Both tasks shipped in 54ba5ca (path fix + clone fallback) and 90d066b
(monorepo clone correction — interns-mcp is a subdir of common, not a
separate repo).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Both tasks done. v1.10.1 fix shipped (aac9088), upgrade tested on claude-skills (ac0fa57).
Unblock ready — mass-rollout of 5-string group can proceed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
[hermes-flavour-mcp-setups] and [hermes-installer-skill] gated only on
[hermes-converter-mvp] (shipped in 6b36b31) — flipped 🔵 → ⚪.
[hermes-mvp-coverage] still blocked on the other two; [hermes-converter-ci]
still blocked on hermes-mvp-coverage.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Shipped in b0d2d51. Coverage check completed inline (acceptance criteria
all have evidence: SKILL.md sections, README mirror, version bump,
build+install verified, smoke-tests covered by self-application).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirror of done [using-projects-meta-fix-paths] for the sister skill.
setup-interns/SKILL.md still uses <project-root>/.common/... (cwd-
relative); should be ~/projects/.common/... like setup-projects-meta.
Surfaced during factory-bootstrap field-test (Phase 1 STOP because
claude inherited cwd C:\Windows\System32, no .common/ child there).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Surfaced during factory-bootstrap field-test on Win11 laptop.
Phase 4 of /setup-projects-meta retries clone with USER:TOKEN@host
URL on auth-failure, which git persists in .git/config of the
cloned repo. Replace with per-invocation extraheader form:
git -c http.extraheader="Authorization: token $T" clone <url>
Field-test artefact: .factory/L0/install-log.md шаг 11c-1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Combined the two backlog tasks [active-platform-tuning] +
[active-platform-eval] into a single workstream. Eval IS the tuning
mechanism; "wait for 5 real signals" was a placeholder replaced by
a 20-query synthetic eval set balanced across Win/Lin/Mac.
Spec written at .wiki/concepts/active-platform-eval-design.md
(~150 lines): 20 queries (>=3 should-trigger per OS + near-miss
negatives), run_loop.py 5-iter autoloop in parallel with manual
body sweep (WSL clarity, BSD/macOS expansion, ambiguity policy).
Workspace at .tasks/active-platform-eval/ (eval-set.json committed,
iterations gitignored). Version bump 1.0.0 -> 1.1.0 planned (MINOR).
Pre-flight verified: claude CLI on PATH at C:\nvm4w\nodejs\claude.ps1
(Claude Code 2.1.128); run_loop.py present in skill-creator install.
Both autoloop deps satisfied -- no fallback to manual single-pass.
Per-task file at .tasks/active-platform-eval.md (Goal, Key files,
Decisions log, Open questions, Notes). STATUS.md collapsed the two
original blocks into one paused block; resume point is Q2
(write 20 queries solo vs run skill-creator HTML-review template).
Also fixed in same pause: [install-ps1] STATUS scope expanded to
paired install.sh + install.ps1, cross-platform parity, prune flag
(lesson from [compress-dedup]).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
