[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD55978EY23TE91WMB5N60":3,"skill-same:01M7FD55978EY23TE91WMB5N60":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":44},"01M7FD55978EY23TE91WMB5N60","pstack-pi",null,"Maps the Cursor names in pstack skills to Pi tools, child Pi processes, models, and paths. pstack skills read it once per session; poteto-mode embeds it.","mr-jones123\u002Fpstack-harness","mr-jones123","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F104372691?v=4","01M7FCRJB8YVBWJJ1BQXH89H0R","Xynil Jhed Lacap","01M7FCRJBVNEVCP78T6XKNR907",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fsrc\u002Fpi\u002Fskills\u002Fpstack-pi\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: pstack-pi\ndescription: Maps the Cursor names in pstack skills to Pi tools, child Pi processes, models, and paths. pstack skills read it once per session; poteto-mode embeds it.\ndisable-model-invocation: true\n---\n\n# pstack in Pi\n\npstack skills use Cursor names. In Pi, read this once per session, then map each Cursor name in a pstack skill with the tables below. When this text arrives embedded in `poteto-mode`, it is already read. Do not read it again. `\u003Cpstack>` means the package folder that holds `skills\u002F`, `agents\u002F`, and `docs\u002F`, two levels up from the skill file you are reading. Resolve it to an absolute path once, because child Pi briefs need absolute paths. If a Cursor field has no row, drop it and say so. Never pass a flag or field that Pi rejects.\n\n## Tools\n\n| Cursor | Pi |\n| --- | --- |\n| `Task` | A child Pi process started with `bash`. See Subagents. If the session has a `subagent` tool from an extension, you may use it instead with one of the agents it lists, and the brief tells the child to read the matching `\u003Cpstack>\u002Fagents\u002F\u003Cagent>.md` first. |\n| `AskQuestion` | A question tool if the session has one. Otherwise ask in plain text and end your turn to wait for the answer. |\n| Open a todolist | A todo tool if the session has one. Otherwise keep the list in your reply and update it at each phase. |\n| Run another pstack skill (`\u002Fname` or \"the **name** skill\") | Read `\u003Cpstack>\u002Fskills\u002F\u003Cname>\u002FSKILL.md` and follow it, unless its body is already in context from `\u002Fskill:\u003Cname>` or an earlier read. When you tell the user to type it, write `\u002Fskill:\u003Cname>`. |\n| `Read`, `Write`, `StrReplace`, `Shell`, `Grep`, `Glob` | `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`. When `grep` or `find` is not enabled, use `bash` with `rg`. |\n| `WebFetch`, `WebSearch` | A web tool if the session has one. Otherwise `bash` with `curl` for a known URL, and say that search is unavailable. |\n\n## Subagents\n\nRun each subagent as its own child Pi. Write the brief to a file, then start the child with the agent's prompt file appended to its system prompt:\n\n```bash\npi -p --no-session --model \"\u003Cmodel>\" --append-system-prompt \"\u003Cpstack>\u002Fagents\u002F\u003Cagent>.md\" @\"\u003Cdir>\u002F\u003Cname>.brief.md\" \"Follow the attached brief.\" > \"\u003Cdir>\u002F\u003Cname>.out.md\" 2>&1\n```\n\n- `\u003Cagent>` is `poteto-agent`, `comment-sicko`, or `pstack-worker`. See Subagent fields.\n- `\u003Cmodel>` comes from Models. Drop `--model` to run the child on Pi's default model.\n- The child sees none of this conversation. The brief carries the goal, the absolute paths it needs, the absolute path of this adapter (`\u003Cpstack>\u002Fskills\u002Fpstack-pi\u002FSKILL.md`), and the report you expect back.\n- For parallel work, start each child with a trailing `&` in one `bash` call, then `wait`. Give that call a timeout long enough for the slowest child, or none. Read each `.out.md` when the call returns.\n- You own every child's work. Review its diff and output yourself.\n- Children run in `-p` mode, which skips untrusted project-local packages. Install pstack user-wide (`pi install` without `-l`) so children load its skills in every project.\n\n| Cursor | Pi |\n| --- | --- |\n| `subagent_type: generalPurpose` | `pstack-worker`. |\n| `poteto-agent` | `poteto-agent`. The brief names the absolute path of `\u003Cpstack>\u002Fskills\u002Fpoteto-mode\u002FSKILL.md`. |\n| `comment-sicko` | `comment-sicko`. |\n| `readonly: true` | Add `--exclude-tools write,edit` to the child, and the brief says \"do not edit files\". The child keeps `bash` for `git log` and `git blame`, so this is an instruction, not a sandbox. Check `git status` afterward. `readonly: false` needs nothing. |\n| `environment: \"cloud\"` | Create a worktree with `git worktree add`, then start the child inside it (`cd \u003Cworktree> && pi -p ...`). Name the base commit in the brief. Never run two writers in one checkout. A worktree is not a VM and shares your credentials. |\n| `environment: \"local\"` | Omit. |\n| `cloud_base_branch: \u003Cb>` | Base the worktree on `\u003Cb>`. |\n| `run_in_background: true` | Start the child with a trailing `&`, as above. |\n| `resume` | Start a fresh child and paste the earlier result into its brief. |\n| `file_attachments` | Add each file as another `@\u003Cpath>` argument, or list absolute paths in the brief. |\n\n## Models\n\n| Cursor | Pi |\n| --- | --- |\n| The `pstack-models.mdc` rule, `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` | `~\u002F.pi\u002Fagent\u002Fpstack-models.md`. Read it when it exists. Each role line's value is a Pi model pattern, such as `anthropic\u002Fclaude-opus-5-5:xhigh`, a list of them for a panel, or `inherit-parent`. |\n| `claude-\u003Cfamily>-\u003Cversion>-\u003Ceffort>[-fast]`, such as `claude-opus-5-5-xhigh` | The role's line in `pstack-models.md`. Without the file or the line, drop `--model` and say so. |\n| A `grok-*`, `gpt-*`, or other non-Claude slug | The role's line in `pstack-models.md`. Without the file or the line, drop `--model` and say so. |\n| `auto` or `inherit-parent` | Drop `--model`. |\n| An effort suffix (`-xhigh`, `-high`) or `-fast` | The pattern's `:\u003Cthinking>` suffix: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max`. Drop `-fast`. |\n| A two-family panel (arena, architect, interrogate) | One child per panel entry. Children without `--model` all run on one model, which is not multi-model evidence. Say so. |\n\n## setup-pstack\n\nFollow its steps with these changes.\n\n- Detect. `pi --list-models` lists each `provider` and `model` you can use, and whether it supports thinking. A pattern is `\u003Cprovider>\u002F\u003Cmodel>`, with a `:\u003Cthinking>` suffix only for a model that supports thinking.\n- Defaults. Map `claude-opus-5-5-xhigh` to the detected Anthropic Opus model. Map `grok-4.7-xhigh-fast` to a detected xAI Grok model, else mark the role as needing a choice.\n- Budget. The budget sets the `:\u003Cthinking>` suffix of every pattern (`:max`, `:xhigh`, `:high`, or `:medium`). Replace the whole suffix. Never edit tokens inside the model name. A model without thinking gets no suffix.\n- Validate. Each pattern without its suffix equals a detected `\u003Cprovider>\u002F\u003Cmodel>`. `inherit-parent` and `auto` always pass.\n- Write. Write `~\u002F.pi\u002Fagent\u002Fpstack-models.md` with no frontmatter: the comment lines, the `# budget` line, and one line per role from step 5 with a Pi pattern or `inherit-parent`. Overwrite the whole file. Never put role lines in `AGENTS.md`.\n\n## Paths\n\n| Cursor | Pi |\n| --- | --- |\n| `.cursor\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F` | `.pi\u002Fskills\u002F`, `~\u002F.pi\u002Fagent\u002Fskills\u002F`. Pi also reads `.agents\u002Fskills\u002F` and `~\u002F.agents\u002Fskills\u002F`. |\n| `~\u002F.cursor\u002Fplugins\u002F`, `.cursor-plugin\u002Fplugin.json` | `\u003Cpstack>`. `\u003Cpstack>\u002F..\u002Fpackage.json` holds the version. |\n| `.cursor\u002Frules\u002F*.mdc`, always-applied rules | `AGENTS.md` in the project or a parent folder. User-wide rules live in `~\u002F.pi\u002Fagent\u002FAGENTS.md`. Pi never reads `.mdc` files. The model rule is the exception. See Models. |\n| `https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins\u002Fblob\u002Fmain\u002Fpstack\u002F\u003Cpath>` | `\u003Cpstack>\u002F\u003Cpath>` when that file exists. The package ships the skills and `docs\u002Fguide\u002F`. Read the local copy and never fetch it. Give the user the URL when they need a link. |\n| Transcripts in `~\u002F.cursor\u002Fprojects\u002F\u003Cslug>\u002Fagent-transcripts\u002F` | Pi sessions in `~\u002F.pi\u002Fagent\u002Fsessions\u002F\u003Cfolder>\u002F\u003Ctimestamp>_\u003Cid>.jsonl`. Pick the folder whose session files have a header line (`\"type\":\"session\"`) with `cwd` equal to the workspace. The newest file is the current session. Children started with `--no-session` leave no transcript, so keep their `.out.md` files. Read only this workspace's sessions. |\n\n## Cursor-only features\n\nPi has no Cursor Automations, Bugbot, Cursor cloud agents, persistent `\u002Floop` wakes, custom mode, or built-in PR tool. When a step needs one, put one line in your reply, `Skipped in Pi: \u003Cstep>. \u003Creason>.`, then go on to the next step. Do not stop, ask, or retry. When a later step needs what the skipped step made, such as a URL or a key, leave a placeholder and name it in the line.\n\n| Cursor | Pi |\n| --- | --- |\n| Cursor Automations: routines, `update_state` routine calls, `api2.cursor.sh\u002Fautomations` webhooks, routine wakes, and `SendToUser` secret requests | Skip with the line. |\n| Bugbot | Bugbot comments on a GitHub PR are ordinary review threads, so triage them with the forge command the step gives. Skip a step that starts, waits for, or configures Bugbot when the PR has no Bugbot check or comment. |\n| Cursor cloud agents | `environment: \"cloud\"` maps as in Subagent fields. Skip a step that needs the cloud agent itself, such as its dashboard. |\n| A built-in PR tool | Use the forge command the step gives, such as `gh pr create`. That is not a skip, so write no line. |\n| `\u002Floop` | Keep working in this session until the predicate holds. Pi has no wake scheduler that outlives the session, so say so when the task needs one. |\n| A custom mode that stays on across turns | Skip with the line. The user re-invokes `\u002Fskill:poteto-mode` when they want the mode again. |\n| `\u002Fvisualize` | Draw the diagram as a Mermaid block in the reply. |\n| Cursor's built-in `create-skill` | The bundled `create-skill` skill. |\n\n## Helper limits\n\n`poteto-mode\u002Fscripts\u002Fworktree-audit.sh` decides liveness from Cursor transcripts, so this package's copy exits 2 before it audits anything. Use `git worktree list`, then check each checkout's status, its unpushed commits, and which Pi session owns it. Unknown liveness means keep the checkout. Other helpers keep their own protocols, such as internal `gh --json` calls. Read a helper before you run it.\n","# pstack in Pi\n\npstack skills use Cursor names. In Pi, read this once per session, then map each Cursor name in a pstack skill with the tables below. When this text arrives embedded in `poteto-mode`, it is already read. Do not read it again. `\u003Cpstack>` means the package folder that holds `skills\u002F`, `agents\u002F`, and `docs\u002F`, two levels up from the skill file you are reading. Resolve it to an absolute path once, because child Pi briefs need absolute paths. If a Cursor field has no row, drop it and say so. Never pass a flag or field that Pi rejects.\n\n## Tools\n\n| Cursor | Pi |\n| --- | --- |\n| `Task` | A child Pi process started with `bash`. See Subagents. If the session has a `subagent` tool from an extension, you may use it instead with one of the agents it lists, and the brief tells the child to read the matching `\u003Cpstack>\u002Fagents\u002F\u003Cagent>.md` first. |\n| `AskQuestion` | A question tool if the session has one. Otherwise ask in plain text and end your turn to wait for the answer. |\n| Open a todolist | A todo tool if the session has one. Otherwise keep the list in your reply and update it at each phase. |\n| Run another pstack skill (`\u002Fname` or \"the **name** skill\") | Read `\u003Cpstack>\u002Fskills\u002F\u003Cname>\u002FSKILL.md` and follow it, unless its body is already in context from `\u002Fskill:\u003Cname>` or an earlier read. When you tell the user to type it, write `\u002Fskill:\u003Cname>`. |\n| `Read`, `Write`, `StrReplace`, `Shell`, `Grep`, `Glob` | `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`. When `grep` or `find` is not enabled, use `bash` with `rg`. |\n| `WebFetch`, `WebSearch` | A web tool if the session has one. Otherwise `bash` with `curl` for a known URL, and say that search is unavailable. |\n\n## Subagents\n\nRun each subagent as its own child Pi. Write the brief to a file, then start the child with the agent's prompt file appended to its system prompt:\n\n```bash\npi -p --no-session --model \"\u003Cmodel>\" --append-system-prompt \"\u003Cpstack>\u002Fagents\u002F\u003Cagent>.md\" @\"\u003Cdir>\u002F\u003Cname>.brief.md\" \"Follow the attached brief.\" > \"\u003Cdir>\u002F\u003Cname>.out.md\" 2>&1\n```\n\n- `\u003Cagent>` is `poteto-agent`, `comment-sicko`, or `pstack-worker`. See Subagent fields.\n- `\u003Cmodel>` comes from Models. Drop `--model` to run the child on Pi's default model.\n- The child sees none of this conversation. The brief carries the goal, the absolute paths it needs, the absolute path of this adapter (`\u003Cpstack>\u002Fskills\u002Fpstack-pi\u002FSKILL.md`), and the report you expect back.\n- For parallel work, start each child with a trailing `&` in one `bash` call, then `wait`. Give that call a timeout long enough for the slowest child, or none. Read each `.out.md` when the call returns.\n- You own every child's work. Review its diff and output yourself.\n- Children run in `-p` mode, which skips untrusted project-local packages. Install pstack user-wide (`pi install` without `-l`) so children load its skills in every project.\n\n| Cursor | Pi |\n| --- | --- |\n| `subagent_type: generalPurpose` | `pstack-worker`. |\n| `poteto-agent` | `poteto-agent`. The brief names the absolute path of `\u003Cpstack>\u002Fskills\u002Fpoteto-mode\u002FSKILL.md`. |\n| `comment-sicko` | `comment-sicko`. |\n| `readonly: true` | Add `--exclude-tools write,edit` to the child, and the brief says \"do not edit files\". The child keeps `bash` for `git log` and `git blame`, so this is an instruction, not a sandbox. Check `git status` afterward. `readonly: false` needs nothing. |\n| `environment: \"cloud\"` | Create a worktree with `git worktree add`, then start the child inside it (`cd \u003Cworktree> && pi -p ...`). Name the base commit in the brief. Never run two writers in one checkout. A worktree is not a VM and shares your credentials. |\n| `environment: \"local\"` | Omit. |\n| `cloud_base_branch: \u003Cb>` | Base the worktree on `\u003Cb>`. |\n| `run_in_background: true` | Start the child with a trailing `&`, as above. |\n| `resume` | Start a fresh child and paste the earlier result into its brief. |\n| `file_attachments` | Add each file as another `@\u003Cpath>` argument, or list absolute paths in the brief. |\n\n## Models\n\n| Cursor | Pi |\n| --- | --- |\n| The `pstack-models.mdc` rule, `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` | `~\u002F.pi\u002Fagent\u002Fpstack-models.md`. Read it when it exists. Each role line's value is a Pi model pattern, such as `anthropic\u002Fclaude-opus-5-5:xhigh`, a list of them for a panel, or `inherit-parent`. |\n| `claude-\u003Cfamily>-\u003Cversion>-\u003Ceffort>[-fast]`, such as `claude-opus-5-5-xhigh` | The role's line in `pstack-models.md`. Without the file or the line, drop `--model` and say so. |\n| A `grok-*`, `gpt-*`, or other non-Claude slug | The role's line in `pstack-models.md`. Without the file or the line, drop `--model` and say so. |\n| `auto` or `inherit-parent` | Drop `--model`. |\n| An effort suffix (`-xhigh`, `-high`) or `-fast` | The pattern's `:\u003Cthinking>` suffix: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max`. Drop `-fast`. |\n| A two-family panel (arena, architect, interrogate) | One child per panel entry. Children without `--model` all run on one model, which is not multi-model evidence. Say so. |\n\n## setup-pstack\n\nFollow its steps with these changes.\n\n- Detect. `pi --list-models` lists each `provider` and `model` you can use, and whether it supports thinking. A pattern is `\u003Cprovider>\u002F\u003Cmodel>`, with a `:\u003Cthinking>` suffix only for a model that supports thinking.\n- Defaults. Map `claude-opus-5-5-xhigh` to the detected Anthropic Opus model. Map `grok-4.7-xhigh-fast` to a detected xAI Grok model, else mark the role as needing a choice.\n- Budget. The budget sets the `:\u003Cthinking>` suffix of every pattern (`:max`, `:xhigh`, `:high`, or `:medium`). Replace the whole suffix. Never edit tokens inside the model name. A model without thinking gets no suffix.\n- Validate. Each pattern without its suffix equals a detected `\u003Cprovider>\u002F\u003Cmodel>`. `inherit-parent` and `auto` always pass.\n- Write. Write `~\u002F.pi\u002Fagent\u002Fpstack-models.md` with no frontmatter: the comment lines, the `# budget` line, and one line per role from step 5 with a Pi pattern or `inherit-parent`. Overwrite the whole file. Never put role lines in `AGENTS.md`.\n\n## Paths\n\n| Cursor | Pi |\n| --- | --- |\n| `.cursor\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F` | `.pi\u002Fskills\u002F`, `~\u002F.pi\u002Fagent\u002Fskills\u002F`. Pi also reads `.agents\u002Fskills\u002F` and `~\u002F.agents\u002Fskills\u002F`. |\n| `~\u002F.cursor\u002Fplugins\u002F`, `.cursor-plugin\u002Fplugin.json` | `\u003Cpstack>`. `\u003Cpstack>\u002F..\u002Fpackage.json` holds the version. |\n| `.cursor\u002Frules\u002F*.mdc`, always-applied rules | `AGENTS.md` in the project or a parent folder. User-wide rules live in `~\u002F.pi\u002Fagent\u002FAGENTS.md`. Pi never reads `.mdc` files. The model rule is the exception. See Models. |\n| `https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins\u002Fblob\u002Fmain\u002Fpstack\u002F\u003Cpath>` | `\u003Cpstack>\u002F\u003Cpath>` when that file exists. The package ships the skills and `docs\u002Fguide\u002F`. Read the local copy and never fetch it. Give the user the URL when they need a link. |\n| Transcripts in `~\u002F.cursor\u002Fprojects\u002F\u003Cslug>\u002Fagent-transcripts\u002F` | Pi sessions in `~\u002F.pi\u002Fagent\u002Fsessions\u002F\u003Cfolder>\u002F\u003Ctimestamp>_\u003Cid>.jsonl`. Pick the folder whose session files have a header line (`\"type\":\"session\"`) with `cwd` equal to the workspace. The newest file is the current session. Children started with `--no-session` leave no transcript, so keep their `.out.md` files. Read only this workspace's sessions. |\n\n## Cursor-only features\n\nPi has no Cursor Automations, Bugbot, Cursor cloud agents, persistent `\u002Floop` wakes, custom mode, or built-in PR tool. When a step needs one, put one line in your reply, `Skipped in Pi: \u003Cstep>. \u003Creason>.`, then go on to the next step. Do not stop, ask, or retry. When a later step needs what the skipped step made, such as a URL or a key, leave a placeholder and name it in the line.\n\n| Cursor | Pi |\n| --- | --- |\n| Cursor Automations: routines, `update_state` routine calls, `api2.cursor.sh\u002Fautomations` webhooks, routine wakes, and `SendToUser` secret requests | Skip with the line. |\n| Bugbot | Bugbot comments on a GitHub PR are ordinary review threads, so triage them with the forge command the step gives. Skip a step that starts, waits for, or configures Bugbot when the PR has no Bugbot check or comment. |\n| Cursor cloud agents | `environment: \"cloud\"` maps as in Subagent fields. Skip a step that needs the cloud agent itself, such as its dashboard. |\n| A built-in PR tool | Use the forge command the step gives, such as `gh pr create`. That is not a skip, so write no line. |\n| `\u002Floop` | Keep working in this session until the predicate holds. Pi has no wake scheduler that outlives the session, so say so when the task needs one. |\n| A custom mode that stays on across turns | Skip with the line. The user re-invokes `\u002Fskill:poteto-mode` when they want the mode again. |\n| `\u002Fvisualize` | Draw the diagram as a Mermaid block in the reply. |\n| Cursor's built-in `create-skill` | The bundled `create-skill` skill. |\n\n## Helper limits\n\n`poteto-mode\u002Fscripts\u002Fworktree-audit.sh` decides liveness from Cursor transcripts, so this package's copy exits 2 before it audits anything. Use `git worktree list`, then check each checkout's status, its unpushed commits, and which Pi session owns it. Unknown liveness means keep the checkout. Other helpers keep their own protocols, such as internal `gh --json` calls. Read a helper before you run it.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","0826529c4391fc70aa5202aaf46321b52dd5fb0b","src\u002Fpi\u002Fskills\u002Fpstack-pi","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness","https:\u002F\u002Fgithub.com\u002Fmr-jones123","I make cool stuff.","2026-10-28 19:24:06",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add mr-jones123\u002Fpstack-harness --skill pstack-pi",{"tool":38,"command":39},"bunx","bunx skills add mr-jones123\u002Fpstack-harness --skill pstack-pi",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mr-jones123\u002Fpstack-harness --skill pstack-pi","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fsrc\u002Fpi\u002Fskills\u002Fpstack-pi\u002FSKILL.md",[],[46,53,60,66,73,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7FD534A9NNSPEF63NHQXKN9","create-skill","Author or revise an Agent Skills SKILL.md for Pi. Stands in for Cursor's built-in create-skill, which pstack skills name. Use when writing or editing a skill.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fsrc\u002Fpi\u002Fskills\u002Fcreate-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FD511C7R39T8T427JQ45FQ","pstack-omp","Maps the Cursor names in pstack skills to OMP tools, agents, models, and paths. pstack skills read it once per session; poteto-mode embeds it.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fsrc\u002Fomp\u002Fskills\u002Fpstack-omp\u002FSKILL.md",[],[],{"skillNo":61,"name":48,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FD4YWGMPSRSNREJJ19QBCK","Author or revise an Agent Skills SKILL.md for OMP. Stands in for Cursor's built-in create-skill, which pstack skills name. Use when writing or editing a skill.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fsrc\u002Fomp\u002Fskills\u002Fcreate-skill\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FD4T3R0XMZ7XYE96K36T9C","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7FD4P0A76YMSPZPKJY6VJKE","verify-this","Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fskills\u002Fverify-this\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7FD4MQ64AFQTCVJSAJ066C0","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fmr-jones123\u002Fpstack-harness\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[]]