@webpresso/plugin-claude 0.0.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +21 -0
- package/.claude-plugin/plugin.json +20 -0
- package/LICENSE +104 -0
- package/bin/wp +60 -0
- package/commands/audit.md +29 -0
- package/commands/blueprint.md +27 -0
- package/commands/qa.md +5 -0
- package/commands/test.md +5 -0
- package/package.json +41 -0
- package/plugin-skill-ownership.json +99 -0
- package/skills/ai-deslop/SKILL.md +91 -0
- package/skills/autopilot/SKILL.md +77 -0
- package/skills/autoresearch/SKILL.md +49 -0
- package/skills/best-practice-research/SKILL.md +89 -0
- package/skills/browse/SKILL.md +25 -0
- package/skills/claude/SKILL.md +186 -0
- package/skills/codex/SKILL.md +142 -0
- package/skills/deep-interview/LICENSE.txt +28 -0
- package/skills/deep-interview/SKILL.md +269 -0
- package/skills/deep-research/SKILL.md +258 -0
- package/skills/delivery-program/SKILL.md +57 -0
- package/skills/design-review/SKILL.md +26 -0
- package/skills/devex-review/SKILL.md +28 -0
- package/skills/fix/SKILL.md +174 -0
- package/skills/grok/SKILL.md +32 -0
- package/skills/hooks-doctor/SKILL.md +78 -0
- package/skills/investigate/SKILL.md +72 -0
- package/skills/lore-protocol/SKILL.md +84 -0
- package/skills/opencode-go/SKILL.md +97 -0
- package/skills/plan-ceo-review/SKILL.md +27 -0
- package/skills/plan-design-review/SKILL.md +27 -0
- package/skills/plan-devex-review/SKILL.md +19 -0
- package/skills/plan-eng-review/SKILL.md +24 -0
- package/skills/plan-refine/SKILL.md +50 -0
- package/skills/plan-refine/references/full-methodology.md +645 -0
- package/skills/ralplan/SKILL.md +50 -0
- package/skills/team/SKILL.md +77 -0
- package/skills/tech-debt/SKILL.md +79 -0
- package/skills/testing-philosophy/SKILL.md +53 -0
- package/skills/testing-philosophy/references/full-testing-philosophy.md +523 -0
- package/skills/tph/SKILL.md +35 -0
- package/skills/ultragoal/SKILL.md +179 -0
- package/skills/verify/SKILL.md +283 -0
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
---
|
|
2
|
+
type: skill
|
|
3
|
+
slug: plan-refine
|
|
4
|
+
title: Plan Refinement Methodology
|
|
5
|
+
status: active
|
|
6
|
+
scope: repo
|
|
7
|
+
applies_to: [agents]
|
|
8
|
+
related: []
|
|
9
|
+
created: "2026-05-07"
|
|
10
|
+
last_reviewed: "2026-07-03"
|
|
11
|
+
name: plan-refine
|
|
12
|
+
description: "Blueprint hardening: fact-check assumptions, run plan reviews, split parallel tasks, and lock verification."
|
|
13
|
+
---
|
|
14
|
+
|
|
15
|
+
# Plan Refinement Methodology
|
|
16
|
+
|
|
17
|
+
Use when a blueprint or implementation plan needs fact-checking, architecture hardening, parallel task shaping, or review consolidation before execution.
|
|
18
|
+
|
|
19
|
+
## Core principle
|
|
20
|
+
|
|
21
|
+
A plan is only as strong as its weakest unchecked assumption and only as fast as its coarsest task granularity.
|
|
22
|
+
|
|
23
|
+
## Required workflow
|
|
24
|
+
|
|
25
|
+
1. **Technology fact-check.** Verify API, version, runtime, platform, and package claims against official/upstream sources when external behavior matters.
|
|
26
|
+
2. **Codebase verification.** Confirm file paths, exports, existing patterns, dependency availability, and local command surfaces in the repo.
|
|
27
|
+
3. **Architecture review.** Challenge race conditions, error cascades, ownership boundaries, concurrency, auth/session edges, public-package leakage, and unnecessary abstractions.
|
|
28
|
+
4. **Plan-review lenses.** Folded `/autoplan`: run the relevant CEO/founder, design, engineering, and DevEx review lenses; consolidate keep/change/drop decisions, unresolved taste calls, tests, and go/no-go.
|
|
29
|
+
5. **Blueprint enforcement.** Split tasks for independent execution, declare dependencies, identify file conflicts, require TDD/proof steps, and preserve acceptance criteria.
|
|
30
|
+
6. **Apply and record.** Update edge cases, risks, technology choices, cross-plan references, and verification gates. Do not edit implementation code during plan refinement.
|
|
31
|
+
|
|
32
|
+
## Mandatory gates
|
|
33
|
+
|
|
34
|
+
- Apply DRY, SOLID, YAGNI, and KISS; reject speculative abstractions.
|
|
35
|
+
- Choose the most elegant and durable solution the constraints allow, not merely a correct one: prefer deleting/reusing over adding, shrink public/export surface to the minimum real consumers require, keep the change scoped to one coherent idea, and reject the heavier option even when it works — record in the plan why the chosen shape is the durable one.
|
|
36
|
+
- For package, catalog, generated-surface, or release changes, require package-surface and public-content checks.
|
|
37
|
+
- Prefer deletion/reuse over new layers or dependencies.
|
|
38
|
+
- Stop on unverified external claims, unresolved shared-file conflicts, or missing authority for destructive work.
|
|
39
|
+
|
|
40
|
+
## Output
|
|
41
|
+
|
|
42
|
+
Return a concise plan review with:
|
|
43
|
+
|
|
44
|
+
- verdict: ready / ready with edits / blocked
|
|
45
|
+
- material corrections with evidence
|
|
46
|
+
- task/dependency changes needed for parallel execution
|
|
47
|
+
- required tests and audits
|
|
48
|
+
- residual risks or explicit blockers
|
|
49
|
+
|
|
50
|
+
For the full historical checklist and examples, read `references/full-methodology.md` only when deeper plan surgery is needed.
|