From dfa1a83071f3c7700efbb7278c192caec9b666cb Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Mon, 26 Oct 2026 05:27:17 +0000 Subject: [PATCH] docs: drop separate-plugin wording for bundled skills deslop, control-cli, and control-ui are part of this plugin. Remove every mention of the upstream kit they were copied from, including skill lines that told readers to install it separately. Co-authored-by: Kaitian Xie --- .agents/skills/poteto-help/SKILL.md | 1 - .agents/skills/poteto-mode/SKILL.md | 4 ++-- .agents/skills/poteto-mode/playbooks/autopilot-full.md | 4 ++-- .agents/skills/poteto-mode/playbooks/multi-phase-plan.md | 2 +- .agents/skills/poteto-mode/playbooks/opening-a-pr.md | 2 +- .agents/skills/poteto-mode/playbooks/orchestrate.md | 2 +- .agents/skills/poteto-mode/playbooks/shipping.md | 2 +- .agents/skills/poteto-mode/references/codex.md | 2 +- README.md | 4 ++-- UPSTREAM.md | 2 +- docs/guide/05-build-and-clean.md | 2 +- 11 files changed, 13 insertions(+), 14 deletions(-) diff --git a/.agents/skills/poteto-help/SKILL.md b/.agents/skills/poteto-help/SKILL.md index 72200af..ee0befd 100644 --- a/.agents/skills/poteto-help/SKILL.md +++ b/.agents/skills/poteto-help/SKILL.md @@ -114,7 +114,6 @@ Close calls: Not in pstack: -- `/deslop`, `control-cli`, and `control-ui` ship in the `cursor-team-kit` plugin. - Long-running goals depend on the available Codex host. Skill authoring uses `skill-creator` when installed, otherwise the adapter's format guidance. - pstack has no `/orchestrate` skill. Orchestrate is a `/poteto-mode` playbook. If the slash menu shows `/orchestrate`, another plugin provides it. diff --git a/.agents/skills/poteto-mode/SKILL.md b/.agents/skills/poteto-mode/SKILL.md index 018b32d..e20790c 100644 --- a/.agents/skills/poteto-mode/SKILL.md +++ b/.agents/skills/poteto-mode/SKILL.md @@ -26,9 +26,9 @@ Remaining triggers: - Nontrivial multi-step → write the throughput checkpoint (Feature step 3). - Any prose surface, your reply to the user included → the **unslop** skill. Write the reply per **Writing the reply**. Agent-facing prose also follows the **skill-creator** skill when available (for authoring SKILL.md files). - Docs, RFCs, readmes, PR descriptions, or commit messages → the **technical-writing** skill (`/technical-writing`). -- Before commit → the `deslop` skill from the `cursor-team-kit` plugin (`/deslop`). +- Before commit → the `deslop` skill (`/deslop`). - Before review → the **no-comments** skill (`/no-comments`). -- Shipping UI / IDE / CLI → the matching control skill. `cursor-team-kit` publishes `control-cli` (CLIs and TUIs) and `control-ui` (browser / Electron / web UIs). For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception. +- Shipping UI / IDE / CLI → the matching control skill. This plugin includes `control-cli` (CLIs and TUIs) and `control-ui` (browser / Electron / web UIs). For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception. - Running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured → the **benchmark-checklist** skill before you report or act on the number. - Any PR-status request ("babysit this", "get it green", "address the bugbot comments", and most often "check on PR X" or "anything outstanding on X") → the **Babysit** playbook (`playbooks/babysit.md`), not Cursor's built-in babysit skill, whose description matches the same words. Never triggered by merely opening a PR. Declare its mode before polling. The playbook's step 1 owns the request-to-mode mapping. Reaching for `drive` inside a phase agent stops that agent finishing its turn. - Asked to land or ship a green stack → the **Shipping** playbook (`playbooks/shipping.md`). Green is not safe. Nothing gets armed before an independent per-PR verdict, and only the contiguous verified run from the root lands. diff --git a/.agents/skills/poteto-mode/playbooks/autopilot-full.md b/.agents/skills/poteto-mode/playbooks/autopilot-full.md index 0688823..9f5aa20 100644 --- a/.agents/skills/poteto-mode/playbooks/autopilot-full.md +++ b/.agents/skills/poteto-mode/playbooks/autopilot-full.md @@ -7,11 +7,11 @@ A verdict covers one patch and green CI covers one head. Step 4 runs a full swar 1. **The operator's gates come first.** The grant covers only the queue's items, so items the operator names as theirs and PRs outside the queue stop at merge-ready. A request to state the plan is not a go. 2. **Spawn one owner per PR, and keep its work where a replacement can find it.** Resolve the forge once for the program. GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). Each owner is a Cursor cloud agent that builds, opens its PR per `playbooks/opening-a-pr.md`, proves the change on the real artifact, babysits to green per `playbooks/babysit.md`, and merges once steps 4 and 5 clear it. - Open the PR early so CI and bots run alongside the work. The code is ready only after the slop-strip (the `deslop` skill from the `cursor-team-kit` plugin (`/deslop`)) and the `/no-comments` pass, so the full swarm runs on finished code. Then rebase onto current trunk and report the code-ready head before self-proof, so verification runs on the base the patch lands on. Report every later head, and merge-ready once self-proof, CI, and babysit are done. Fix rounds stay on that base unless trunk conflicts or breaks CI, because each rebase restarts CI. Run the repo's checks for the touched paths on the committed head before the code-ready push and before a later push that needs a verifier. + Open the PR early so CI and bots run alongside the work. The code is ready only after the slop-strip (the `deslop` skill (`/deslop`)) and the `/no-comments` pass, so the full swarm runs on finished code. Then rebase onto current trunk and report the code-ready head before self-proof, so verification runs on the base the patch lands on. Report every later head, and merge-ready once self-proof, CI, and babysit are done. Fix rounds stay on that base unless trunk conflicts or breaks CI, because each rebase restarts CI. Run the repo's checks for the touched paths on the committed head before the code-ready push and before a later push that needs a verifier. Assume the VM dies. Soon after starting, push and start a decision trail in the root agent's store (path in the system prompt) per the **show-me-your-work** skill, then push after every unit worth keeping. Whoever spawns a subagent records its id, state, and a stuck-after runtime from past runs of its kind in that store, so the root can probe it if the parent dies. Force-push only your own branch, with `--force-with-lease` pinned to the SHA you last pushed or took over, and on any push you did not make, stop and report to the root. 3. **Run owners in parallel off trunk, never stacked,** so each PR lands on its own. -4. **Swarm-verify once.** A full swarm runs once, at the code-ready head. Another full swarm runs only for new behavior, a redesign, or a large new diff. A rebase, a merge-conflict resolution, or a minor fix gets a single verifier at the new head. Fan out independent verifiers at the code-ready SHA per the **swarm** skill. They re-run the gates, prove the load-bearing behavior live on the real surface through its control skill (such as `control-ui` or `control-cli` from `cursor-team-kit`) or a named driver, and audit the diff. The verdict is not clean without the live lane, or before you audit the merge-ready report's receipts, because no lane trusts a claim it has not checked. +4. **Swarm-verify once.** A full swarm runs once, at the code-ready head. Another full swarm runs only for new behavior, a redesign, or a large new diff. A rebase, a merge-conflict resolution, or a minor fix gets a single verifier at the new head. Fan out independent verifiers at the code-ready SHA per the **swarm** skill. They re-run the gates, prove the load-bearing behavior live on the real surface through its control skill (such as `control-ui` or `control-cli`) or a named driver, and audit the diff. The verdict is not clean without the live lane, or before you audit the merge-ready report's receipts, because no lane trusts a claim it has not checked. Send every proven finding, whatever a lane labeled it, to the owner in one fix-forward, with a red test across every site with the same defect. A defect trunk shows without the PR is recorded against trunk and does not gate the PR, but one the PR copies or newly reaches is the PR's own. Never push a fix yourself, because each branch has one writer. Replace a stuck owner instead. 5. **The owner merges only what you verified, tested on the trunk it lands on.** Green CI alone never authorizes a merge. Once the swarm's lanes have started, merge prep rebases onto current trunk, reports the new head, and waits for green CI. diff --git a/.agents/skills/poteto-mode/playbooks/multi-phase-plan.md b/.agents/skills/poteto-mode/playbooks/multi-phase-plan.md index 7042ddf..ed9169e 100644 --- a/.agents/skills/poteto-mode/playbooks/multi-phase-plan.md +++ b/.agents/skills/poteto-mode/playbooks/multi-phase-plan.md @@ -12,7 +12,7 @@ **Verification.** Tests alone are not sufficient verification. A PR is verified only when its unit, live, and perf boxes are all checked (the **prove-it-works** principle skill). That sentence is the verification rule. Every verification block opens with it. The live block is mandatory. Ten lanes at the PR head drive the real surface through its control skill, per the **swarm** skill, on the `swarm workers` model (default `grok-4.7-xhigh-fast`). Each lane is one box with a concrete scenario, the screenshot it saves, and its pass predicate. One lane is the **Regression lane against trunk.** It runs the same load-bearing scenario on trunk and head. If trunk does not have the feature, the lane records that fact and gates the behavior the diff adds plus the end state the user waits for instead of inventing a trunk result. The perf gate is dual-sided. Trunk and head must both produce the named metric. If trunk lacks the feature, also isolate the work the diff adds and set an absolute budget for that work plus the end-to-end state the user waits for. Do not claim a ratio between unlike scenarios. The perf block names the metric, the interleaved probe, the trunk baseline measured first, and the rule with the number that fails. A PR that changes an interaction is review-gated. The operator reviews it in chat with screenshots and a video before merge. A PR that changes no interaction writes `**Review gate.** None. is not review-gated.` and no boxes under it. -**Control skill.** Pick it by surface. Browser, Electron, and web UIs use `control-ui` from `cursor-team-kit`. CLIs and TUIs use `control-cli` from `cursor-team-kit`. Native mobile uses whatever simulator-driving skill the repo has. A PR that touches two surfaces gets lanes on both. A surface with no control skill is a risk in Appendix C, and its live block still names how each lane drives it. +**Control skill.** Pick it by surface. Browser, Electron, and web UIs use `control-ui`. CLIs and TUIs use `control-cli`. Native mobile uses whatever simulator-driving skill the repo has. A PR that touches two surfaces gets lanes on both. A surface with no control skill is a risk in Appendix C, and its live block still names how each lane drives it. ````markdown # plan diff --git a/.agents/skills/poteto-mode/playbooks/opening-a-pr.md b/.agents/skills/poteto-mode/playbooks/opening-a-pr.md index d729a7a..054e050 100644 --- a/.agents/skills/poteto-mode/playbooks/opening-a-pr.md +++ b/.agents/skills/poteto-mode/playbooks/opening-a-pr.md @@ -6,7 +6,7 @@ Invoked at the end of every other playbook. **Commits.** Commit liberally. Rebase into small, ordered commits before opening PRs. Each commit is a future PR: landable, ordered to tell the story. Amend when the fix belongs in a just-made commit. New commit when separable. Commit bodies don't restate the subject. -**PRs.** Run `/deslop` from `cursor-team-kit` over the diff before commit and `/no-comments` before review. Write every PR title, description, and commit body with `/technical-writing` (every layer except Diátaxis, and apply the STE vocabulary rules: one word per action, keep articles, a plain verb over `-ing` where one works), then apply `/unslop`. +**PRs.** Run `/deslop` over the diff before commit and `/no-comments` before review. Write every PR title, description, and commit body with `/technical-writing` (every layer except Diátaxis, and apply the STE vocabulary rules: one word per action, keep articles, a plain verb over `-ing` where one works), then apply `/unslop`. **Titles.** Conventional Commits `type(scope): subject`, no trailing period. Type such as `feat`, `fix`, `docs`, `refactor`, `test`, `chore`, or `perf`. Scope is the area, such as `pstack` or `poteto-mode`. Subject is short, imperative, and names a real symbol when one carries the change, for example `fix(pstack): retarget opening-a-pr babysit trigger`. diff --git a/.agents/skills/poteto-mode/playbooks/orchestrate.md b/.agents/skills/poteto-mode/playbooks/orchestrate.md index 4ccb24d..548fcdb 100644 --- a/.agents/skills/poteto-mode/playbooks/orchestrate.md +++ b/.agents/skills/poteto-mode/playbooks/orchestrate.md @@ -14,7 +14,7 @@ Three rules carry the rest. - **Coordinator (this chat).** Local. Frames, authors briefs, drains the inbox, owns the human report, makes judgment calls. It never authors or edits code. Conflicted merges, chain rebases, and code changes are always tasks. Mechanically landing a verified unit (fast-forward or clean cherry-pick of a worker's commit, then push) is bookkeeping the coordinator may do itself on repos where local git is cheap. Queueing finished work behind an idle stacker is how a deadline harvests nothing. The loop is agentic end to end. Agents are spawned, resumed, and drained only through the Task tool. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section. State reads and writes go through `scripts/orch/orch.ts` at drain points, one command in and one line out. The CLI never spawns, waits, or wakes anything. - **Sub-coordinator.** Always local, durable, one per track, and only when the program exceeds what one coordinator's drains can manage. A track the coordinator can drain itself needs no middle layer. Each nested layer re-pays a full orientation preamble, and a blocking sub-coordinator hides its children while the parent idles. Owns its track's units and boards, authors its workers' briefs, spawns its own workers and verifiers (nesting works to depth 3, and a nested spawn has the full Task schema including `environment`). Rolls up aggregates at wave boundaries. Never forwards raw child reports. Cap in-flight children at what one drain can process, roughly ten, as a rolling window. Never as blocking batches, which cost the slowest child of every batch. -- **Worker / verifier.** Always `environment: "cloud"` unless the task needs this machine: `control-ui` or `control-cli` runtime verification (from `cursor-team-kit`). Reading local transcripts under `agent-transcripts/`. Simulators and local IDE state. Auth that exists only here. Cloud agents cannot read the local store, so their briefs inline what they need or point at repo paths. Prefer fewer, broader workers. One writer per worktree or branch (principle-separate-before-serializing-shared-state). Run a unit's verifier on a different model family from its worker. +- **Worker / verifier.** Always `environment: "cloud"` unless the task needs this machine: `control-ui` or `control-cli` runtime verification. Reading local transcripts under `agent-transcripts/`. Simulators and local IDE state. Auth that exists only here. Cloud agents cannot read the local store, so their briefs inline what they need or point at repo paths. Prefer fewer, broader workers. One writer per worktree or branch (principle-separate-before-serializing-shared-state). Run a unit's verifier on a different model family from its worker. Depth stays at coordinator, track, worker. Author the track decomposition per project (build, landing, and verification are common cuts, not a required shape). Hard-coded swarm trees were tried and parked as too rigid. diff --git a/.agents/skills/poteto-mode/playbooks/shipping.md b/.agents/skills/poteto-mode/playbooks/shipping.md index 0a0c3cf..ccc7dc9 100644 --- a/.agents/skills/poteto-mode/playbooks/shipping.md +++ b/.agents/skills/poteto-mode/playbooks/shipping.md @@ -2,7 +2,7 @@ **You own what lands. Verify each PR independently, land only the verified run from the root, then keep your hands off the stack.** -1. **Resolve the forge, then verify each PR independently before it lands.** GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). One verifier per PR, each a Cursor cloud agent, runs the change the way a user would with the matching control skill (such as `control-ui` or `control-cli` from `cursor-team-kit`), parent against head, and posts `PASS`, `PASS+NOTES`, or `FAIL` on that PR. Only a verdict from an agent that did not write the code counts, because an author checks what it meant to build. Green CI and an approving bot review are not verdicts, because neither runs the change as a user would. +1. **Resolve the forge, then verify each PR independently before it lands.** GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). One verifier per PR, each a Cursor cloud agent, runs the change the way a user would with the matching control skill (such as `control-ui` or `control-cli`), parent against head, and posts `PASS`, `PASS+NOTES`, or `FAIL` on that PR. Only a verdict from an agent that did not write the code counts, because an author checks what it meant to build. Green CI and an approving bot review are not verdicts, because neither runs the change as a user would. 2. **Land only the contiguous verified run rooted at the bottom.** Walk up from the lowest unmerged PR and stop at the first one without `PASS` or `PASS+NOTES`. The PRs below it are the run, and the top one is the ceiling. A verified PR above an unverified one waits, because it cannot land without the code below it. One whose branch neither holds nor needs that code can move onto trunk and land on its own. It needs a fresh verdict first, because its old one ran with that code beneath it and trunk does not have it. 3. **Re-check that the verdicts still describe the code.** A verdict covers a patch, and a chain rebase moves every PR above it to a new SHA without failing any check. Compare `git patch-id` at the verdict SHA with the current head before trusting an older verdict. When the patches differ only in tests, docs, or lint config, a lane's result stands if what it ran builds the same at both SHAs apart from noise. Noise is a difference that also shows up between two builds of the verdict SHA, or an embedded commit SHA. Report each kind of noise with its files, so a reader can check the call. The change itself still gets fresh checks and a review, because the old verdict never saw it. A lane with no build output, such as a dev server, cannot show this, so rerun it, and re-verify anything else that drifted. 4. **Land bottom-up, one PR at a time.** Always merge the run's lowest unmerged PR, with `origin pr merge ` or `gh pr merge --squash`. On Origin the plain command also merges every PR below the one you name, and on GitHub a PR whose base is still its parent's branch merges into that branch, not trunk. Read the PR back for the result (`origin pr view ` or `gh pr view --json state,mergedAt,baseRefName`), because a merge command can report success when a merge queue only queued the PR, and a requested auto-merge is not a merge. A landed PR reads merged with trunk as its base, not its parent's branch. Arm `--auto` (Origin merge-when-ready or GitHub auto-merge) only on a PR whose verdict covers its current head, because it lands whatever head is ready. After a merge lands, retarget the PR whose base was the merged branch to trunk (`origin pr edit --base ` or `gh pr edit --base `), move its patch onto the merge result, and push with `--force-with-lease`. The verdict covers the patch, not its commits, so step 3's patch-id rule decides whether the verdict survives. Merge it once its checks pass and its verdict survives. diff --git a/.agents/skills/poteto-mode/references/codex.md b/.agents/skills/poteto-mode/references/codex.md index fd41d05..45ae122 100644 --- a/.agents/skills/poteto-mode/references/codex.md +++ b/.agents/skills/poteto-mode/references/codex.md @@ -6,7 +6,7 @@ Read this once per session before following any pstack workflow. Apply these map The plugin root contains `.codex-plugin/plugin.json`, `.agents/skills/`, `agents/`, and `docs/`. Resolve sibling skills at `../..//SKILL.md` from this file's directory, or `..//SKILL.md` from a skill directory. Prefer the path in the session's skill catalog. Read a referenced skill and follow it; do not assume a separate skill-invocation tool exists. This package is discovered as `pstack:`: user prompts use `$pstack:poteto-mode`, `$pstack:setup-pstack`, and `$pstack:` in place of upstream `/name` examples. If skills are copied without a package manifest, use the unprefixed names actually shown in the catalog. Match skills by their leaf name when resolving a namespaced catalog entry. -Create project skills only at `.agents/skills//SKILL.md` and personal skills only at `~/.agents/skills//SKILL.md`. Keep one skill per immediate child directory; do not introduce personal category nesting. Explicit-only skills use `policy.allow_implicit_invocation: false` in their `agents/openai.yaml`. Use `skill-creator` when available; otherwise write valid YAML `name` and `description` frontmatter and follow the installed Codex skill guidance. The bundled `deslop`, `control-cli`, and `control-ui` replace the upstream cursor-team-kit dependency. +Create project skills only at `.agents/skills//SKILL.md` and personal skills only at `~/.agents/skills//SKILL.md`. Keep one skill per immediate child directory; do not introduce personal category nesting. Explicit-only skills use `policy.allow_implicit_invocation: false` in their `agents/openai.yaml`. Use `skill-creator` when available; otherwise write valid YAML `name` and `description` frontmatter and follow the installed Codex skill guidance. The bundled `deslop`, `control-cli`, and `control-ui` are part of this plugin. Read bundled guides locally. An upstream URL ending in `pstack/skills/` refers to `/.agents/skills/`; other bundled upstream paths resolve from the plugin root. Do not fetch a file already shipped locally. The role files in `agents/` are prompt briefs, not registered Codex agent types. diff --git a/README.md b/README.md index c33999a..c68dd42 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # pstack for Codex -Codex port of [pstack](https://github.com/cursor/plugins/tree/99b609a72323b70204eab407c622f436e858e112/pstack) `0.15.32` by Lauren Tan, following [agy-pstack](https://github.com/pstack-ports/agy-pstack). Bundles `deslop`, `control-cli`, and `control-ui` from cursor-team-kit. See [UPSTREAM.md](./UPSTREAM.md) for the source pin and port scope. +Codex port of [pstack](https://github.com/cursor/plugins/tree/99b609a72323b70204eab407c622f436e858e112/pstack) `0.15.32` by Lauren Tan, following [agy-pstack](https://github.com/pstack-ports/agy-pstack). Bundles `deslop`, `control-cli`, and `control-ui`. See [UPSTREAM.md](./UPSTREAM.md) for the source pin and port scope. Skills live only in `.agents/skills/`. The [Codex adapter](./docs/harness/codex.md) maps preserved upstream tool names to the current session and is loaded by every skill. The original author's introduction follows. @@ -258,7 +258,7 @@ twenty-four short skills, one principle each. `poteto-mode` indexes them inline ## bundled dependencies -This port includes `deslop`, `control-cli`, and `control-ui` under `.agents/skills/`; no cursor-team-kit installation is needed. Skill authoring uses `skill-creator` when available, otherwise the adapter's Codex format guidance. PR-status work uses pstack's own Babysit playbook. +This port includes `deslop`, `control-cli`, and `control-ui` under `.agents/skills/`. Skill authoring uses `skill-creator` when available, otherwise the adapter's Codex format guidance. PR-status work uses pstack's own Babysit playbook. ## why are there no planning skills? diff --git a/UPSTREAM.md b/UPSTREAM.md index 787a006..85d87b6 100644 --- a/UPSTREAM.md +++ b/UPSTREAM.md @@ -3,7 +3,7 @@ Imported unchanged before the Codex port: - `pstack/` from [`cursor/plugins` at `99b609a72323b70204eab407c622f436e858e112`](https://github.com/cursor/plugins/tree/99b609a72323b70204eab407c622f436e858e112/pstack), version `0.15.32`, by Lauren Tan. -- `cursor-team-kit/skills/{deslop,control-cli,control-ui}` from the same commit, by Eric Zakariasson, following the [agy-pstack example](https://github.com/pstack-ports/agy-pstack). +- `deslop`, `control-cli`, and `control-ui` skills from cursor/plugins at the same commit, by Eric Zakariasson, following the [agy-pstack example](https://github.com/pstack-ports/agy-pstack). The first Git commit is the imported source snapshot. The Codex port follows in a separate commit for review. The original MIT license and assets are retained. diff --git a/docs/guide/05-build-and-clean.md b/docs/guide/05-build-and-clean.md index a5de632..997d68e 100644 --- a/docs/guide/05-build-and-clean.md +++ b/docs/guide/05-build-and-clean.md @@ -56,7 +56,7 @@ In context, that's enough. [`/tdd`](../../.agents/skills/tdd/SKILL.md) writes th ## Clean before you commit -The [Opening a PR playbook](../../.agents/skills/poteto-mode/playbooks/opening-a-pr.md) runs `/deslop` on the diff before each commit and applies [`/unslop`](../../.agents/skills/unslop/SKILL.md) to the PR description and commit bodies. `/deslop` ships in the `cursor-team-kit` plugin, not in pstack. If you don't have it, ask for the same outcome in plain words: remove narrating comments, unsupported guards, dead compatibility paths, and unrelated edits. +The [Opening a PR playbook](../../.agents/skills/poteto-mode/playbooks/opening-a-pr.md) runs `/deslop` on the diff before each commit and applies [`/unslop`](../../.agents/skills/unslop/SKILL.md) to the PR description and commit bodies. `/deslop` ships in this plugin. If you don't have it, ask for the same outcome in plain words: remove narrating comments, unsupported guards, dead compatibility paths, and unrelated edits. For prose, `/unslop` takes a target and any extra rules you have: