This is an automated email from the ASF dual-hosted git repository. spmallette pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/tinkerpop.git
commit c011cb4024cefb2c4f827cd0457526eabac07a14 Author: Stephen Mallette <[email protected]> AuthorDate: Fri Jul 3 17:23:09 2026 -0400 tinker-review: harmonize SKILL.md phase terminology with DESIGN.md Phase 2 now spans the agent-driven steps (enrichment, the optional functional test, and the report), matching DESIGN.md's two-phase model. Steps 3-5 are labelled Phase 2; a lead-in frames Phase 1 as step 1 and step 2 as playbook prep. Previously only enrichment carried the Phase 2 label, leaving the functional test and report as unlabelled peers. Assisted-by: Claude Code:claude-opus-4-8 --- .skills/tinker-review/SKILL.md | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/.skills/tinker-review/SKILL.md b/.skills/tinker-review/SKILL.md index 8e0e808af1..c11faa41b1 100644 --- a/.skills/tinker-review/SKILL.md +++ b/.skills/tinker-review/SKILL.md @@ -30,6 +30,11 @@ metadata: When invoked with `/review <pr-number>`: +The run has two phases (see [DESIGN.md](DESIGN.md)). **Phase 1** (step 1) is +deterministic and builds the graph. **Phase 2** (steps 3–5) is agent-driven — +enrichment, an optional functional test, then the report. Step 2 loads the +playbooks that guide Phase 2; step 6 tears down. + ### 1. Setup + Phase 1 (deterministic) Run the review script. This handles everything mechanical: @@ -82,7 +87,7 @@ meaning of every field is documented in [references/interfaces.md](references/interfaces.md) (`Evidence`), which points to the per-check `@typedef`s in `scripts/patterns/*.js`. -### 3. Phase 2 — Enrichment (agent-driven) +### 3. Phase 2 — Enrichment The Gremlin Server is still running. Use `scripts/enrichment/cli.js` to read from and write to the knowledge graph. Do NOT write your own connection @@ -134,7 +139,7 @@ The connection info is read from `/tmp/pr-review-<pr>/session.json` automaticall Follow the playbook's Enrich section. Check Escape conditions. -### 4. Functional Testing (subagent) +### 4. Phase 2 — Functional Testing (optional, subagent) **IMPORTANT: Functional testing is NOT running the project's unit tests.** DO NOT use `mvn test`. DO NOT run TreeTest, DO NOT run any existing test class. @@ -175,7 +180,7 @@ and attempts adversarial edge cases. The subagent returns: test plan, results, adversarial findings, exact test code. -### 5. Produce Report +### 5. Phase 2 — Produce Report Write the narrative JSON, then render.
