Strip the disable-model-invocation frontmatter key from all 19 editable skills. Absent = default = model invocation enabled. 8 were 'true' and blocked the model AND orchestrators from self-routing (status, plugin-check, analyze, onboard, refactor, init-project, pdf-translate, ship-feature) — contradicting the CLAUDE.md skill-routing rules. The other 11 were 'false', a no-op noise line.
The setting is binary (no per-caller granularity), so enabling orchestrator chaining also enables model auto-fire — accepted. Genuinely destructive operations remain guarded by the careful/guard hooks, independent of this flag.
Capitalized: BDR-019 (decision), LRN-026 (learning), journal 2026-06-09.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The awk extraction now correctly parses both `description: text` (inline)
and `description: |` (block scalar) YAML formats.
Co-Authored-By: Claude <noreply@anthropic.com>
Personal skills are identified by checking if their SKILL.md references
an agent file from ~/.claude/agents/. Adds agent column to output table.
Replaces unreliable git history heuristic.
Co-Authored-By: Claude <noreply@anthropic.com>
Use git history heuristic: skills added in bulk commits (5+ SKILL.md
files at once) are framework installs, not user-created. Only show
skills added in small commits (1-3 files).
Co-Authored-By: Claude <noreply@anthropic.com>
Lists all local skills from ~/.claude/skills/ with name and description,
excluding symlinked/external ones (gstack, emil-design-eng).
Co-Authored-By: Claude <noreply@anthropic.com>