Menu
Advisory-only algorithm and data-structure review gate between Technical Design and Task List.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Strict parser and validator for Workbench closeout comments, verdict/status discipline, PR reference types, and cross-issue REMAINING sync.
Scout, pilot, or review Mirage virtual-filesystem tool use for Workbench agents while preserving source-of-truth and public-safety boundaries.
Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.
Disk, swap, VM, agent workspace, and stale session hygiene for Multica workbench runtimes.
Durable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.
Use when an operator asks what changed recently, what was left hanging, what can move now, "gm", "where are we", or when a session-derived update needs to become visible to the whole Workbench. Recall recent memory, verify live repo/issue/automation state, surface drift first, and produce a short evidence-labeled action menu.
| name | workbench-algorithm-advisory-gate |
| description | Advisory-only algorithm and data-structure review gate between Technical Design and Task List. |
Use this skill when an issue declares SDD_STAGE: Algorithm Advisory Gate,
asks for algorithm review before Task List, or assigns the Remote Algorithm
Advisor.
SDD_STAGE: Technical Design block.docs/algorithm-advisory-gate-lane.md.code_scope or SCOPED_EVIDENCE.data-algo skill entrypoint.Do not read unrelated issue history or broad repo trees unless the Technical Design names that evidence.
.capy/settings.json, Multica
runtime config, Sanity datasets, credentials, or Workbench Max.HOME and temporary Claude config when running in a
VM or disposable cell.FLAG with the
observed model readback.ALGO_ADVISORY_REPORT
target_issue:
source_stage: Technical Design
runtime:
model:
isolation:
skill_sources:
code_scope:
correctness_verdict: PASS | BLOCK
complexity_verdict: PASS | FLAG | BLOCK
data_structure_notes:
algorithmic_risks:
task_list_injections:
verification_injections:
settings_readback:
residual_risk:
VERDICT: PASS | FLAG | BLOCK
PASS: no correctness blocker and complexity risk is acceptable.FLAG: Task List may proceed only if advisory injections become explicit
tasks, checks, or residual risks.BLOCK: Technical Design must be revised before Task List because the
advisor found a concrete correctness, data-loss, privacy, concurrency, or
semantic risk.