# New Skill

> Scaffold a new logic-* skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens.

- **Type:** Skill
- **Install:** `agentstack add skill-hyhmrright-logic-lens-new-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [hyhmrright](https://agentstack.voostack.com/s/hyhmrright)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [hyhmrright](https://github.com/hyhmrright)
- **Source:** https://github.com/hyhmrright/logic-lens/tree/main/.claude/skills/new-skill
- **Website:** https://github.com/hyhmrright/logic-lens

## Install

```sh
agentstack add skill-hyhmrright-logic-lens-new-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# new-skill

CLAUDE.md → "Adding a New Skill" is the authoritative checklist. This skill exists to make sure *every* step actually runs — the session-start loop and the eval cases are the ones most often forgotten.

**Read CLAUDE.md's "Adding a New Skill" section now**, then execute its steps for `logic-` (ask the user for `` if not in `$ARGUMENTS`):

1. **`skills/logic-/SKILL.md`** — copy the frontmatter shape from `skills/logic-review/SKILL.md` (`name` + `description`). The `description` MUST include a "Do NOT trigger for:" clause and a "SCOPE … RULE" line distinguishing it from the other skills. Process section = 5–7 numbered items, each citing a guide step. Follow lazy-loading per `skills/_shared/common.md` §13.
2. **`skills/logic-/logic--guide.md`** — numbered steps (Step 1, 2, …), each explaining the *why*, concrete examples over abstractions.
3. **`commands/logic-.md`** — mirror `commands/logic-review.md`:
   ```markdown
   ---
   description: 
   allowed-tools: Skill
   ---
   Use the Skill tool to invoke `logic-lens:logic-`, then follow its instructions exactly. $ARGUMENTS
   ```
4. **`hooks/session-start`** (CLAUDE.md step 6 — easy to miss) — add `logic-` to BOTH the `for skill in …` loop and the printed skill list:
   ```bash
   grep -n "for skill in" hooks/session-start
   ```
5. **Eval cases** (CLAUDE.md step 7 — easy to miss) — add 3–5 content cases to `evals/content/v2/evals-v2.json`. Trigger cases under `evals/trigger/v2/` are optional and only catch description regressions (positive cases always score 0% — see CLAUDE.md → Gotchas).
6. **`gemini-extension.json`** — CLAUDE.md says Gemini auto-discovers from `skills/`, but the file *also* enumerates each skill+command under `contribution`. If you want that list complete, add `logic-` entries to both `contribution.skills` and `contribution.commands`. (Not checked by `validate-repo.sh`.)
7. **Validate** — run `npm run validate` and confirm all checks pass.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [hyhmrright](https://github.com/hyhmrright)
- **Source:** [hyhmrright/logic-lens](https://github.com/hyhmrright/logic-lens)
- **License:** MIT
- **Homepage:** https://github.com/hyhmrright/logic-lens

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-hyhmrright-logic-lens-new-skill
- Seller: https://agentstack.voostack.com/s/hyhmrright
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.