v0.1.1: Rubric tightening, skill merge, platform set update#10
Merged
discreteds merged 35 commits intomainfrom Apr 26, 2026
Merged
v0.1.1: Rubric tightening, skill merge, platform set update#10discreteds merged 35 commits intomainfrom
discreteds merged 35 commits intomainfrom
Conversation
Redesigns the rubric system with structured condition IDs, explicit checkable vs judgement types, hybrid AND/OR scoring, lookup tables, and fixes: annotations linking uplift actions to rubric criteria. Switches platforms to Claude/Codex/Cursor/Gemini/Antigravity/OpenClaw. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix scoring formula edge cases: define zero-critical → N/A, zero-optional → Score 3, single-critical → binary, minimum-categories guard for bands - Mark status as implementation-pending (branch still has old platform set) - Add JIT execution scope note (read-only checks on author's own repo) - Update Antigravity details from research: .agents/ preferred path, GEMINI.md priority, workflows for commands, OpenVSX distribution - Update OpenClaw details: plugin SDK hooks (before_tool_call, tool_result_persist), dual manifest requirement, bundle auto-detection - Add platform research notes to component support matrix Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
17 tasks across 5 phases: lookup tables, framework rewrite, 6 platform YAML rubrics, skill rewrites with fixes: annotations, pattern doc updates, platform set migration, and final validation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Foundation reference for rubric conditions and uplift actions. Covers model mapping, tool names, hook events, path variables, field stripping, manifest fields, hook formats, skill directories, and agent output formats across all 6 target platforms. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…scoring Replaces prose scoring with condition ID schema, checkable/judgement types, hybrid AND/OR formula, percentage-based bands, N/A handling, and JIT guidance. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Drops 15 files. Platform set is now: Claude Code, Codex, Cursor, Gemini, Antigravity, OpenClaw. Also updated all pattern documents, templates, and skills to remove references to these platforms. Cleaned up: - Injection checks (removed OpenCode plugin transform check) - Detection algorithm (removed opencodeMain and opencode_shim checks) - Hook merging (removed Copilot CLI event mapping) - Manifest generation (removed opencode and copilot-cli schemas) - Publishing & discoverability (removed both sections) - Bootstrapping pattern (removed Copilot CLI hook porting step) - Templates (updated session-start.sh hook comments) - All skills (removed platform references from descriptions and logic) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…skills Remove remaining OpenCode/Copilot references. Add Antigravity/OpenClaw entries to pattern docs. Update using-skill-portability platform list. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Merges assessing-plugin-portability and uplifting-a-plugin into single plugin-portability skill. Two upfront questions (mode + platforms), shared detection/inventory/scoring, then optional uplift phases. Pseudocode extracted to lib/patterns/ files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Restore two-layer uplift strategy: shape-based target (skill-first, full-portable-plugin, curated-note-only) + per-platform repair depth (incremental vs full from scores) - Add condition-to-artifact index built from template fixes: annotations - Phase 5 generation gated by both shape target and platform depth Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace JIT reverse-engineering of template fixes: annotations with requiring the template field on every fixable rubric condition. The rubric IS the mapping. Migration step added to populate template fields in existing YAML rubrics. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Split Phase 0 into 0a (before scanning: mode + platforms) and 0b (after detection: uplift target with shape-derived recommendation) - Use AskUserQuestion for structured input on Claude Code, with platform-equivalent fallbacks - Shape detection recommends uplift target, user confirms or overrides - Auto-derived decisions (incremental/full, codex path) stay automatic Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add create/merge/none action types for template field — merge updates existing files instead of skipping them, none emits manual action items - Replace execute_full_generation with ALLOWED_CATEGORIES table keyed by uplift target — skill-first can never generate manifests/hooks/runtime regardless of per-platform depth - Add Phase 9 summary with created/merged/manual sections Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
7 tasks: populate template fields in rubrics, create inventory pattern, create merged plugin-portability skill, reference pointers, update using-skill-portability, remove old directories, final validation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add template: fields mapping each fixable condition to its corresponding file in lib/templates/. Uses ?merge suffix for conditions that fix existing files (missing fields, coverage gaps) vs create new files. 41 template mappings across 6 platform rubrics, all paths validated. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Merges assessment Phase 2 (7 inventory substeps) with uplift Phase 2 (asset discovery + conflict detection) into a single INVENTORY function with 8 substeps, referenced by the merged plugin-portability skill. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Single entry point replacing both assessing-plugin-portability and uplifting-a-plugin. Workflow orchestrator with inline pseudocode for intent gathering (Phases 0a/0b) and generation (Phase 5), delegating detection, inventory, scoring, hooks, docs, and bootstrapping to external lib/patterns/ files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
… old skills - Add codex-tools.md and gemini-tools.md reference pointers - Update using-skill-portability to reference plugin-portability - Remove assessing-plugin-portability/ and uplifting-a-plugin/ Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Update version across all platform manifests, package.json, README badge, and CHANGELOG with full 0.1.1 release notes covering rubric tightening, skill merge, and platform set changes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove OpenCode and Copilot CLI references, add Antigravity (OpenVSX) and OpenClaw (ClawHub/npm) sections. Update skill path references from uplifting-a-plugin to plugin-portability. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
templatefields mapping to fixable artifactsassessing-plugin-portabilityanduplifting-a-plugininto singleplugin-portabilityskill with Phase 0 intent detection via AskUserQuestion# fixes:annotations. Two-layer strategy: shape-based target (user confirms) × per-platform depth (auto from scores)lib/references/platform-mappings.mdcovering model mapping, tool names, hook events, path variables, field stripping, manifest fields, hook format, skill dirs, agent formatsTest plan
plugin-portabilityskill in assess mode against a test pluginplugin-portabilityskill in uplift mode against a bare-skill-repo🤖 Generated with Claude Code