deprecated/researching-gourmet-venues/SKILL.md
Deprecated internal workflow for auditable city-based food research with multi-source evidence, scope-checked rankings, standardized scoring, and synchronized candidate, recommendation, and exclusion files.
npx skillsauth add narumiruna/agent-skills researching-gourmet-venuesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This rarely used workflow is excluded from active discovery but retained for explicit local compatibility. Keep evidence, scores, and decisions traceable across a six-file city research pack.
overview.md.assets/templates/ into gourmet/<city-slug>/ to create overview.md, inbox.md, candidates.md, notes.md, top-places.md, and excluded.md; replace placeholders before research.Never fabricate sources, ratings, hours, or claims. Use unknown. Never delete a candidate: mark it rejected and record the reason in excluded.md.
inbox.md, then move viable entries to candidates.md with status.notes.md evidence block for each candidate with practical constraints. Require four independent source roles by default: official channel, maps/aggregator, local reviews, and guide/editorial.evidence: limited, why, and attempted sources. Do not score or publish a recommendation with fewer sources outside this exception.notes.md, candidates.md, top-places.md, and excluded.md. Leave no unresolved inbox status in the final pack.Before returning “highest score” or top-N results, confirm:
Handle consent, language, or location gates so list items actually render. If static extraction fails, use available browser tooling; do not substitute a nearby ranking scope. Record exclusions needed to enforce the requested boundary.
Check all six files exist; language and original-name policy are recorded; claims and ratings have sources or unknown; limited evidence and negative-review triggers are documented; score arithmetic and thresholds are correct; and every candidate appears consistently in recommendation or exclusion outputs.
Return the requested recommendations first, then source coverage, score rationale, practical caveats, and any unresolved evidence gap.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.