[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F3XTQMPHCZ2MR2BSW2ANXD":3,"skill-same:01M7F3XTQMPHCZ2MR2BSW2ANXD":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},"01M7F3XTQMPHCZ2MR2BSW2ANXD","compound",null,"Write up each non-obvious problem a unit solved in docs\u002Fsolutions\u002F, index it, and update the resume point. Use after every unit's work review clears (it writes up what was non-obvious, if anything, then asks before merging unless the repo records a standing merge grant), and always when the user says \"compound\". With the argument checkpoint it writes up what is outstanding and the handoff without merging, so a compaction loses nothing. Compound step of the methodical loop. Not the same as compacting the context.","BigLeverVentures\u002Fmethodical-gated-engineering","BigLeverVentures","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F196365016?v=4","01M7F3V567G0YQ3QWY39AHD9BN","Big Lever Ventures","01M7F3V56S1VHYERWFCQM018V7",0,"MIT","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical-codex\u002Fskills\u002Fcompound\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: compound\ndescription: \"Write up each non-obvious problem a unit solved in docs\u002Fsolutions\u002F, index it, and update the resume point. Use after every unit's work review clears (it writes up what was non-obvious, if anything, then asks before merging unless the repo records a standing merge grant), and always when the user says \\\"compound\\\". With the argument checkpoint it writes up what is outstanding and the handoff without merging, so a compaction loses nothing. Compound step of the methodical loop. Not the same as compacting the context.\"\n---\n\n# Compound\n\nSay `Step: compound` before anything else.\n\nCompound writes down what was learned so the next unit starts ahead. An explicit request to compound\nand compact uses checkpoint mode on the current branch, followed by the host's compact action.\nWhy: only a written-up solution is found by a later session before it re-solves a familiar problem;\na memory pointer alone is not the compound step.\n\n## Two modes\n\n- **Closure** is the default, a bare `\u002Fmethodical:compound`, and the step after work review clears:\n  everything under \"What it produces\" and \"The merge ask\", ending at the merge ask or a standing grant.\n- **Checkpoint** uses the argument `checkpoint` or the adapter’s `checkpoint then compact` prefix. It is run from the offers before a compaction,\n  from the question at a typed `\u002Fcompact`, and by the compact skill. It writes up what is outstanding\n  and the handoff on the current branch and stops: it never merges, never asks about a merge, never\n  uses a standing grant and never closes the unit. Why: a compaction can come at any moment, and the\n  unit is not finished then.\n\n## Checkpoint\n\nDo this instead of the rest of the skill for either checkpoint argument or an explicit request to\ncompound and compact together. It is one turn: it says what it did and never ends with a question.\n\n1. **The counterfactual.** Could a later engineer redo this stretch's work from the final code, tests\n   and docs alone? If so for all of it, write no solution file and say why in one line.\n2. **Otherwise one write-up for each outstanding non-obvious problem of the stretch**, made and indexed\n   as under \"What it produces\". Near the context limit write each concisely, and carry any lesson that\n   cannot be written in full in the handoff. A worker may write the solution files; this thread reads\n   their results and writes the handoff and the production checkpoint.\n3. **Run all of the project's tests** now, before the handoff, unless you have read\n   `${PLUGIN_ROOT}\u002Freference\u002Fnarrow-checks.md` and followed it for the checkpoint's files, printing each path beside the\n   `narrow-check:` line it matched; a run without that printout is a full run. Why: finish verification before publication so its results are in the handoff.\n4. **The handoff**: the compact skill's resume point (its shape, every ruling verbatim), in the place the\n   user chose (`docs\u002Fresume.md`, or `docs\u002Fprivate\u002Fresume.md`, which stays uncommitted and is never\n   force-added). Name that location in the handoff so recovery reads the right one. Commit the tracked\n   files (write-ups, index, resume point) on the current branch; no push, no merge.\n5. **Publish and verify, last.** Follow the finalization protocol and parent-authored Work template in\n   `${PLUGIN_ROOT}\u002Freference\u002Fnative-routing.md`. Finish the resume point, verbatim rulings, lesson index,\n   tests, commits and all relevant-state records first. Include the chosen resume file as the required\n   `methodical:resume` capture; include required support at its original path. Derive the binding from the\n   existing approved unit and current routing state. Write the Work input under `.methodical\u002Fevidence\u002F`.\n   The final tool call is the overlay's `checkpoint-finalize` runtime command. It publishes the production\n   bundle and performs a read-only freshness check in that same invocation. Only its successful\n   `methodical-checkpoint-finalized` receipt with `current: true` completes the handoff. A missing binding,\n   unsupported runtime, failed command or stale result is an explicit unfinished checkpoint; never claim a pass.\n   Make no tool call of any kind after successful finalization, chapter and task tools included.\n   When the host adapter started this checkpoint with the `checkpoint then compact` prefix, say the handoff is written\n   and end the turn. The adapter owns the requested compaction. For a standalone checkpoint or a host\n   without automatic chaining, tell the user they can run the host's manual compact action.\n   Why: a later write, commit, new ruling or routing transition makes the portable record stale.\n\nIf a compaction lands during a checkpoint, re-read the resume point, note \"resumed after a compaction\nboundary\" in the handoff, and finish. If the unit solved nothing non-obvious, the checkpoint is still the\nhandoff and a verified production checkpoint.\n\n## What it produces (closure)\n\n1. **One write-up per non-obvious problem solved**, made from\n   `${PLUGIN_ROOT}\u002Ftemplates\u002Fsolution.md` into `docs\u002Fsolutions\u002F\u003Ccategory>\u002F\u003Cslug>.md`. Reuse a\n   category folder that already exists before making a new one.\n2. **Its index line** in `docs\u002Fsolutions\u002FREADME.md`, as the template's last section gives it.\n   Create the README with a one-line header and `## Index` if it is missing. Why: an unindexed\n   write-up is not found.\n3. **The resume point updated**, with this unit's rulings and the state in flight (the compact\n   skill gives its shape). Before quoting the user, read\n   `${PLUGIN_ROOT}\u002Frules\u002Fuser-words.md` and follow it.\n\nCommit these on the unit's branch, which work-review left unmerged (or a short docs branch if the\nunit is already merged), and run the tests as step 3 says. If the unit solved nothing non-obvious, say so in one\nline and only update the resume point. After a waived plan, compound runs as usual; one line\nsaying nothing non-obvious was solved is the normal outcome.\n\nCompound never offers to skip itself. If the user skips it, go to the merge ask.\n\n## The merge ask, or a standing grant\n\nBefore any merge, whether the user's go or a standing grant gives it, run all of the project's tests on the branch's\nHEAD, unless you ran all of them on that exact HEAD in this session. Why: a merge should rest on a full run of what\nmerges, and narrowing is for commits, not for merges; you cannot tell from memory whether an earlier commit was\nnarrowed.\n\nThen look for a standing merge grant. From the repo root (`cd \"$(git rev-parse --show-toplevel)\"`),\nrun exactly:\n\n```sh\ngrep -nE '^[[:space:]>*-]*(\\*\\*)?merge-grant: (standing|ask)\\b' CLAUDE.md docs\u002Frulings.md docs\u002Fprivate\u002Frulings.md 2>\u002Fdev\u002Fnull\n```\n\nIt checks the repo's root `CLAUDE.md`, `docs\u002Frulings.md` and `docs\u002Fprivate\u002Frulings.md` for a line\nthat, after any list, quote or bold opener, starts `merge-grant: standing` (optionally followed by\n` — \u003Cconditions>`) or `merge-grant: ask`. Read its printed lines, never its exit status: a missing\nfile makes grep exit non-zero even when another file matched.\n\n- **Any `merge-grant: ask` line** → ask, as below. `ask` wins, so the user can take a grant back\n  in their rulings file without editing `CLAUDE.md`.\n- **Otherwise any `merge-grant: standing` line** → do not ask. Say\n  \"Merging on the standing grant at `\u003Cfile>:\u003Cline>`: \u003Cthe line>\", honor every condition written\n  after the dash as written, then merge and delete the branch. If you cannot verify a condition the\n  line names (a check not completed and passing, a kind of session the line excludes), ask instead.\n- **No line printed** → ask. Prose such as \"merging at green is Claude's job\" is never a grant.\n\nOnly the user writes a `merge-grant:` line. Never add, edit or infer one, and never turn their prose\ninto one, even when tidying a file. Why: a grant you wrote is a ruling they never gave.\n\nA grant is written as a plain line or list item. The grep cannot see code fences, so these three\nfiles never show the form inside one.\n\nTo ask, ask \"Merge when green?\" with the native structured-question tool and stop; this is the unit's one merge ask:\n`options: \"Merge when green (Recommended)\" \u002F \"Hold\"`. If you\nrecord their answer, first read `${PLUGIN_ROOT}\u002Frules\u002Fuser-words.md` and follow it. Never\nmerge to `main` or delete the branch without their go or a standing grant; \"merge it\" in the\nuser's own words is the go. The grant covers this\nmerge ask only: plan approval, the North Star, money and irreversible acts still stop. Why: `main`\nis the user's trunk; a standing grant is their ruling given once, and `ask` is how they take it\nback. The write-up lands in the same merge as its unit.\n\nThe write-up is worker work: write it on the worker's row, or the decider's row when the plan's\n`escalation:` is `lean` or `full` (Escalation in\n`${PLUGIN_ROOT}\u002Freference\u002Fseat-selection.md`), with that row's model and effort, or launch\nit on one.\n\n## When it hands on\n\nOnce merged, by the user's go or a standing grant, delete the branch in the same turn and return to\nthe user's next request; the loop starts again there. Say `Step: compact`\nand continue with the compact skill only if the context window is half full or more, or the user\nasks. Why: compacting after every merge spends a resume point on a window that still has room.\n","# Compound\n\nSay `Step: compound` before anything else.\n\nCompound writes down what was learned so the next unit starts ahead. An explicit request to compound\nand compact uses checkpoint mode on the current branch, followed by the host's compact action.\nWhy: only a written-up solution is found by a later session before it re-solves a familiar problem;\na memory pointer alone is not the compound step.\n\n## Two modes\n\n- **Closure** is the default, a bare `\u002Fmethodical:compound`, and the step after work review clears:\n  everything under \"What it produces\" and \"The merge ask\", ending at the merge ask or a standing grant.\n- **Checkpoint** uses the argument `checkpoint` or the adapter’s `checkpoint then compact` prefix. It is run from the offers before a compaction,\n  from the question at a typed `\u002Fcompact`, and by the compact skill. It writes up what is outstanding\n  and the handoff on the current branch and stops: it never merges, never asks about a merge, never\n  uses a standing grant and never closes the unit. Why: a compaction can come at any moment, and the\n  unit is not finished then.\n\n## Checkpoint\n\nDo this instead of the rest of the skill for either checkpoint argument or an explicit request to\ncompound and compact together. It is one turn: it says what it did and never ends with a question.\n\n1. **The counterfactual.** Could a later engineer redo this stretch's work from the final code, tests\n   and docs alone? If so for all of it, write no solution file and say why in one line.\n2. **Otherwise one write-up for each outstanding non-obvious problem of the stretch**, made and indexed\n   as under \"What it produces\". Near the context limit write each concisely, and carry any lesson that\n   cannot be written in full in the handoff. A worker may write the solution files; this thread reads\n   their results and writes the handoff and the production checkpoint.\n3. **Run all of the project's tests** now, before the handoff, unless you have read\n   `${PLUGIN_ROOT}\u002Freference\u002Fnarrow-checks.md` and followed it for the checkpoint's files, printing each path beside the\n   `narrow-check:` line it matched; a run without that printout is a full run. Why: finish verification before publication so its results are in the handoff.\n4. **The handoff**: the compact skill's resume point (its shape, every ruling verbatim), in the place the\n   user chose (`docs\u002Fresume.md`, or `docs\u002Fprivate\u002Fresume.md`, which stays uncommitted and is never\n   force-added). Name that location in the handoff so recovery reads the right one. Commit the tracked\n   files (write-ups, index, resume point) on the current branch; no push, no merge.\n5. **Publish and verify, last.** Follow the finalization protocol and parent-authored Work template in\n   `${PLUGIN_ROOT}\u002Freference\u002Fnative-routing.md`. Finish the resume point, verbatim rulings, lesson index,\n   tests, commits and all relevant-state records first. Include the chosen resume file as the required\n   `methodical:resume` capture; include required support at its original path. Derive the binding from the\n   existing approved unit and current routing state. Write the Work input under `.methodical\u002Fevidence\u002F`.\n   The final tool call is the overlay's `checkpoint-finalize` runtime command. It publishes the production\n   bundle and performs a read-only freshness check in that same invocation. Only its successful\n   `methodical-checkpoint-finalized` receipt with `current: true` completes the handoff. A missing binding,\n   unsupported runtime, failed command or stale result is an explicit unfinished checkpoint; never claim a pass.\n   Make no tool call of any kind after successful finalization, chapter and task tools included.\n   When the host adapter started this checkpoint with the `checkpoint then compact` prefix, say the handoff is written\n   and end the turn. The adapter owns the requested compaction. For a standalone checkpoint or a host\n   without automatic chaining, tell the user they can run the host's manual compact action.\n   Why: a later write, commit, new ruling or routing transition makes the portable record stale.\n\nIf a compaction lands during a checkpoint, re-read the resume point, note \"resumed after a compaction\nboundary\" in the handoff, and finish. If the unit solved nothing non-obvious, the checkpoint is still the\nhandoff and a verified production checkpoint.\n\n## What it produces (closure)\n\n1. **One write-up per non-obvious problem solved**, made from\n   `${PLUGIN_ROOT}\u002Ftemplates\u002Fsolution.md` into `docs\u002Fsolutions\u002F\u003Ccategory>\u002F\u003Cslug>.md`. Reuse a\n   category folder that already exists before making a new one.\n2. **Its index line** in `docs\u002Fsolutions\u002FREADME.md`, as the template's last section gives it.\n   Create the README with a one-line header and `## Index` if it is missing. Why: an unindexed\n   write-up is not found.\n3. **The resume point updated**, with this unit's rulings and the state in flight (the compact\n   skill gives its shape). Before quoting the user, read\n   `${PLUGIN_ROOT}\u002Frules\u002Fuser-words.md` and follow it.\n\nCommit these on the unit's branch, which work-review left unmerged (or a short docs branch if the\nunit is already merged), and run the tests as step 3 says. If the unit solved nothing non-obvious, say so in one\nline and only update the resume point. After a waived plan, compound runs as usual; one line\nsaying nothing non-obvious was solved is the normal outcome.\n\nCompound never offers to skip itself. If the user skips it, go to the merge ask.\n\n## The merge ask, or a standing grant\n\nBefore any merge, whether the user's go or a standing grant gives it, run all of the project's tests on the branch's\nHEAD, unless you ran all of them on that exact HEAD in this session. Why: a merge should rest on a full run of what\nmerges, and narrowing is for commits, not for merges; you cannot tell from memory whether an earlier commit was\nnarrowed.\n\nThen look for a standing merge grant. From the repo root (`cd \"$(git rev-parse --show-toplevel)\"`),\nrun exactly:\n\n```sh\ngrep -nE '^[[:space:]>*-]*(\\*\\*)?merge-grant: (standing|ask)\\b' CLAUDE.md docs\u002Frulings.md docs\u002Fprivate\u002Frulings.md 2>\u002Fdev\u002Fnull\n```\n\nIt checks the repo's root `CLAUDE.md`, `docs\u002Frulings.md` and `docs\u002Fprivate\u002Frulings.md` for a line\nthat, after any list, quote or bold opener, starts `merge-grant: standing` (optionally followed by\n` — \u003Cconditions>`) or `merge-grant: ask`. Read its printed lines, never its exit status: a missing\nfile makes grep exit non-zero even when another file matched.\n\n- **Any `merge-grant: ask` line** → ask, as below. `ask` wins, so the user can take a grant back\n  in their rulings file without editing `CLAUDE.md`.\n- **Otherwise any `merge-grant: standing` line** → do not ask. Say\n  \"Merging on the standing grant at `\u003Cfile>:\u003Cline>`: \u003Cthe line>\", honor every condition written\n  after the dash as written, then merge and delete the branch. If you cannot verify a condition the\n  line names (a check not completed and passing, a kind of session the line excludes), ask instead.\n- **No line printed** → ask. Prose such as \"merging at green is Claude's job\" is never a grant.\n\nOnly the user writes a `merge-grant:` line. Never add, edit or infer one, and never turn their prose\ninto one, even when tidying a file. Why: a grant you wrote is a ruling they never gave.\n\nA grant is written as a plain line or list item. The grep cannot see code fences, so these three\nfiles never show the form inside one.\n\nTo ask, ask \"Merge when green?\" with the native structured-question tool and stop; this is the unit's one merge ask:\n`options: \"Merge when green (Recommended)\" \u002F \"Hold\"`. If you\nrecord their answer, first read `${PLUGIN_ROOT}\u002Frules\u002Fuser-words.md` and follow it. Never\nmerge to `main` or delete the branch without their go or a standing grant; \"merge it\" in the\nuser's own words is the go. The grant covers this\nmerge ask only: plan approval, the North Star, money and irreversible acts still stop. Why: `main`\nis the user's trunk; a standing grant is their ruling given once, and `ask` is how they take it\nback. The write-up lands in the same merge as its unit.\n\nThe write-up is worker work: write it on the worker's row, or the decider's row when the plan's\n`escalation:` is `lean` or `full` (Escalation in\n`${PLUGIN_ROOT}\u002Freference\u002Fseat-selection.md`), with that row's model and effort, or launch\nit on one.\n\n## When it hands on\n\nOnce merged, by the user's go or a standing grant, delete the branch in the same turn and return to\nthe user's next request; the loop starts again there. Say `Step: compact`\nand continue with the compact skill only if the context window is half full or more, or the user\nasks. Why: compacting after every merge spends a resume point on a window that still has room.\n",{"name":5,"description":7},"main","67bcf3c285965a9714d303252d8023a960a82511","plugins\u002Fmethodical-codex\u002Fskills\u002Fcompound","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering","https:\u002F\u002Fgithub.com\u002FBigLeverVentures","www.bigleverventures.com","2026-11-15 10:50:39",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add BigLeverVentures\u002Fmethodical-gated-engineering --skill compound",{"tool":37,"command":38},"bunx","bunx skills add BigLeverVentures\u002Fmethodical-gated-engineering --skill compound",{"tool":40,"command":41},"pnpm","pnpm dlx skills add BigLeverVentures\u002Fmethodical-gated-engineering --skill compound","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical-codex\u002Fskills\u002Fcompound\u002FSKILL.md",true,[],[46,52,58,65,72,79],{"skillNo":47,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7F3ZT8YMJ3EZ6RDQ20X5SVF","phrase-outside","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fhand-off\u002Fphrase-outside\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7F3ZR6P6W75DY7QVP7TP9NT","named-only","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fhand-off\u002Fnamed-only\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7F3ZMHBD3K2WMEFC5XS2224","work","Build an approved plan from docs\u002Fplans\u002F on its own short-lived branch, or a change the user said to make without a plan. Use when a plan reads state: approved and the user wants it built, when resuming such a build, or when the user has waived the plan for a named change. Work step of the methodical loop. Not when no approved plan exists and the user has not waived one (run the plan step), and not for reviewing finished work.","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical\u002Fskills\u002Fwork\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7F3ZFVSDD9CMC6X63S8TWK5","work-review","Review a finished build on its branch against its plan, with reviewer seats matched to the code's language, before it merges. Use when the work step's tests pass and the plan's approach is done, or when the user asks for a review of a branch's changes. Work-review step of the methodical loop. Not for reviewing a plan.","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical\u002Fskills\u002Fwork-review\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7F3ZC9EXRTW3D90JRAV32ED","plan","Write the plan file in docs\u002Fplans\u002F that code changes get before building, unless the user has said to build without one. Use when the user asks to build, fix, edit or change code and docs\u002Fplans\u002F has no approved plan for it, or when a plan must be revised after review. Plan step of the methodical loop. Not for questions or reading code, and not when the user has waived the plan for this change (go to work).","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7F3Z8YMRZJDESVP61JQHM27","plan-review","Review a plan in docs\u002Fplans\u002F with reviewer seats matched to the project's language, before the user approves it. Use when a plan has just been written or deepened, when a plan was revised after review, or when the user asks for a plan review. Plan-review step of the methodical loop. Not for reviewing built code.","https:\u002F\u002Fgithub.com\u002FBigLeverVentures\u002Fmethodical-gated-engineering\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodical\u002Fskills\u002Fplan-review\u002FSKILL.md",[],[]]