/close-all
Batch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close".
$ npx -y skills add anton-abyzov/specweave --skill close-all --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/close-all
Context preview
The summary Claude sees to decide when to auto-load this skill.
Batch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close".
SKILL.md
close-all.SKILL.mdname: close-all
description: Batch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close".
version: 1.0.0
argument-hint: "[--dry-run]"
Batch Close All Complete Increments
Closes all active increments that have reached 100% task completion by delegating each one to `sw:done`. This skill is a thin batch-discovery loop; all actual closure logic (gates, reports, sync) lives in `sw:done`.
Step 1: Discover Closeable Increments
for meta in $(find .specweave/increments -maxdepth 2 -name "metadata.json" | sort); do
st=$(jq -r '.status' "$meta" 2>/dev/null)
[ "$st" != "active" ] && [ "$st" != "in-progress" ] && [ "$st" != "ready_for_review" ] && continue
d=$(dirname "$meta"); id=$(basename "$d"); tasks="$d/tasks.md"
[ ! -f "$tasks" ] && continue
pending=$(grep -c '\[ \]' "$tasks" 2>/dev/null || echo 0)
done_count=$(grep -c '\[x\]' "$tasks" 2>/dev/null || echo 0)
if [ "$pending" -eq 0 ] && [ "$done_count" -gt 0 ]; then
echo "CLOSEABLE: $id"
fi
doneIf no closeable increments are found, report "No increments ready for closure" and stop.
Step 2: Dry-run
If the user passed `--dry-run`, print the discovered list and stop without closing anything.
Step 3: Delegate each to `sw:done`
Iterate the discovered list sequentially. For each `<ID>`:
Skill({ skill: "sw:done", args: "<ID>" })`sw:done` owns the actual closure workflow: code-review, simplify, grill, judge-llm, PM validation, external sync, and final status transition. Close sequentially to respect dependency order; if `sw:done` fails for an increment, log the failure and continue with the next.
Step 4: Summary
Print a final summary with CLOSED / FAILED counts per increment. Failures are not retried here — the user re-runs `sw:done <ID>` individually once blockers are resolved.
Notes
- All gate logic lives in `sw:done`. This skill MUST NOT duplicate closure behaviour.
- Parallel closure is intentionally not supported — race conditions on shared living docs are a real hazard.
Read more
name: close-all description: Batch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close". version: 1.0.0 argument-hint: "[--dry-run]"
Batch Close All Complete Increments
Closes all active increments that have reached 100% task completion by delegating each one to `sw:done`. This skill is a thin batch-discovery loop; all actual closure logic (gates, reports, sync) lives in `sw:done`.
Step 1: Discover Closeable Increments
for meta in $(find .specweave/increments -maxdepth 2 -name "metadata.json" | sort); do
st=$(jq -r '.status' "$meta" 2>/dev/null)
[ "$st" != "active" ] && [ "$st" != "in-progress" ] && [ "$st" != "ready_for_review" ] && continue
d=$(dirname "$meta"); id=$(basename "$d"); tasks="$d/tasks.md"
[ ! -f "$tasks" ] && continue
pending=$(grep -c '\[ \]' "$tasks" 2>/dev/null || echo 0)
done_count=$(grep -c '\[x\]' "$tasks" 2>/dev/null || echo 0)
if [ "$pending" -eq 0 ] && [ "$done_count" -gt 0 ]; then
echo "CLOSEABLE: $id"
fi
doneIf no closeable increments are found, report "No increments ready for closure" and stop.
Step 2: Dry-run
If the user passed `--dry-run`, print the discovered list and stop without closing anything.
Step 3: Delegate each to `sw:done`
Iterate the discovered list sequentially. For each `<ID>`:
Skill({ skill: "sw:done", args: "<ID>" })`sw:done` owns the actual closure workflow: code-review, simplify, grill, judge-llm, PM validation, external sync, and final status transition. Close sequentially to respect dependency order; if `sw:done` fails for an increment, log the failure and continue with the next.
Step 4: Summary
Print a final summary with CLOSED / FAILED counts per increment. Failures are not retried here — the user re-runs `sw:done <ID>` individually once blockers are resolved.
Notes
- All gate logic lives in `sw:done`. This skill MUST NOT duplicate closure behaviour.
- Parallel closure is intentionally not supported — race conditions on shared living docs are a real hazard.
Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.
Repo: anton-abyzov/specweave
Other skills on specweave.
- /ado-mapper
Bidirectional conversion between SpecWeave increments and Azure DevOps work items. Use when exporting increments to ADO epics, importing ADO epics as increments, or resolving sync conflicts. Handles Epic/Feature/User Story/Task hierarchy mapping.
Open skill - /ado-multi-project
[DEPRECATED] Use `sw:multi-project --tool ado` instead. Organizes specs and tasks across multiple Azure DevOps projects. This skill will be removed in SpecWeave v1.3.0.
Open skill - /ado-resource-validator
Validates Azure DevOps projects, area paths, and teams exist with auto-creation of missing resources. Use when setting up ADO integration, configuring .env variables, or troubleshooting missing project errors. Supports project-per-team, area-path-based, and team-based strategies.
Open skill - /ado-sync
[DEPRECATED] Help and guidance for Azure DevOps synchronization with SpecWeave increments. Use when asking how to set up ADO sync, configure credentials, or troubleshoot integration issues. For actual syncing, use sw-ado:push or sw-ado:pull command.
Open skill - /analytics
Analytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts.
Open skill - /architect
System architect for scalable technical designs and ADRs. Use for system architecture, microservices, database design, trade-off analysis, component diagrams, tech selection.
Open skill

