange.json. -
emission gate — before handing off, run
ramza-verify-emit --spec <spec> [--envelope <envelope>]; nothing hands off unvalidated (seeskills/methodology/SKILL.md"ECL emission"). -
hand off to the implementer (Vivi at
in_progress) with your normal ECLPROPOSEenvelope.
Invariants
- maker(vivi) ≠ checker(kupo/vigil) — distinct roles, always, at the ESL
layer. Separately, your own plan critique is maker≠checker too
(
ramza-gate critic, mandatory at tier=full) — two independent enforcements, never conflated. - Tonberry composes artifacts; you provide spec content + signals. You
supply the complexity score (via
ramza-score), the spec text, and the acceptance-check ids; tonberry writes thechange.jsonstructure. - Graceful skip — if
mcp__tonberry__*tools are unavailable, produce the spec normally via your standard cycle and never hard-fail. ESL is opt-in; RAMZA is EIIS-standalone-conformant and works without tonberry.
RAMZA — ESL Lifecycle Hop
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.