skills/settle/SKILL.md
DEPRECATED redirect. /settle, /pr-fix, and /pr-polish now route to /deliver --polish-only <branch|PR> — the single owner of "existing branch -> merge-ready" (backlog 080 collapsed settle into deliver). Slated for deletion next release. Use when: muscle-memory "polish this", "address PR reviews", "get this merge-ready" — then run /deliver --polish-only. Trigger: /settle, /pr-fix, /pr-polish.
npx skillsauth add phrazzld/agent-skills settleInstall 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.
/settle collapsed into /deliver (backlog 080). One skill now owns
"existing branch → merge-ready," whether the branch came from /implement or
from a human. This file is a redirect, slated for deletion next release —
update muscle memory now.
/settle has no separate delegation behavior. Use
/deliver --polish-only, whose Delegation Floor and specialized phase lanes
own existing-branch merge-readiness.
| You ran | Run instead |
|---|---|
| /settle | /deliver --polish-only |
| /settle <branch\|PR> | /deliver --polish-only <branch\|PR> |
| /pr-fix <PR> | /deliver --polish-only <PR> |
| /pr-polish <PR> | /deliver --polish-only <PR> |
/ci → /code-review → /refactor → conditional
/design + /a11y → /qa) is /deliver's clean loop —
skills/deliver/references/clean-loop.md.skills/deliver/references/pr-fix.md; the
full-comment fetcher →
cargo run --locked -p harness-kit-checks -- fetch-pr-reviews.skills/deliver/references/pr-polish.md./refactor
(skills/refactor/references/simplify.md)./deliver --polish-only ends with the full /deliver closeout — a brief
plus /reflect. The old /settle stopped at merge-ready and left
reflection to /ship. Same merge-readiness gates, deliberately heavier
closeout. Full protocol: skills/deliver/references/polish-only.md.
Semantic waiver: /settle is a deprecated redirect, so its behavior is proven
by /deliver --polish-only gates rather than a separate eval. Validate this
stub with cargo run --locked -p harness-kit-checks -- check-frontmatter --repo ..
testing
Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.
testing
Route Misty Step factory application capabilities. Use when choosing, auditing, integrating, or operating Canary, Powder, Landmark, Aesthetic, or Bitterblossom: production observability, incidents, health checks, error logging, backlog/work-card state, release intelligence, UI/UX system adoption, or supervised/unsupervised agent dispatch. Trigger: /factory-apps, /factory-stack.
testing
Prove a skill beats no-skill with a falsifiable A/B eval, or retire it. Design, generate, run, and maintain a skill-specific eval: name the one claim the skill must earn, run it skill-on vs raw same-model, grade blind with objective checks first, return a keep/adapt/cut verdict. Use when: "eval this skill", "does this skill help", "prove the skill beats no skill", "write an eval for", "benchmark a skill", "is this skill worth it", "skill A/B", "skill regression test", "generate skill evals". Trigger: /skill-eval, /eval-skill, /prove-skill.
tools
> Template. Copy to `<target-repo>/.agents/skills/<repo>-<domain>/SKILL.md` > and fill every bracketed placeholder from the live target repo. Delete this > line and every other `> ` guidance line before committing. See > `../../references/repo-local-skill-generation.md` for the full process. --- name: <repo>-<domain> description: | [One paragraph: what this skill verifies/runs/operates for <repo>, stated in terms of the repo's real shape (service/CLI/library/etc.), not generic process. En