anton-abyzov/specweave/done

Claude Code and agent skill by anton-abyzov/specweave

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".

Install

npx vskill@latest install anton-abyzov/specweave/done

Semi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard

SKILL.md

sw-done: close an increment

Closing is verify, review, complete. The one hard gate is a passing reports/verify.json; everything else is evidence.

Steps

  1. Board. specweave task list: every task must be done or skipped. Anything

open goes back to sw-do, or specweave task skip T-04 --reason "<why>".

  1. Verify. specweave verify runs the project's test, lint and build commands

(config testing.commands, else detected), checks every acceptance criterion against the ledger (an AC is met when all its tasks are done) and writes reports/verify.md and reports/verify.json. Red: fix and re-run. Do not tick AC boxes; they are derived.

  1. Review. For anything that ships, run sw-review in a fresh context. With

review.crossModel on, also specweave review: another model family reviews the diff (exit 3 means fix first). If the project has a GLOSSARY.md, run specweave glossary check and rename new code that uses an avoided word. Fix critical and high findings, then verify again. In a bloated context, spawn the sw-closer agent as the fresh-context option; it returns JSON, fixes nothing and completes only on a clean ship review, so re-read reports/verify.json and the review report yourself rather than trusting its summary, fix any critical or high finding here, then complete.

  1. Docs. If commands, config or user-facing behaviour changed, update README,

CHANGELOG and the ## Commands table in AGENTS.md in the same branch.

  1. Complete. specweave complete 0042. It refuses without a passing verify unless

the user gives a reason: specweave complete 0042 --reason "<why>".

  1. Ship. Push the branch and open the PR the way this repository ships;

specweave report writes an HTML timeline to attach as evidence.

Report in one paragraph: verify result, review verdict (or "skipped"), commits, anything deferred.

Accepted skips

When a check of an AC cannot be run because the user lacks an installation or a license, and the user explicitly accepts skipping that named check, record it:

bash
specweave ac accept-skip AC-03 0042 --check <check-id> --reason "<why it cannot run>" \
--accepted-by <person> --authorization "<their words, or a message/thread ref>" [--accepted-at 2026-10-27]

This records one accept-skip event in the increment's ledger, which is never rewritten, so an AC and check already accepted is refused. On an AC that no task cites, one accepted skip closes the whole AC, so the command refuses until you confirm with --uncovered (first check no task cites the AC in another form); verify marks such an AC uncovered. Reason and authorization are capped at 1,000 and 2,000 characters: quote the key words and point to the message or thread. Ordinary unavailability never authorizes it; only the user's own words do. An accepted skip is never verification: it does not tick the AC or count toward met ACs, and other work on the AC stays as it was. specweave ac list and the --json of task list, verify and pickup show each AC's acceptance: met, mixed (met by its tasks or checkbox, plus an accepted skip), skipped-accepted (not met, no task citing it is unresolved, at least one accepted skip) or open. A skipped-accepted AC lets specweave complete pass; verify.md, verify.json (acceptedSkips, acs.skippedAccepted) and the closure output name it.

Manual path (no CLI)

Check every task in spec.md has a done or skip line in ledger.jsonl. Run the project's test, lint and build commands yourself and put their real output in reports/verify.md. Then set "status": "completed" in metadata.json, the one state change the manual path makes by hand.

Rules

  • Never ask "should I close?" when the tasks are done; close, and the user can reopen.
  • Never edit metadata.json status while the CLI is available.
  • Several agents on one increment: only the lead closes, after every agent has handed

off or released its claims.

  • Completing never calls GitHub, Jira or Azure DevOps unless close-on-complete is set;

a failed sync afterwards is retried with specweave sync push.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Installs
6
Unique users
1
Repository stars
85
Repository forks
9
Repository npm downloads, 7 days
7,753
7-day trend score
48

Installs come from the vskill CLI. Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 17 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/anton-abyzov/specweave/done/badge)](https://verified-skill.com/skills/anton-abyzov/specweave/done)

Something wrong with this skill or its page? Tell us.