feat: add quality scoring, core principles, and 3 wiki-sourced patterns#94
Open
Charpup wants to merge 1 commit intoblader:mainfrom
Open
feat: add quality scoring, core principles, and 3 wiki-sourced patterns#94Charpup wants to merge 1 commit intoblader:mainfrom
Charpup wants to merge 1 commit intoblader:mainfrom
Conversation
…rced patterns Adds practical rewriting tools adapted from Humanizer-zh/stop-slop (quality scoring /50, 5 core principles, pre-delivery checklist) and 3 new patterns sourced from Wikipedia's Signs of AI Writing article (citation fabrication, broken markup artifacts, era-specific vocabulary clustering). Also adds a detection confidence framework that categorizes all 32 patterns by signal strength (HIGH/MEDIUM/LOW). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Charpup
added a commit
to Charpup/openclaw-task-workflow
that referenced
this pull request
Apr 18, 2026
Round-2 standardization pass. All additions additive; no breaking changes. ## Changes ### examples/humanizer-skill-schedule/ (new) Real completed run from the humanizer-skill build (PR blader/humanizer#94 merged). 21 tasks across 9 author-defined batches, which the scheduler reshapes into 12 dependency-aware batches. 4 files: - README.md: explains GOLD labeling and characteristic lessons - input-task_plan.md: verbatim snapshot of the real plan - output-schedule.json: full DAG output with tasks_extracted, batches, batch_metadata (parallelism + max complexity per batch + notes), summary (critical path, complexity sum, max parallelism) - output-handoff-snippet.json: how the same schedule lives inside triadev-handoff.json (excerpt, planning + scheduling sections only) Demonstrates fan-out (T7 → 5 downstream refs), fan-in (T13 ← 5 refs), within-batch complexity ordering (T1=1, T2=1, T16=1, T6=4 in batch 1). ### evals/evals.json (4 → 8 cases) New coverage: - batch-ordering-complexity-01: verifies within-batch tasks are ordered ascending by complexity (no-dep tasks only) - cross-session-persistence-01: CST 00:00 migration — completed tasks stay, running + pending get "migrated" status and carried over - standalone-mode-01: task-workflow works without triadev-handoff.json, reading task_plan.md directly; must NOT create triadev-handoff.json - dynamic-insertion-01: mid-execution insertion of a new task; only remaining (non-completed) tasks get re-scheduled Assertion types shifted: - Added sequence_order type for batch ordering verification - Added json_path_length for assertion on batches array size - ~80% of assertions now deterministic (file_exists, json_path_*, sequence_order, contains_all/any, does_not_contain) vs ~20% llm_judge (was 50/50 in v3.1) ### README.md Full rewrite aligning with sister-skill docs. Adds What's New in v3.2 table, Working Example callout, changelog v3.2 entry. ## Verification - 3 new JSON files parse cleanly - Example schedule consistent with SKILL.md's batch-ordering rules
Merged
3 tasks
5 tasks
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
Motivation
These additions make the skill more actionable in practice:
All new content is English-only and maintains the existing style/structure.
Test plan
🤖 Generated with Claude Code