[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F0R7V80H7FD64A5YHS4VM8":3,"skill-same:01M7F0R7V80H7FD64A5YHS4VM8":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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7F0R7V80H7FD64A5YHS4VM8","setup-pstack",null,"Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-loaded block in ~\u002F.codex\u002FAGENTS.md that overrides the skill defaults. Use for $pstack:setup-pstack, \"configure pstack models\", \"pstack budget\", or changing pstack's model choices.","irfanalimd\u002Fpstack-ports","irfanalimd","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55896554?v=4","01M7F0CXJRB2KHNDXGYJDG9R65","Mohammed Irfan Ali","01M7F0CXKNYHJDNQ8RREHX0ZG0",0,"MIT","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fcodex\u002Fpstack\u002Fskills\u002Fsetup-pstack\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: setup-pstack\ndescription: Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-loaded block in ~\u002F.codex\u002FAGENTS.md that overrides the skill defaults. Use for $pstack:setup-pstack, \"configure pstack models\", \"pstack budget\", or changing pstack's model choices.\n---\n\n# Setup pstack\n\nWrite the `pstack-models` block in `~\u002F.codex\u002FAGENTS.md`, an always-loaded block that sets pstack's model per role.\n\n## Steps\n\n### 1. Detect available models\n\nRun `codex debug models` and keep every entry whose `visibility` is `list`. Each supported effort in its `supported_reasoning_levels` makes one detected slug, `\u003Cslug>-\u003Ceffort>`. That is the dependable source.\n\n```bash\ncodex debug models | python3 -c 'import json,sys\nfor m in json.load(sys.stdin)[\"models\"]:\n    if m.get(\"visibility\") == \"list\":\n        for l in m[\"supported_reasoning_levels\"]: print(m[\"slug\"] + \"-\" + l[\"effort\"])'\n```\n\nIf `command -v claude` succeeds, also detect the cross-vendor entries `claude:\u003Calias>-\u003Ceffort>` for the aliases `opus`, `sonnet`, `haiku`, and `fable` and the efforts `low`, `medium`, `high`, `xhigh`, and `max`. They run through the local `claude` CLI and are valid in any role. Confirm each chosen `claude:` entry once with a one-turn probe, `claude -p --model \u003Calias> --effort \u003Ceffort> \"reply OK\"`, because `command -v claude` does not show which efforts a model supports. If the probe fails, drop the entry. If you cannot detect any, ask the user to paste the slugs they have access to. Never write a real slug you have not confirmed is available. The aliases `inherit-parent` and `auto` are always valid even though they are not detected slugs.\n\n### 2. Load current state\n\nThe default role-to-model mapping is the block shape shown in step 5 below. If `~\u002F.codex\u002FAGENTS.md` (or `AGENTS.override.md` in the same directory, when it exists) already holds the `pstack-models` block, read it and treat its `# budget` line and its role values as the current choices. Otherwise start from those defaults. A line whose role is not in step 5, such as `how critics`, is from a retired role. Drop it.\n\n### 3. Budget, map, and confirm\n\n**(a) Ask for a budget.** Prefer `request_user_input` over free text. Use it when your tool list has it, else ask in plain text with the same labels. Offer these four options with these exact labels, and name the current budget when the block records one. With no block, say that `large` matches the skill defaults.\n\n- `unlimited — max reasoning`\n- `large — xhigh reasoning`\n- `medium — high reasoning`\n- `small — medium reasoning`\n\n**(b) Apply it.** Build the working table from the skill defaults, and on a re-run keep any role you changed by family, list, or alias (`inherit-parent`, `auto`). `unlimited`, `large`, `medium`, and `small` set the effort token of every real slug, panel entries included, to `max`, `xhigh`, `high`, or `medium`. The effort token is the last `-` token, on the ladder `max` > `xhigh` > `high` > `medium` > `low`. If the result is not a detected slug, use the same family's detected slug with the highest effort at or below the target, else mark the role as needing a choice. `inherit-parent` and `auto` do not change. So `unlimited` turns `gpt-6-astra-xhigh` into `gpt-6-astra-max`. Codex also offers `ultra` above `max` on `gpt-6-astra` and the `sol` models, but no budget sets it, so `unlimited` stays `max` and `ultra` is an opt-in per role in step (c). `large` keeps both defaults. `small` turns them into `gpt-6-astra-medium` and `gpt-6.1-sol-medium`. A `claude:` entry follows the same ladder.\n\n**(c) Show the roles and confirm.** Show every role with its model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped. Ask whether to accept as-is or change specific roles, offering the detected models plus `inherit-parent` and `auto` (both mean: this role runs on the parent chat model, whatever model the thread runs on) as the options. Offer `ultra` as an opt-in for any role on a model that lists it. Prefer `request_user_input` over free text, as in (a). For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. A detected `claude:` entry can join a panel list, `arena cross-judge pool` included, and gives that panel a second vendor. Without the `claude` CLI every default panel is two OpenAI models, so say so when the user cares about model diversity. `arena cross-judge pool` is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. `swarm workers` is the default model for every worker unless a race or comparison assigns another model per arm.\n\n### 4. Validate\n\nEvery real slug written must be in the detected set. `inherit-parent` and `auto` always pass. A `claude:` entry passes only when its probe from step 1 succeeded. If a chosen real slug is not available, stop and ask again.\n\n### 5. Write the block\n\nWrite the block between `\u003C!-- pstack-models:begin -->` and `\u003C!-- pstack-models:end -->` in `~\u002F.codex\u002FAGENTS.md`, with a `# budget` line with the chosen label and its target effort, and one line per role, using the same labels poteto-mode uses. Codex loads `~\u002F.codex\u002FAGENTS.md` into every new thread, so the block applies everywhere. Replace the text between the markers when they exist, append the block when they don't, create the file when it is missing, and never touch anything outside the markers, so re-runs stay idempotent. Shape:\n\n```\n\u003C!-- pstack-models:begin -->\n# pstack model configuration. One line per role. Delete a line to fall back to the skill default.\n# `inherit-parent` or `auto` as a value: the role runs on the parent chat model (omit `model` and `reasoning_effort`). Alias entries in a panel list still count toward its fan-out.\n# budget: large (xhigh)\nfeature, refactoring: gpt-6.1-sol-xhigh\nbug-fix: gpt-6.1-sol-xhigh\nperf-issue: gpt-6.1-sol-xhigh\nhillclimb: gpt-6.1-sol-xhigh\njudgment and prose: gpt-6-astra-xhigh\nhardest tasks: gpt-6-astra-xhigh\nhow explorer: gpt-6.1-sol-xhigh\nhow explainer: gpt-6-astra-xhigh\nwhy investigators: gpt-6.1-sol-xhigh\nwhy synthesizer: gpt-6-astra-xhigh\nreflect tooling: gpt-6.1-sol-xhigh\nreflect judgment, divergent, synthesizer: gpt-6-astra-xhigh\narena runners: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\narena cross-judge pool: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\nswarm workers: gpt-6.1-sol-xhigh\narchitect runners: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\ninterrogate reviewers: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\n\u003C!-- pstack-models:end -->\n```\n\nWith the block saved to a file, this replaces or appends it in place. It exits with a message unless the block file starts with the begin marker and ends with the end marker, and unless the target has at most one begin marker with its end marker after it. Markers match only at line start. If `AGENTS.override.md` exists in the Codex home, Codex loads it instead of `AGENTS.md`, so the updater tells the user and writes the block there. The write is atomic.\n\n```bash\npython3 - \"${CODEX_HOME:-$HOME\u002F.codex}\" \u003Cblock-file> \u003C\u003C'PY'\nimport os, re, sys, tempfile\nBEGIN, END = \"\u003C!-- pstack-models:begin -->\", \"\u003C!-- pstack-models:end -->\"\nhome, block = sys.argv[1], open(sys.argv[2]).read().strip() + \"\\n\"\nif not (block.startswith(BEGIN) and block.rstrip(\"\\n\").endswith(END)):\n    sys.exit(\"The block file must start with the begin marker and end with the end marker.\")\npath = os.path.join(home, \"AGENTS.md\")\noverride = os.path.join(home, \"AGENTS.override.md\")\nif os.path.exists(override):\n    print(\"Codex loads \" + override + \" instead of AGENTS.md, so the block goes there.\")\n    path = override\ntext = open(path).read() if os.path.exists(path) else \"\"\nbegins = list(re.finditer(\"^\" + re.escape(BEGIN) + r\"[ \\t]*$\", text, re.M))\nends = list(re.finditer(\"^\" + re.escape(END) + r\"[ \\t]*$\\n?\", text, re.M))\nif len(begins) > 1:\n    sys.exit(\"The file has more than one begin marker. Fix it by hand, then rerun.\")\nif ends and not begins:\n    sys.exit(\"The file has an end marker without a begin marker. Fix it by hand, then rerun.\")\nif begins:\n    after = [e for e in ends if e.start() > begins[0].start()]\n    if not after or len(ends) > 1:\n        sys.exit(\"The begin marker needs exactly one matching end marker after it. Fix it by hand, then rerun.\")\n    text = text[:begins[0].start()] + block + text[after[0].end():]\nelse:\n    text = text.rstrip(\"\\n\") + \"\\n\\n\" + block if text.strip() else block\nos.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)\nfd, tmp = tempfile.mkstemp(dir=os.path.dirname(os.path.abspath(path)), prefix=\".pstack-\")\nwith os.fdopen(fd, \"w\") as f:\n    f.write(text)\n    f.flush()\n    os.fsync(f.fileno())\nif os.path.exists(path):\n    os.chmod(tmp, os.stat(path).st_mode & 0o7777)\nos.replace(tmp, path)\nPY\n```\n\n\nThen install pstack's agent roles. Codex plugins cannot register roles, so copy them from this plugin with `mkdir -p \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fagents\" && cp ..\u002F..\u002Fagents\u002Fpoteto-agent.toml ..\u002F..\u002Fagents\u002Fcomment-sicko.toml \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fagents\u002F\"`, with both source paths resolved from this file's directory. This overwrites only pstack's own two role files.\n\n### 6. Confirm\n\nTell the user the block was written and the `poteto-agent` and `comment-sicko` roles were installed, and that both apply to new threads. Re-running this skill updates them. For big fan-outs (`$pstack:swarm`, `$pstack:arena`, the Orchestrate playbook), add that Codex runs at most `[agents] max_threads` threads at once, 6 by default, and that `[agents] max_depth` caps how deep subagents can nest if Codex refuses a nested spawn. Both live in `~\u002F.codex\u002Fconfig.toml`.\n\n### 7. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with $pstack:create-verification-skill.\" On yes, invoke `$pstack:create-verification-skill` (resolves wherever pstack is installed: workspace, user, or plugin). On no, move on without pushing.\n","# Setup pstack\n\nWrite the `pstack-models` block in `~\u002F.codex\u002FAGENTS.md`, an always-loaded block that sets pstack's model per role.\n\n## Steps\n\n### 1. Detect available models\n\nRun `codex debug models` and keep every entry whose `visibility` is `list`. Each supported effort in its `supported_reasoning_levels` makes one detected slug, `\u003Cslug>-\u003Ceffort>`. That is the dependable source.\n\n```bash\ncodex debug models | python3 -c 'import json,sys\nfor m in json.load(sys.stdin)[\"models\"]:\n    if m.get(\"visibility\") == \"list\":\n        for l in m[\"supported_reasoning_levels\"]: print(m[\"slug\"] + \"-\" + l[\"effort\"])'\n```\n\nIf `command -v claude` succeeds, also detect the cross-vendor entries `claude:\u003Calias>-\u003Ceffort>` for the aliases `opus`, `sonnet`, `haiku`, and `fable` and the efforts `low`, `medium`, `high`, `xhigh`, and `max`. They run through the local `claude` CLI and are valid in any role. Confirm each chosen `claude:` entry once with a one-turn probe, `claude -p --model \u003Calias> --effort \u003Ceffort> \"reply OK\"`, because `command -v claude` does not show which efforts a model supports. If the probe fails, drop the entry. If you cannot detect any, ask the user to paste the slugs they have access to. Never write a real slug you have not confirmed is available. The aliases `inherit-parent` and `auto` are always valid even though they are not detected slugs.\n\n### 2. Load current state\n\nThe default role-to-model mapping is the block shape shown in step 5 below. If `~\u002F.codex\u002FAGENTS.md` (or `AGENTS.override.md` in the same directory, when it exists) already holds the `pstack-models` block, read it and treat its `# budget` line and its role values as the current choices. Otherwise start from those defaults. A line whose role is not in step 5, such as `how critics`, is from a retired role. Drop it.\n\n### 3. Budget, map, and confirm\n\n**(a) Ask for a budget.** Prefer `request_user_input` over free text. Use it when your tool list has it, else ask in plain text with the same labels. Offer these four options with these exact labels, and name the current budget when the block records one. With no block, say that `large` matches the skill defaults.\n\n- `unlimited — max reasoning`\n- `large — xhigh reasoning`\n- `medium — high reasoning`\n- `small — medium reasoning`\n\n**(b) Apply it.** Build the working table from the skill defaults, and on a re-run keep any role you changed by family, list, or alias (`inherit-parent`, `auto`). `unlimited`, `large`, `medium`, and `small` set the effort token of every real slug, panel entries included, to `max`, `xhigh`, `high`, or `medium`. The effort token is the last `-` token, on the ladder `max` > `xhigh` > `high` > `medium` > `low`. If the result is not a detected slug, use the same family's detected slug with the highest effort at or below the target, else mark the role as needing a choice. `inherit-parent` and `auto` do not change. So `unlimited` turns `gpt-6-astra-xhigh` into `gpt-6-astra-max`. Codex also offers `ultra` above `max` on `gpt-6-astra` and the `sol` models, but no budget sets it, so `unlimited` stays `max` and `ultra` is an opt-in per role in step (c). `large` keeps both defaults. `small` turns them into `gpt-6-astra-medium` and `gpt-6.1-sol-medium`. A `claude:` entry follows the same ladder.\n\n**(c) Show the roles and confirm.** Show every role with its model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped. Ask whether to accept as-is or change specific roles, offering the detected models plus `inherit-parent` and `auto` (both mean: this role runs on the parent chat model, whatever model the thread runs on) as the options. Offer `ultra` as an opt-in for any role on a model that lists it. Prefer `request_user_input` over free text, as in (a). For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. A detected `claude:` entry can join a panel list, `arena cross-judge pool` included, and gives that panel a second vendor. Without the `claude` CLI every default panel is two OpenAI models, so say so when the user cares about model diversity. `arena cross-judge pool` is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. `swarm workers` is the default model for every worker unless a race or comparison assigns another model per arm.\n\n### 4. Validate\n\nEvery real slug written must be in the detected set. `inherit-parent` and `auto` always pass. A `claude:` entry passes only when its probe from step 1 succeeded. If a chosen real slug is not available, stop and ask again.\n\n### 5. Write the block\n\nWrite the block between `\u003C!-- pstack-models:begin -->` and `\u003C!-- pstack-models:end -->` in `~\u002F.codex\u002FAGENTS.md`, with a `# budget` line with the chosen label and its target effort, and one line per role, using the same labels poteto-mode uses. Codex loads `~\u002F.codex\u002FAGENTS.md` into every new thread, so the block applies everywhere. Replace the text between the markers when they exist, append the block when they don't, create the file when it is missing, and never touch anything outside the markers, so re-runs stay idempotent. Shape:\n\n```\n\u003C!-- pstack-models:begin -->\n# pstack model configuration. One line per role. Delete a line to fall back to the skill default.\n# `inherit-parent` or `auto` as a value: the role runs on the parent chat model (omit `model` and `reasoning_effort`). Alias entries in a panel list still count toward its fan-out.\n# budget: large (xhigh)\nfeature, refactoring: gpt-6.1-sol-xhigh\nbug-fix: gpt-6.1-sol-xhigh\nperf-issue: gpt-6.1-sol-xhigh\nhillclimb: gpt-6.1-sol-xhigh\njudgment and prose: gpt-6-astra-xhigh\nhardest tasks: gpt-6-astra-xhigh\nhow explorer: gpt-6.1-sol-xhigh\nhow explainer: gpt-6-astra-xhigh\nwhy investigators: gpt-6.1-sol-xhigh\nwhy synthesizer: gpt-6-astra-xhigh\nreflect tooling: gpt-6.1-sol-xhigh\nreflect judgment, divergent, synthesizer: gpt-6-astra-xhigh\narena runners: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\narena cross-judge pool: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\nswarm workers: gpt-6.1-sol-xhigh\narchitect runners: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\ninterrogate reviewers: gpt-6-astra-xhigh, gpt-6.1-sol-xhigh\n\u003C!-- pstack-models:end -->\n```\n\nWith the block saved to a file, this replaces or appends it in place. It exits with a message unless the block file starts with the begin marker and ends with the end marker, and unless the target has at most one begin marker with its end marker after it. Markers match only at line start. If `AGENTS.override.md` exists in the Codex home, Codex loads it instead of `AGENTS.md`, so the updater tells the user and writes the block there. The write is atomic.\n\n```bash\npython3 - \"${CODEX_HOME:-$HOME\u002F.codex}\" \u003Cblock-file> \u003C\u003C'PY'\nimport os, re, sys, tempfile\nBEGIN, END = \"\u003C!-- pstack-models:begin -->\", \"\u003C!-- pstack-models:end -->\"\nhome, block = sys.argv[1], open(sys.argv[2]).read().strip() + \"\\n\"\nif not (block.startswith(BEGIN) and block.rstrip(\"\\n\").endswith(END)):\n    sys.exit(\"The block file must start with the begin marker and end with the end marker.\")\npath = os.path.join(home, \"AGENTS.md\")\noverride = os.path.join(home, \"AGENTS.override.md\")\nif os.path.exists(override):\n    print(\"Codex loads \" + override + \" instead of AGENTS.md, so the block goes there.\")\n    path = override\ntext = open(path).read() if os.path.exists(path) else \"\"\nbegins = list(re.finditer(\"^\" + re.escape(BEGIN) + r\"[ \\t]*$\", text, re.M))\nends = list(re.finditer(\"^\" + re.escape(END) + r\"[ \\t]*$\\n?\", text, re.M))\nif len(begins) > 1:\n    sys.exit(\"The file has more than one begin marker. Fix it by hand, then rerun.\")\nif ends and not begins:\n    sys.exit(\"The file has an end marker without a begin marker. Fix it by hand, then rerun.\")\nif begins:\n    after = [e for e in ends if e.start() > begins[0].start()]\n    if not after or len(ends) > 1:\n        sys.exit(\"The begin marker needs exactly one matching end marker after it. Fix it by hand, then rerun.\")\n    text = text[:begins[0].start()] + block + text[after[0].end():]\nelse:\n    text = text.rstrip(\"\\n\") + \"\\n\\n\" + block if text.strip() else block\nos.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)\nfd, tmp = tempfile.mkstemp(dir=os.path.dirname(os.path.abspath(path)), prefix=\".pstack-\")\nwith os.fdopen(fd, \"w\") as f:\n    f.write(text)\n    f.flush()\n    os.fsync(f.fileno())\nif os.path.exists(path):\n    os.chmod(tmp, os.stat(path).st_mode & 0o7777)\nos.replace(tmp, path)\nPY\n```\n\n\nThen install pstack's agent roles. Codex plugins cannot register roles, so copy them from this plugin with `mkdir -p \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fagents\" && cp ..\u002F..\u002Fagents\u002Fpoteto-agent.toml ..\u002F..\u002Fagents\u002Fcomment-sicko.toml \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fagents\u002F\"`, with both source paths resolved from this file's directory. This overwrites only pstack's own two role files.\n\n### 6. Confirm\n\nTell the user the block was written and the `poteto-agent` and `comment-sicko` roles were installed, and that both apply to new threads. Re-running this skill updates them. For big fan-outs (`$pstack:swarm`, `$pstack:arena`, the Orchestrate playbook), add that Codex runs at most `[agents] max_threads` threads at once, 6 by default, and that `[agents] max_depth` caps how deep subagents can nest if Codex refuses a nested spawn. Both live in `~\u002F.codex\u002Fconfig.toml`.\n\n### 7. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with $pstack:create-verification-skill.\" On yes, invoke `$pstack:create-verification-skill` (resolves wherever pstack is installed: workspace, user, or plugin). On no, move on without pushing.\n",{"name":5,"description":7},"main","3cf90aeb365f524d07ef38f0fb3cbad19aeecc6f","codex\u002Fpstack\u002Fskills\u002Fsetup-pstack","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports","https:\u002F\u002Fgithub.com\u002Firfanalimd","irfanali.me","2026-10-17 07:04:24",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add irfanalimd\u002Fpstack-ports --skill setup-pstack",{"tool":37,"command":38},"bunx","bunx skills add irfanalimd\u002Fpstack-ports --skill setup-pstack",{"tool":40,"command":41},"pnpm","pnpm dlx skills add irfanalimd\u002Fpstack-ports --skill setup-pstack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fcodex\u002Fpstack\u002Fskills\u002Fsetup-pstack\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"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},"01M7F0ZB3XY54V5W1VACEVX58W","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\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Fwhy\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},"01M7F0Z9GHCK4T0WPSBEBAEMB7","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7F0Z7K4GWX9DDDD13G98GBE","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7F0Z3ATKTCM4ZEFP0V8YW90","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7F0YZW6SA7BJN6WA9T58GGX","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7F0YWN310MAHQWZF0ADYADS","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Firfanalimd\u002Fpstack-ports\u002Fblob\u002Fmain\u002Fupstream\u002Fpstack\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]