Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready features. You stay in the loop for the decisions that matter. Your agents handle the the rest. One command to start building - /spectre:scope
This repository also configures its own agents. See what spectre tells them →
Skill Claude Code
Run final adversarial review through a pinned high-effort opposing runtime with one native fallback. Use at the final boundary to falsify correctness, safety, production readiness, and requirement delivery. Do not use for partial checkpoints or implementation; review only.
Skill Claude Code
Generate a grounded draft pull request from the actual diff and open it via gh. Use when wrapping up a branch or writing a PR description; not for Ship-owned cleanup, rebase, or delivery sequencing.
Skill Claude Code
Execute tasks/plans with checks/reviews/proof. Use after planning/resume. Not for planning, unplanned fixes, or pruning.
Skill Claude Code
Internal initializer for a missing Spectre feature root. Invoke only from a standalone workflow with no confirmed managed root. Do NOT invoke for existing roots, orchestrated calls missing a root, or direct user requests.
Skill Claude Code
Internal diagnosis engine for the Spectre Fix workflow. Use only when invoked by spectre-fix to investigate a reported bug and prepare its Execute handoff. Do NOT invoke directly for user requests.
Skill Claude CodeCodex
Investigate a reported bug, pin its root cause, and prepare an Execute handoff. Use for errors, stack traces, failing behavior, or repro steps. Do NOT use for greenfield work (plan/execute) or a complete repair report (execute).
Skill Claude CodeCodex
Clear session memory - archive all session files so next session starts fresh.
Skill Claude CodeCodex
Save a quiet, branch-keyed session snapshot with continuity, active work, and optional task/todo state for automatic resume. Use when ending or pausing a coding session; do not use for project documentation or workflow routing.
Skill Claude CodeCodex
User-invoked front door for durable capture. Use when the user invokes /learn or asks to remember, correct, preserve, or summarize consequential project work; interpret the request and delegate persistence to Capture. Do not use for autonomous capture, routine progress, unsupported hypotheses, personal preferences, or…
Skill Claude Code
Internal semantic classifier for Plan-or-Execute preparation. Use only from Plan or Execute with bounded routing input; never for planning, artifacts, telemetry, or user gates.
Skill Claude CodeCodex
Create a repository-grounded aligned draft after confirmed Scope, present its concise alignment brief, and hand it to Execute preflight. Do not use for scoping, bug diagnosis, read-only work, or execution of approved artifacts.
Skill Claude CodeCodex
Create one self-contained HTML prototype to resolve ambiguity, validate flows, or render UX before planning. Use for prototype/mockup/preview requests and UX Stage 1→2; not for production code, multi-file apps, scope, or planning.
Skill Claude CodeCodex
Research a codebase to answer a question — fan out read-only agents (finder/analyst/patterns, web-research for 3rd-party), then synthesize evidence-backed findings into a saved research doc with file:line citations. Use when the user asks "how does X work", "where does Y live", "investigate/research Z before…
Skill Claude Code
Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md. Trigger for new or fuzzy work or re-scoping. Do NOT trigger for technical design/research (spectre-plan) or standalone bug…
Skill Claude CodeCodex
Turn completed branch work into a reviewer-ready PR: directly coordinate cleanup, rebase, one advisory full suite, repair/route failures, and spectre-createpr. Use when asked to ship finished work. Proof is optional. Do NOT use for implementation, main/master pushes, releases, or autonomous request-to-PR delivery.
Skill Claude Code
Codex-only Spectre uninstall workflow. Use when the user wants to uninstall the native spectre@spectre Codex plugin; cleans expired workflow data and removes managed Spectre custom agents before native plugin removal while preserving marketplace registration and project knowledge.
Skill Claude CodeCodex
Define user flows, screens, states, copy, and accessibility in ux.md. Two stages: align flows, then specify. Use after scope/PRD for behavioral UX; not backend, scope, or architecture.
Skill Claude Code
Validate whether completed implementation delivers its scope/task requirements — dispatch independent @spectreanalyst checks for definition, connection, and reachability, then write one actionable validationgaps.md. Trigger for standalone requirement validation or from Execute before observed Proof. Do NOT trigger to…
Skill Claude Code
Capture durable project decisions, accepted corrections, verified reusable patterns or gotchas, disproved guidance, and changed persistent blockers as soon as they matter. The user's correction is sufficient authority without code corroboration. Do not use for routine progress, transient errors, incidental code, task…
Skill Claude Code
Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries. Requires exact ownership. Not for reusable guidance, routine progress, batches or orchestrated Create PR.
Skill Claude Code
Assess and repair a project's Spectre knowledge, work history, tags, and retrieval quality through primary-led decisions, parallel evidence review, and delegated repairs. Use for corpus cleanup, claim accuracy review, legacy migration, format compliance, or Knowledge Doctor. Not for installer/runtime diagnostics…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: