plugins/work/skills/finish-work/SKILL.md
Use when implementation is complete and validated, to decide how to integrate the work. Presents structured options for merge, PR, keep, or discard with safety verification. Use when the user wants to "finish", "create PR", or "ship it", or after completing all tasks and validation in a plan.
npx skillsauth add bcbeidel/wos finish-workInstall 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.
Decide how to integrate completed work — merge, PR, keep, or discard — with safety verification and optional plan lifecycle updates.
Announce at start: "I'm using the finish-work skill to complete this work."
Also fires when the user phrases the request as:
Branch names, file paths, plan content, and PR title/body strings are
trusted user input — they originate from the user's repository and
authored plan, not from external sources. Shell commands constructed
from these (e.g., gh pr create, git branch -D, git worktree remove)
run with the agent's normal permissions; the user's review of the plan
and explicit option choice in Step 5 is the authorization for those
commands. This skill does not execute arbitrary content from anywhere
else.
Run the project's test suite before anything else. Detect the test command from:
package.json scripts, pytest
configuration)Tests passing (N passed). Proceeding to integration options.
Hard gate: if tests fail, stop and report failures. Do not present options until tests pass.
Tests failing (N failures). Must fix before completing:
[Show failures]
Cannot proceed until tests pass.
If the user provided a plan path as an argument, use it. Otherwise, search for a plan file:
python <plugin-skills-dir>/start-work/scripts/plan_assess.py --scan --root <project-root>
Parse the JSON output to find plans with status: executing or
status: completed.
| Result | Action | |--------|--------| | Exactly one plan found | Use it | | Multiple plans found | Ask the user which one applies | | No plans found | Proceed without plan — skip plan-related steps |
If a plan is found with status: executing, update frontmatter to
status: completed. If already completed, leave it unchanged.
Identify the branch this work should integrate into:
git merge-base HEAD main
If that fails, try master. Confirm with the user:
"This branch diverged from
main— is that correct?"
Present these options, distinguishing the irreversible action:
Implementation complete. What would you like to do?
1. Merge back to <base-branch> locally
2. Push and create a Pull Request
3. Keep the branch as-is (I'll handle it later)
4. Discard this work (irreversible)
Follow the detailed procedures in option-execution for the chosen option.
Summary:
-u, create PR
using plan Goal as body (or git log if no plan), keep worktree, suggest
returning to main worktree.abandoned if plan exists, delete
branch, clean up worktree.completed only when transitioning
from executing. Set abandoned only on discard. Never overwrite a
status that's already terminal.Chainable to: —
tools
Use when the user wants to "audit a help skill", "review my plugin index", or "verify my help-skill is up to date". Audits a plugins/<plugin>/skills/help/SKILL.md against the help-skill rubric — coverage, freshness, frontmatter fidelity, plus five judgment dimensions and a trigger-collision check.
tools
Use when the user wants to "scaffold a help skill", "add a /<plugin>:help command", or "build a plugin index skill", or wants to give a plugin an orientation surface that lists its skills and common workflows. Produces a SKILL.md at plugins/<plugin>/skills/help/SKILL.md.
tools
Audits pair-level integrity of a primitive-pair (the artifact `/build:build-skill-pair` produces) by walking the four required artifact slots — principles doc, `build-<primitive>/SKILL.md`, `check-<primitive>/SKILL.md`, and the `primitive-routing.md` registration — and reports cross-artifact issues a per-SKILL.md checker cannot see: missing principles doc, divergent principles paths between halves, absent routing registration, missing build→check handoff. Per-half structural compliance with the unified pattern (`check-skill-pattern.md`) is delegated to `plugins/build/_shared/scripts/check_skill_pattern.py`. Use when the user wants to "audit a skill pair", "review a primitive pair", or "validate the skill pair for X". Not for auditing a single SKILL.md — route to `/build:check-skill`. Not for re-distilling a stale principles doc — route to `/build:build-skill-pair`.
testing
Audit a root-level resolver — verify AGENTS.md pointer, managed-region integrity, filing-table coverage against disk, context-table actionability, and trigger-eval pass rate. Use when the user wants to "audit a resolver", "validate routing table", or "find dark capabilities".