agent-routing
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe…
Discover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which skill provides it, when the boot-emitted skill list is names-only and you need a full description, or when you want to list the catalog. Verbs are list (names only),
$ npx -y skills add oaustegard/claude-skills --skill finding-skills --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/finding-skillsContext preview
The summary Claude sees to decide when to auto-load this skill.
Discover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which skill provides it, when the boot-emitted skill list is names-only and you need a full description, or when you want to list the catalog. Verbs are list (names only),
name: finding-skills description: Discover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which skill provides it, when the boot-emitted skill list is names-only and you need a full description, or when you want to list the catalog. Verbs are list (names only), search (rank by name/description match against a query), and show (emit the full SKILL.md for a named skill). metadata: version: 0.1.0
Skills on disk at `/mnt/skills/user/` are a catalog — too expensive to preload as descriptions in every session's context. This skill is the on-demand accessor, analogous to Anthropic's ToolSearch for MCP tools.
PY=/home/user/.spokes/claude-skills/finding-skills/scripts/skills.py # List every skill by name (cheap, ~1.4KB) python3 "$PY" list # Search by keyword — ranks name matches above description matches python3 "$PY" search "adversarial review" # Load the full SKILL.md of a specific skill python3 "$PY" show challenging
In a live CCotw session the script lives at `/mnt/skills/user/finding-skills/scripts/skills.py`.
1. `search "<what you want to do>"` — get 3–10 ranked candidates 2. `show <top-pick>` — read its SKILL.md 3. Follow the SKILL.md's instructions (which may point at `scripts/`, `references/`, etc.)
Stop at step 1 if none of the candidates fit — don't shoehorn an unrelated skill onto the task.
Case-insensitive throughout. Results sorted high-to-low, ties broken by name.
All three are line-oriented so they compose with `grep`, `head`, etc.
A collection of Claude skills distributed as a Claude Code plugin marketplace. Skills are primarily designed for the Claude.ai PaaS skill compute environment; mileage will vary if used as Claude Code Agent Skills.
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe…
Cross-context adversarial review for deliverables before shipping. Use when producing blog posts, technical recommendations,…
Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six…
Routes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to,…
Delegates work to a subagent or spawned session by writing only the task, while a PreToolUse hook pages the parent transcript…
Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a…