Skill curiosity shelf¶

Interesting, playful, provocative, or highly personal agent skills that are worth remembering but are intentionally kept outside this repo's daily workflow.

Entries on this page are docs-only. They are not copied into skills/vendor/, listed in vendor.yaml, or exposed through the marketplace, so they do not participate in skill discovery unless someone explicitly visits and installs an upstream project.

Status enum (single source of truth across the catalog)

Every external-skill or MCP entry below carries a status: value:

Status	Meaning	Where it links
`vendored`	Already in `vendor.yaml`.	Link to the `skills/vendor/<name>/` (or series) entry.
`deferred`	Open `TODO P?` item — under consideration.	Link to the `TODO.md` anchor.
`skipped`	Looked at, chose not to vendor.	Inline reason required (1 sentence).
`evaluated`	Read but no decision recorded. Effectively "tracked."	Inline 1-line note describing what was learned.
`wishlist`	Surfaced but not yet evaluated.	No link required; default for fresh discoveries.

Status changes are explicit edits — see the Adding catalog entries workflow doc (under Workflows in the nav) for the wishlist → deferred → vendored recipe.

Manual install for non-vendored skills

When a skill is not in vendor.yaml, you can still install it directly from upstream via the npx skills CLI:

# Whole-repo install (if SKILL.md sits at repo root or skills/)
npx skills@latest add <owner>/<repo>

# Subpath install (when the skill is nested)
npx skills@latest add <owner>/<repo>/<path-to-skill-dir>

# Cherry-pick by name
npx skills@latest add <owner>/<repo> -s <skill-name>

# Force deep discovery (skill nested >1 level inside skills/)
npx skills@latest add <owner>/<repo> --full-depth -s <skill-name>

For Anthropic-style plugin marketplaces (e.g. anthropics/financial-services, anthropics/knowledge-work-plugins), use the Claude Code plugin commands instead:

claude plugin marketplace add <owner>/<repo>
claude plugin install <plugin-name>@<repo-name>

For MCP servers, see the per-entry "Auth & install" section in the MCP wiki — install commands vary by transport (HTTP / stdio / SSE) and host (Claude Code / Claude Desktop / Cursor / Managed Agents).

Meta-skills and persona experiments¶

Skill	Premise	Why it is interesting	Why it stays docs-only	Status
`anti-distill`	Rewrites a skill so it appears complete while withholding its most valuable tacit knowledge.	A sharp, satirical inversion of knowledge-distillation and corporate knowledge-transfer workflows.	Deliberately adversarial to ordinary documentation and knowledge-sharing goals; interesting as commentary, unsuitable for the default workflow.	`skipped`
`distilly` (formerly `colleague-skill`)	Distills source material about a colleague, relationship, or public figure into a reusable person profile for an agent.	An unusually elaborate example of persona extraction, evidence collection, and continuously updated character simulation.	Highly personal, privacy-sensitive, and outside the repo's general engineering workflow.	`skipped`
`create-ex`	Builds an evolving simulated persona of an ex-partner from memories, chat history, photos, and social posts.	A memorable experiment at the boundary between agent skills, digital memory, and emotional simulation.	Sensitive relationship data and a narrow personal-use scenario make it inappropriate for automatic discovery here.	`skipped`

Adding another curiosity¶

Add a row when a skill is worth revisiting for its idea, cultural signal, or unusual interaction design, but should not become part of normal agent behavior. Keep the note descriptive rather than endorsing the behavior.

Use skipped with a concise reason. If an entry later becomes genuinely useful for routine work, move it to External skills and follow the normal catalog status workflow.