* feat: add golang-uber-dig and golang-uber-fx skills
Two new library skills covering uber-go's reflection-based DI ecosystem. golang-uber-dig covers the container, Provide/Invoke, dig.In/dig.Out, named values, value groups, dig.As, optional deps, Decorate, Scopes, error handling, and Visualize. golang-uber-fx covers fx.New/Run, lifecycle hooks, fx.Module, fx.Annotate, fx.Supply/Replace/Decorate, fxevent logging, and fxtest. Each skill ships recipes.md (end-to-end app examples) and testing.md (test patterns and CI graph validation), and cross-references golang-samber-do, golang-google-wire, and golang-dependency-injection.
* refactor(uber-dig,uber-fx): trim SKILL.md under 2,500 tokens
Both SKILL.md exceeded the project budget. Moved Decorate, Scopes, optional deps, error helpers, Visualize, and Quick Reference into references/advanced.md for both skills. dig: 3,744 -> 2,264 tok. fx: 4,466 -> 2,499 tok. README updated.
* test(uber-dig,uber-fx): add eval prompts and assertions
11 adversarial evals per skill targeting unique guidance: parameter objects, value groups (with flatten), named values, dig.As to hide concrete types, scopes for request locals, container at composition root, DryRun graph validation, Decorate, RecoverFromPanics, fx vs dig choice. fx evals additionally cover lifecycle non-blocking OnStart, fx.Annotate vs fx.Out, modules, fx.Supply, fx.Replace + fx.Populate in fxtest, fxevent.ZapLogger, manual lifecycle for CLI embedding.
* test(uber-dig,uber-fx): add preliminary eval results to EVALUATIONS.md
Ran 4 evals × 2 configs per skill (16 subagents total) with Claude Opus 4.7. Both skills score 100% with-skill. Without-skill: dig 90% (-10pp uplift), fx 95% (-5pp uplift). The base model has very strong baseline knowledge of both libraries; only adversarial evals targeting subtle API choices (Decorate vs scope-shadow Provide; fx.As interface binding) showed meaningful uplift. Full 11-eval suite (53/56 assertions) remains in evals.json for re-runs via /skill-creator.
* fix(uber-dig): clean up unused context import and fix handler signature in recipes
* fix(golang-uber-dig,golang-uber-fx): address PR #25 review comments and deep review findings
PR comments:
- dig/advanced.md: rephrase "module boundaries" to "scope/package wiring boundaries"
- dig/recipes.md: fix ignored repo.List error in HTTP handler (return 500)
- dig/recipes.md: remove unused context import and _ = context.Background hack
- dig/recipes.md: fix handle() signature to idiomatic (w, r) order
- fx/testing.md: assert net.Listen error before using listener
Deep review:
- dig/advanced.md: add code example for dig.Export(true) call site
- dig/advanced.md: clarify c.String() as text summary, not DOT output
- dig/recipes.md: add missing root.Provide(NewHandler) to request-scope recipe
- fx/advanced.md: add fx.ErrorHook to lifecycle quick reference
- fx/testing.md: add zaptest/observer import hint to observer example
- fx/testing.md: comment why lc.Start is used instead of RequireStart
Redesigned 116 eval groups that showed no delta between with/without
skill runs. Three failure modes addressed:
- Both-fail (adversarial override): removed explicit wrong instructions
from prompts; traps now make the wrong approach a natural default
- Both-pass (common knowledge): replaced widely-known patterns with
Go-specific, niche, or counterintuitive scenarios the model misses
without the skill
- Both-partial (mixed assertions): split homogeneous groups, removed
common-knowledge assertions, fixed coverage-gap ones
Also strengthened eval design principles in CLAUDE.md: clearer
adversarial framing rules, pre-flight gate, positive-trigger
preference, training-data saturation heuristic.
- Replace imperative "search for latest version / check URL" instructions
with passive availability hints in golang-continuous-integration,
golang-dependency-management, golang-modernize, and golang-samber-ro
- Replace `go install govulncheck@latest` with golang/govulncheck-action@v1
in CI security asset (W012)
- Remove `gh repo view` from dependency evaluation checklist (W011)
- Add golang-performance step: paste benchstat output in commit body
- Document W011/W012/W001 fix patterns in CLAUDE.md for future authors
- Add snyk-agent-scan step to the "After updating a skill" workflow
- Bump plugin to v1.2.5; bump affected skill versions
Skills need user-invocable: true to work correctly when installed as a
Claude Code plugin. Updated 25 SKILL.md files that had it set to false.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Introduce skill-library-version in openclaw metadata for skills covering
versioned third-party projects. Add workflow in CLAUDE.md for periodically
checking outdated skills against upstream changelogs. Apply to all 15
library-specific skills with latest upstream versions.
Add AskUserQuestion to the allowed-tools documentation table in
CLAUDE.md and to the allowed-tools frontmatter of all 24 existing
skills, enabling skills to clarify user intent before proceeding.
Bump patch version for all affected skills and plugin (1.2.3 → 1.2.4).
- Add clawhub-publish.sh to publish all skills with version > 0.0.0
- Refactor workflow to use the shared script
- Add WIP skills with version 0.0.0 (skipped by publish)
Samuel Berthe
GustavandGitHub
Александр МелентьевandGitHub
Barkhayot JuraevandGitHub
Paulo GodinhoandGitHub
Brian KetelsenandGitHub