telum-ai

telum-ai/speck

Agent Claude Code

Makes project or epic architecture decisions. Use inside architecture or skeptical-review phases for frontier trade-off judgment.

telum-ai/speck

Agent Claude Code

Attacks planning or implementation independently. Use during analyze or speck-audit after authorship and before downstream work.

telum-ai/speck

Agent Claude Code

Implements planned story work in isolation. Use during story-implement or harden after executable tasks and prerequisites are ready.

telum-ai/speck

Agent Claude Code

Locates files, symbols, and boundaries quickly. Use during discovery, scan, graph repair, or recheck before deeper code analysis.

telum-ai/speck

Agent Claude Code

Researches current external facts. Use inside just-in-time research or frontier scans before an external claim or choice locks.

telum-ai/speck

Agent Claude Code

Extracts code behavior and reusable patterns. Use during brownfield scan, discovery, graph repair, or recheck after file boundaries are known.

telum-ai/speck

Agent Claude Code

Authors project, epic, or story specifications. Use inside specify or epic-breakdown phases before planning begins.

telum-ai/speck

Agent Claude Code

Judges runtime outcomes and readiness. Use at story, epic, or project prove gates after the required adversarial audit.

telum-ai/speck

Skill Claude CodeCodexCursor

Re-engineers validated work after deliberate change. Use after validation to rebuild and re-prove a redesign or pivot.

telum-ai/speck

Skill Claude CodeCodexCursor

Runs decorrelated planning analysis. Use after project-plan, epic-breakdown, or story-tasks before downstream work.

telum-ai/speck

Skill Claude CodeCodexCursor

Designs epic architecture. Use after epic-clarify before epic-plan for cross-service patterns or complex integrations.

telum-ai/speck

Skill Claude CodeCodexCursor

Maps an epic to ordered, traceable stories. Use after epic-plan and before starting story work.

telum-ai/speck

Skill Claude CodeCodexCursor

Fills gaps in epic.md. Use after epic-specify when scope, boundaries, or technical intent are unclear.

telum-ai/speck

Skill Claude CodeCodexCursor

Defines local epic principles. Use after epic-clarify before epic-architecture or epic-plan when local rules are needed.

telum-ai/speck

Skill Claude CodeCodexCursor

Discovers epic boundaries from existing code and docs. Use before epic-specify when brownfield work has no epic map.

telum-ai/speck

Skill Claude CodeCodexCursor

Defines epic UI seams and emotional flow. Use after any epic UX artifacts before epic-plan for user-facing epics.

telum-ai/speck

Skill Claude CodeCodexCursor

Maps epic touchpoints, emotions, and flow. Use after epic-clarify and any architecture, before wireframes or epic-plan.

telum-ai/speck

Skill Claude CodeCodexCursor

Retired alias → speck-skeptical-review / story-tasks. Use when /epic-outline named.

telum-ai/speck

Skill Claude CodeCodexCursor

Writes epic-tech-spec.md with design and traceability. Use after epic clarification and optional architecture work.

telum-ai/speck

Skill Claude CodeCodexCursor

Synthesizes story retros into epic-retro.md. Use after epic-validate when closing an epic.

telum-ai/speck

Skill Claude CodeCodexCursor

Alias of speck-scan --level epic. Use when /epic-scan named.

telum-ai/speck

Skill Claude CodeCodexCursor

Creates epic.md from a project-plan placeholder or new scope. Use before epic-clarify and downstream epic work.

telum-ai/speck

Skill Claude CodeCodexCursor

Validates an epic across completed stories and audit evidence. Use at the epic prove gate before retrospective.

telum-ai/speck

Skill Claude CodeCodexCursor

Epic lifecycle orchestrator. Invoke only via /epic.