Thread experiment_type and methodology_tradition through research recipe#2160
Merged
Trecek merged 1 commit intoMay 7, 2026
Conversation
…ch recipe - plan_visualization now receives experiment_type as 4th positional arg - plan_visualization captures methodology_tradition from Tier-C routing - generate_report, generate_report_inconclusive, re_generate_report receive --experiment-type and --methodology-tradition flags - skill_contracts.yaml updated: plan-visualization gains experiment_type input and methodology_tradition output; generate-report gains both as inputs - plan-visualization SKILL.md: updated args, Step 0, Step 5 (YAML header), Step 7 (methodology_tradition token), ALWAYS section - generate-report SKILL.md: updated args and Step 3 (YAML frontmatter) - 7 new tests in TestResearchRecipeStructure (T1-T7) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Trecek
deleted the
auto-research-9-1-thread-experiment-type-methodology-traditi/855
branch
Trecek
added a commit
that referenced
this pull request
May 8, 2026
…ipe (#2160) ## Summary Thread `experiment_type` (already captured by `review_design`) and `methodology_tradition` (to be captured from `plan_visualization`'s Tier-C routing) through `research.yaml` as explicit context variables consumed by `plan_visualization`, `generate_report`, `generate_report_inconclusive`, and `re_generate_report`. Update the two target skill SKILL.md files to accept these arguments and write them to output metadata. Update `skill_contracts.yaml` to declare the new input/output contracts. ## Requirements <!-- No additional requirements --> ## Implementation Plan Plan file: `/home/talon/projects/autoskillit-runs/impl-20260507-065934-667427/.autoskillit/temp/make-plan/thread_experiment_type_methodology_tradition_plan_2026-05-07_070500.md` 🤖 Generated with [Claude Code](https://claude.com/claude-code) via AutoSkillit <!-- autoskillit:pipeline-signature steps=prepare_pr,run_arch_lenses,compose_pr,annotate_pr_diff,review_pr --> ## Token Usage Summary | Step | Model | count | uncached | output | cache_read | peak_ctx | turns | cache_write | time | |------|-------|-------|----------|--------|------------|----------|-------|-------------|------| | plan | claude-opus-4-6 | 1 | 94 | 14.9k | 1.5M | 82.4k | 96 | 78.7k | 9m 57s | | verify | claude-opus-4-6 | 1 | 7.5k | 16.4k | 2.2M | 117.2k | 52 | 104.1k | 6m 12s | | implement* | MiniMax-M2.7-highspeed | 1 | 1.7M | 9.8k | 1.1M | 29.8k | 90 | 79.1k | 7m 7s | | prepare_pr* | MiniMax-M2.7-highspeed | 1 | 105.6k | 3.5k | 265.0k | 29.8k | 24 | 15.2k | 1m 18s | | compose_pr* | MiniMax-M2.7-highspeed | 1 | 77.9k | 1.5k | 235.2k | 29.8k | 20 | 15.0k | 45s | | **Total** | | | 1.9M | 46.1k | 5.2M | 117.2k | | 292.2k | 25m 19s | \* *Step used a non-Anthropic provider; caching behavior may differ.* ## Token Efficiency | Step | LoC Changed | cache_read/LoC | cache_write/LoC | output/LoC | |------|-------------|----------------|-----------------|------------| | plan | 0 | — | — | — | | verify | 0 | — | — | — | | implement | 138 | 7743.0 | 573.3 | 71.3 | | prepare_pr | 0 | — | — | — | | compose_pr | 0 | — | — | — | | **Total** | **138** | 38022.7 | 2117.4 | 333.9 | ## Model Usage Breakdown | Model | steps | uncached | output | cache_read | cache_write | time | |-------|-------|----------|--------|------------|-------------|------| | claude-opus-4-6 | 2 | 7.6k | 31.3k | 3.7M | 182.8k | 16m 9s | | MiniMax-M2.7-highspeed | 3 | 1.9M | 14.8k | 1.6M | 109.4k | 9m 10s | Co-authored-by: Claude Opus 4.7 <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
Thread
experiment_type(already captured byreview_design) andmethodology_tradition(to be captured fromplan_visualization's Tier-C routing) throughresearch.yamlas explicit context variables consumed byplan_visualization,generate_report,generate_report_inconclusive, andre_generate_report. Update the two target skill SKILL.md files to accept these arguments and write them to output metadata. Updateskill_contracts.yamlto declare the new input/output contracts.Requirements
Implementation Plan
Plan file:
/home/talon/projects/autoskillit-runs/impl-20260507-065934-667427/.autoskillit/temp/make-plan/thread_experiment_type_methodology_tradition_plan_2026-05-07_070500.md🤖 Generated with Claude Code via AutoSkillit
Token Usage Summary
* Step used a non-Anthropic provider; caching behavior may differ.
Token Efficiency
Model Usage Breakdown