feat: increase SSE scanner buffer to 4MB for Anthropic tool calls, add stream error handling, prune unused Go dependencies, and add setup instructions.

2026-05-13 15:09:27 +03:00
parent 7447cb3a56
commit 28eb7e849b
9 changed files with 114 additions and 175 deletions
@@ -0,0 +1,3 @@
+{
+  "fingerprint": "d35fb72ca25ede907167295353fec5720ab0fcb8"
+}
@@ -0,0 +1,75 @@
+# Skill Registry — opantoantro
+
+<!-- Auto-generated by gentle-ai skill-registry refresh. Run `gentle-ai skill-registry refresh --force` to regenerate. -->
+
+Last updated: 2026-05-13
+
+## Sources scanned
+
+- /home/beyhan/.config/opencode/skills
+- /home/beyhan/.claude/skills
+- /home/beyhan/.gemini/skills
+- /home/beyhan/.cursor/skills
+- /home/beyhan/.copilot/skills
+
+## Contract
+
+**Delegator use only.** Any agent that launches subagents reads this registry to resolve compact rules, then injects matching rule text into subagent prompts under `## Project Standards (auto-resolved)`.
+
+Subagents still read their assigned executor/phase skill. During normal runtime, they do **not** independently discover or load additional project/user `SKILL.md` files or this registry; project/user rules arrive pre-digested. Explicit fallback loading is degraded self-healing and must be reported in `skill_resolution` as `fallback-registry` or `fallback-path`.
+
+## Selected skills and compact rules
+
+### branch-pr
+- Path: /home/beyhan/.claude/skills/branch-pr/SKILL.md
+- Trigger: Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### chained-pr
+- Path: /home/beyhan/.claude/skills/chained-pr/SKILL.md
+- Trigger: Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### cognitive-doc-design
+- Path: /home/beyhan/.claude/skills/cognitive-doc-design/SKILL.md
+- Trigger: Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### comment-writer
+- Path: /home/beyhan/.claude/skills/comment-writer/SKILL.md
+- Trigger: Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### go-testing
+- Path: /home/beyhan/.claude/skills/go-testing/SKILL.md
+- Trigger: Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### issue-creation
+- Path: /home/beyhan/.claude/skills/issue-creation/SKILL.md
+- Trigger: Create Gentle AI issues with issue-first checks. Trigger: creating GitHub issues, bug reports, or feature requests.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### judgment-day
+- Path: /home/beyhan/.claude/skills/judgment-day/SKILL.md
+- Trigger: Trigger: judgment day, dual review, adversarial review, juzgar. Run blind dual review, fix confirmed issues, then re-judge.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### skill-creator
+- Path: /home/beyhan/.claude/skills/skill-creator/SKILL.md
+- Trigger: Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.
+
+### work-unit-commits
+- Path: /home/beyhan/.claude/skills/work-unit-commits/SKILL.md
+- Trigger: Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
+- Rules:
+  - No compact rules declared; delegators should load the full skill file before direct work, or pass an explicit fallback path only when Project Standards cannot be injected.