Stats
Actions
Tags
From openltm
Explores codebase and LTM, then writes acceptance criteria. Use when defining what to build before planning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openltm:SpecThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before writing a spec, explore the codebase and recall prior decisions from LTM. Produces acceptance criteria that feed directly into `/plan`.
Before writing a spec, explore the codebase and recall prior decisions from LTM. Produces acceptance criteria that feed directly into /plan.
LTM tools and the recall → learn ritual live in one place: SkillSearch('ltm memory contract') loads the Ltm skill.
| Workflow | Trigger | File |
|---|---|---|
| ExploreAndSpec | "spec", "define what to build", "requirements", "before plan" | Workflows/ExploreAndSpec.md |
Example 1: New feature on existing project
User: "/spec add rate limiting to the API"
→ recall + context for auth/API decisions
→ Explores existing middleware and route files
→ Writes spec with acceptance criteria into specs/
→ Hands off to /plan
Example 2: Bug investigation
User: "/spec the session token expires too early"
→ recall for session/auth gotchas
→ Explores auth files and session logic
→ Writes spec with reproduce steps and acceptance criteria
→ Hands off to /test (ProveIt)
npx claudepluginhub rohirik/openltm --plugin openltmCreates structured specifications before coding for new projects, features, or changes with unclear requirements. Covers objectives, commands, project structure, code style, testing strategy, and boundaries.
Generates structured feature specifications with demoable units, functional requirements, and proof artifacts. Use when defining what to build before writing code.
Converts vague feature ideas into written, agreed specifications through structured questioning across nine dimensions. Produces docs/specs/*.md with acceptance criteria for planning, scaffolding, and TDD tools.