From f664028e9b649ea781aa95210e54b7ce7321012a Mon Sep 17 00:00:00 2001 From: Claude Date: Wed, 2 Sep 2026 16:53:30 +0000 Subject: [PATCH] skills(ai): delete the planned-eval stub and drop its ceiling row #14296 item 2 = A (comment 5507419465): the planned-eval stubs are deleted and their ceilings step down; real fixtures stay, and no new eval packages are created. This is round 2 of #14305 -- round 1 (PR #14463, merged) implemented every RESTRUCTURE finding in skills/objectstack-ai/SKILL.md and deferred AI-H-01 / AI-H-02, the evals/README.md planned-structure stub, to this ruling. Deletes skills/objectstack-ai/evals/README.md (315 tokens, 44 lines -- a placeholder whose "Structure" fence lists five eval files that do not exist anywhere in the repo) and drops its one ceiling row from scripts/check-skills-token-ratchet.mjs. That row was the only reference to the path in the tree, so nothing else reads the file. No other row changes, no ceiling raised. skills/objectstack-ai/evals/ held nothing but the stub, so the ruling's "real fixtures stay" clause has no subject here. Co-Authored-By: Claude Fable 5.1 Claude-Session: https://claude.ai/code/session_01LraLgQVGq8egUwfYZpbYt1 --- scripts/check-skills-token-ratchet.mjs | 1 - skills/objectstack-ai/evals/README.md | 44 -------------------------- 2 files changed, 45 deletions(-) delete mode 100644 skills/objectstack-ai/evals/README.md diff --git a/scripts/check-skills-token-ratchet.mjs b/scripts/check-skills-token-ratchet.mjs index f726a13153..108a75056b 100644 --- a/scripts/check-skills-token-ratchet.mjs +++ b/scripts/check-skills-token-ratchet.mjs @@ -437,7 +437,6 @@ export const CEILINGS = new Map([ ['skills/objectstack-ui/evals/analytics-inline-vs-dataset.json', 1102], // the remaining skills' eval notes - ['skills/objectstack-ai/evals/README.md', 315], ]); /** diff --git a/skills/objectstack-ai/evals/README.md b/skills/objectstack-ai/evals/README.md deleted file mode 100644 index bd34d778d1..0000000000 --- a/skills/objectstack-ai/evals/README.md +++ /dev/null @@ -1,44 +0,0 @@ -# Evaluation Tests (evals/) - -This directory is reserved for future skill evaluation tests. - -## Purpose - -Evaluation tests (evals) validate that AI assistants correctly understand and apply the rules defined in this skill when generating code or providing guidance. - -## Structure - -When implemented, evals will follow this structure: - -``` -evals/ -├── skills/ -│ ├── test-trigger-conditions.md -│ └── test-surface-affinity.md -├── tools/ -│ ├── test-json-schema-parameters.md -│ └── test-strict-unknown-keys.md -├── knowledge/ -│ └── test-knowledge-source-filters.md -└── ... -``` - -## Format - -Each eval file will contain: -1. **Scenario** — Description of the task -2. **Expected Output** — Correct implementation -3. **Common Mistakes** — Incorrect patterns to avoid -4. **Validation Criteria** — How to score the output - -## Status - -⚠️ **Not yet implemented** — This is a placeholder for future development. - -## Contributing - -When adding evals: -1. Each eval should test a single, specific rule or pattern -2. Include both positive (correct) and negative (incorrect) examples -3. Reference the corresponding section of `SKILL.md` -4. Use realistic scenarios from actual ObjectStack projects