dist/codex/plugins/spec-dev/skills/spec-status/SKILL.md
Spec-driven development status and orientation. Use when checking overall project state, viewing a specific task with its linked req/epic, listing tasks by status, running a quality audit for orphans/cycles/missing fields, or for a pipeline overview when unsure which spec sub-skill to use. NOT for mutating state — read-only; use spec-done or spec-work for state changes.
npx skillsauth add alexei-led/claude-code-config spec-statusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read-only entry point for spec-driven development: report progress, or orient the user to the right sub-skill.
If .spec/ doesn't exist, tell the user: "No .spec/ folder. Use the spec-init skill to initialize the project." and stop.
scripts/specctl status 2>/dev/null || echo "NO_SPEC"
spec-init → spec-interview → spec-plan → spec-work → spec-done (loop until epic complete)
spec-status reads state at any point.
spec-init — initialize .spec/, or add requirements from an existing docspec-interview — deep PRD-quality requirement capture via Q&Aspec-plan — create an EPIC + vertical-slice TASKs from a requirement or ideaspec-new — one-off task or requirement from a templatespec-work — implement the next ready task (one per session, user approval at every step)spec-done — mark a task complete with evidence; optionally discover or verify firstspec-status — overview, single-task detail, filtered list, or quality audit.spec/ yet → use the spec-init skill to initialize the projectspec-interview skill to capture requirementsspec-plan skill to create tasksspec-work skill to implement the next task.spec/reqs/REQ-*.md — requirements (WHAT / WHY).spec/epics/EPIC-*.md — epics grouping related tasks.spec/tasks/TASK-*.md — vertical-slice tasks with dependencies.spec/memory/ — pitfalls, conventions, decisions discovered during work.spec/SESSION.yaml — current session (task, step, base commit).spec/PROGRESS.md — activity logFor the bundled specctl CLI command reference, read references/specctl-commands.md.
CLI at scripts/specctl. Match the user's request to one of these views:
TASK-id; show the task + its linked req/epic.total=$(fd -e md . .spec/tasks/ | wc -l | tr -d ' ')
done=$(rg -l '^status: done' .spec/tasks/ 2>/dev/null | wc -l | tr -d ' ')
branch=$(git branch --show-current 2>/dev/null || echo "no-git")
Pick the next priority-ordered todo task:
next=$(rg -l '^priority: critical' .spec/tasks/ 2>/dev/null | xargs rg -l '^status: todo' 2>/dev/null | head -1)
[ -z "$next" ] && next=$(rg -l '^priority: normal' .spec/tasks/ 2>/dev/null | xargs rg -l '^status: todo' 2>/dev/null | head -1)
[ -z "$next" ] && next=$(rg -l '^status: todo' .spec/tasks/ 2>/dev/null | head -1)
Build a top-5 requirement rollup (tasks per REQ, with done counts).
Show:
## Spec status
Branch: <branch>
Tasks: <done>/<total> complete
Next ready: <task id or "none">
### Top requirements
- REQ-<slug>: <m>/<n> tasks done
- ...
### Suggested next
spec-work # pick up the next ready task
spec-status list # see every task
spec-status check # quality audit
User passed a TASK-id. If no matching file exists under .spec/tasks/, say "Task not found." and stop.
Read the task file and any linked epic / requirement.
Show:
## TASK-<id>
Status: <status>
Priority: <priority>
Epic: <epic id or none>
Blocked by: <deps>
<task body>
### Epic
<epic overview>
### Requirement
<linked REQ summary>
list — every tasktodo — only status: todocompleted — only status: doneGroup by epic; show priority and a one-line summary per task.
scripts/specctl validate
scripts/specctl status
Surface:
acceptance criteriastatus: in-progress with no recent commits)For each issue, suggest the workflow that resolves it (usually spec-interview to enrich, spec-plan to add tasks, or manual edit).
tools
Idiomatic shell development for POSIX sh, Bash, Zsh, Fish, hooks, CI shell steps, and scriptable CLI glue. Use when writing or changing `.sh`, `.bash`, `.zsh`, `.fish`, `.bats`, shell functions, shell pipelines, or command-runner recipes. Emphasizes portability, quoting, safe filesystem/process handling, non-TUI CLI tools, ShellCheck, shfmt, Bats, and ShellSpec. NOT for Python, TypeScript, Go, web code, or infrastructure operations.
tools
Use when planning, executing, checkpointing, finishing, or inspecting lightweight spec-driven work. Runs one task at a time using `.spec/` markdown files and the bundled `specctl` helper. NOT for broad product discovery beyond a short requirement interview.
testing
Author, inspect, troubleshoot, and review infrastructure across IaC, Kubernetes, cloud resources, containers, CI/CD, and Linux hosts. Use when changing Terraform/OpenTofu, Kubernetes, Helm, Kustomize, Dockerfiles, GitHub Actions, AWS, GCP, Cloud Run, BigQuery, IAM, logs, instances, or service health. NOT for deploy/apply/rollback workflows (see deploying-infra). NOT for shell scripts or generic command pipelines (see writing-shell).
development
Configure safe git workflow hygiene: pre-commit/pre-push hooks, Gitleaks secret scanning, .gitignore rules, local git config, and guardrails. Use when setting up git hooks, gitleaks/git leaks, staged pre-commit checks, pre-push validation, core.hooksPath, .gitignore, or git config best practices. NOT for creating commits (use committing-code), cleaning branches/worktrees (use cleanup-git), or creating worktrees (use using-git-worktrees).