Workbench algorithm advisory gate

Skill Fearvox/multica-ultimate-workbench/skills/workbench-algorithm-advisory-gate

Public multi-agent workbench skill pack for SDD, review gates, context discipline, VM lanes, Sanity context, and autonomous agent coordination.

Install

npx -y skills add Fearvox/multica-ultimate-workbench --skill workbench-algorithm-advisory-gate

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
23 stars23 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Advisory-only algorithm and data-structure review gate between Technical Design and Task List.

SKILL.md

1.8 KB, as published. Nobody here has run it

Workbench Algorithm Advisory Gate

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.

Required Source Reads

The latest SDD_STAGE: Technical Design block.
docs/algorithm-advisory-gate-lane.md.
The scoped files named by code_scope or SCOPED_EVIDENCE.
The mounted data-algo skill entrypoint.

Do not read unrelated issue history or broad repo trees unless the Technical Design names that evidence.

Runtime Boundary

Advisory-only. Do not edit repo files.
Do not mutate global Claude Code settings, .capy/settings.json, Multica runtime config, Sanity datasets, credentials, or Workbench Max.
Use per-lease temporary HOME and temporary Claude config when running in a VM or disposable cell.
If the exact GPT-5.5 xhigh model setup is unavailable, return FLAG with the observed model readback.

Required Report

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

Verdicts

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.