h-semio-review
SolidINTERNAL SUBROUTINE — semiotic / fanout audit on a concept rename, deprecation sweep, or doc-vs-code consistency check. Walks all carriers (filenames, manifests, stale refs, review surfaces, dashboards, prompts) until fixed-point clean, because one-shot text replacement creates rework when carriers diverge. Manual invocation only. Do not auto-select for general work — for code review use Claude Code review; for FPF reasoning about decisions use h-frame / h-decide.
Install
Quality Score: 89/100
Skill Content
Details
- Author
- m0n0x41d
- Repository
- m0n0x41d/haft
- Created
- 6 months ago
- Last Updated
- today
- Language
- Go
- License
- NOASSERTION
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
scrutinize
Outsider-perspective end-to-end review of a plan, PR, or proposed change — questions intent first (is there a simpler way?), then traces the actual code path (not just the diff) to verify the change does what it claims. Use BEFORE committing to an implementation, or BEFORE merging a PR — pairs with `/review-ai` (scope-question vs diff-local). Output is concise, actionable, with rationale per finding. Maps to H5 (Understand First — outsider lens) + H8 (Find Your Voice — question whether the change should exist).
scrutinizing-projects
Use when asked to critique, audit, or review a codebase for architectural rot, accumulated residues, unclear naming, suboptimal design, or fitness as a base for future extension. Produces a single critique file plus a chat TL;DR. Triggers include "review my project", "audit this codebase", "is this well structured", "find tech debt", "code smells", "should we rewrite", "is this a good base for X".
code-ultrareview
Eight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools.