holistic-analysis

Solid

Forces a full holistic re-analysis when a fix or refactor isn't working. Instead of continuing to patch in isolation, this skill triggers a structured step-back analysis that traces the entire execution path end-to-end — from entry point to exit — analyzing each block, every contract boundary, and the full data flow. Three modes: "fix" (default) for bugs and broken behavior, "refactor" for restructuring/improvement, and "review" for PR validation (returns structured intent-match + system-fit findings for the `pr-reviewer` agent to consume — never run on its own for routine review work). Trigger ONLY when at least one isolated fix attempt has already failed, or the user explicitly requests a full execution-path analysis — phrases like "step back", "think holistically", "analyze the whole thing", "zoom out", "look at the bigger picture", or "rethink this" qualify only in that context. Never trigger for trivial one-line fixes or first-attempt debugging. Also triggers on "/holistic", "/step-back", "/rethink", "/z

Code & Development 8 stars 2 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
32
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Holistic Analysis When this skill activates, STOP all incremental patching. Do not attempt another narrow change. Instead, execute the full analysis protocol below before writing any code. ## Contents - [Mode Detection](#mode-detection) — pick `fix` (default), `refactor`, or `review` (rule file) - [Context Gathering](#context-gathering) — 11-point checklist before reasoning - [Call-Graph Map (optional accelerator)](./rules/call-graph-map.md) — mechanically seed the execution map when a call-graph CLI is available - [Phase 1: Full Execution Path Walkthrough](#phase-1-full-execution-path-walkthrough) — entry-to-exit map, per-block analysis, contract boundaries, summary - [Phase 2: Step Back — Identify the Principle](#phase-2-step-back--identify-the-principle) - [Phase 3: Scene Set — Explain the Situation to the Duck](#phase-3-scene-set--explain-the-situation-to-the-duck) - [Phase 4: Structured Hypothesis Generation](#phase-4-structured-hypothesis-generation) — fix-mode root causes / refactor-mode approaches - [Phase 5: Meta-Cognitive Check — Challenge Your Own Reasoning](#phase-5-meta-cognitive-check--challenge-your-own-reasoning) - [Phase 6: Confidence Gate — Analysis Validation](#phase-6-confidence-gate--analysis-validation) — `/confidence analysis` or `/confidence plan` - [Phase 7: Plan the Change — Words Before Code](#phase-7-plan-the-change--words-before-code) - [Phase 8: Implement and Verify](#phase-8-implement-and-verify) — `/confidence code` gate - [Output Format](...

Details

Author
mthines
Repository
mthines/agent-skills
Created
3 months ago
Last Updated
2 days ago
Language
TypeScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Solid

optimize-approach

Reviews whether a change takes the most optimal approach for its stated intent and, when it does not, researches the code, validates a concretely better approach via holistic analysis, and either proposes it (report mode) or applies it behind a confidence gate (apply mode). Judges four axes — codebase-fit, simplicity, performance, robustness — at the approach level, deferring line-level and failure-mode findings to code-quality, critical, and holistic-review. Stays silent when the approach is already optimal (quiet early-exit). A `plan` mode reviews a drafted plan's approach at plan time (aw-planner Phase 1) — the cheapest moment to switch. Called by the reviewer and pr-reviewer agents, the polish skill, and aw-planner as a default-on lens; also runnable standalone. Triggers on "is this the best approach", "better way to do this", "is this optimal", "optimize this approach", "rethink the approach", "/optimize-approach".

8 Updated 2 days ago
mthines
Code & Development Listed

refactoring-analyst

This skill should be used when the user asks to "analyze code for refactoring", "produce a refactoring plan", "code refactoring review", "refactor analysis", "find code smells", "architectural review of this codebase", "pre-merge architectural review", "Martin Fowler refactoring catalog", "Clean Code review", "SOLID/GRASP audit", "find God classes", "find DRY/KISS violations", "module organization audit", or invokes /refactor. Produces an evidence-first, citation-bound (path:line) structured refactoring plan across 16 fixed sections with CRITICAL/HIGH/MEDIUM/LOW priorities, summary tables, and an implementation roadmap. Produces a read-only analysis and plan - does NOT modify, refactor, or rewrite code (use a code-editing tool to apply the plan), hunt runtime bugs, or run security/performance audits.

2 Updated 2 days ago
chrismccoy
AI & Automation Solid

analyze

Use when deep investigation is needed — project structure, requirement gaps, or root cause diagnosis. Supports --delegate.

11 Updated today
kangig94