[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AHCE4AVGF6CEMT6FPEKJZ3":3,"skill-same:01M7AHCE4AVGF6CEMT6FPEKJZ3":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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7AHCE4AVGF6CEMT6FPEKJZ3","session-critique",null,"Use when a completed multi-file change needs decision-aware independent review, especially for security, trust boundaries, architecture, or cross-cutting behavior. Manual only. NOT for routine focused checks, deterministic validation, or work that is still changing.","SamyakJhaveri\u002Floam","SamyakJhaveri","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39847642?v=4","01M7AH87180VZDSRHE20JD1S32","Samyak Jhaveri","01M7AH871WNGEHDVNXJM2B520R",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fsession-critique\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: session-critique\ndescription: >\n  Use when a completed multi-file change needs decision-aware independent review,\n  especially for security, trust boundaries, architecture, or cross-cutting behavior.\n  Manual only. NOT for routine focused checks, deterministic validation, or work\n  that is still changing.\ndisable-model-invocation: true\n---\n\n# Session Critique\n\nReview one fixed diff against the user's decisions and repository rules. Keep the\nreview independent from implementation. Save its evidence so another turn does not\nrepeat the same review.\n\n## When to use\n\n- The change crosses subsystems or changes architecture.\n- The change affects security, permissions, data integrity, or another trust boundary.\n- The user asks for an independent review.\n\nFor routine or single-area work, use focused self-review plus `\u002Fvalidate`.\n\n## Model and team policy\n\nInspect the live spawn tool before selecting a model or effort. Use a stronger available\nreview profile for the aggregate reviewer. Do not copy a model ID from prose. Add a\nspecialist only for a concrete risk that the aggregate reviewer cannot cover. Mechanical\nevidence gathering uses the default or cheaper available profile.\n\n## Phase 1: Freeze the review input\n\nThe integration owner records:\n\n```text\nbase revision\nchanged paths, including untracked paths\ndiff fingerprint\nvalidation receipt fingerprint, or \"none\"\nnumbered session decisions\n```\n\nThe reviewer uses this fixed diff. It checks the fingerprint before and after review.\nIf the source changes, it stops and reports that its input became stale. It does not\nsilently switch to the new diff.\n\n## Phase 2: Independent review\n\nSpawn one read-only aggregate reviewer. Give it only the fixed input, repository rules,\nand acceptance criteria. Do not include the implementer's rationale or earlier verdicts.\nThe reviewer checks:\n\n1. Correctness and decision adherence.\n2. Security and trust-boundary failures.\n3. Unchecked callers, interfaces, and cross-file contradictions.\n4. Scope drift, excess machinery, and missing error paths.\n5. Claims not supported by the fixed diff or durable validation receipt.\n\nThe reviewer does not rerun an unchanged full suite. It may run a focused check only for\na named unresolved risk that existing evidence does not cover. It reports the command,\nexit code, and why the extra run was needed.\n\n## Phase 3: Durable findings\n\nWrite the report under `.superpowers\u002Freviews\u002F` with the diff fingerprint in the filename.\nKeep it bounded. Point to source sections and log paths instead of pasting whole files or\nlogs.\n\n```markdown\n# Independent review: \u003Cfingerprint>\n\n## Verdict\nPASS | FIX | BLOCKED\n\n## Fixed input\n- Base: \u003Crevision>\n- Diff fingerprint: \u003Cfingerprint>\n- Validation receipt: \u003Cfingerprint or none>\n\n## Findings\n| Severity | Evidence | Consequence | Smallest repair |\n|----------|----------|-------------|-----------------|\n\n## Coverage and deferred checks\n- Checked: ...\n- Deferred: ... because ...\n```\n\nEvery finding is either confirmed with evidence or marked uncertain with the exact check\nthat would settle it. An unrun check is never a pass.\n\n## Phase 4: Repair and re-review\n\nThe user approves any repair that changes scope or a prior decision. A targeted owner\nimplements each accepted repair and runs its focused regression check. The validation\nowner runs new validation because the content fingerprint changed.\n\nReuse the durable review when the diff fingerprint is unchanged. Run a second independent\nreview only when a material repair changes behavior across the reviewed boundary, or when\nthe first report names a concrete unresolved risk. Record why the second review was needed.\n\n## Completion\n\nThe critique is complete when the report has a verdict, every blocking finding has a\nrecorded disposition, the fixed-input fingerprint still matches, and deferred checks are\nvisible. `\u002Fvalidate` remains the one deterministic full-gate owner. Critique does not run\nthat gate again.\n\n## Red flags\n\n- Review input changes while reviewers are running.\n- Several generic reviewers inspect the same diff.\n- A reviewer repeats the full suite without a named evidence gap.\n- Findings exist only in chat or a transcript.\n- A repair changes the fingerprint but old evidence is called current.\n","# Session Critique\n\nReview one fixed diff against the user's decisions and repository rules. Keep the\nreview independent from implementation. Save its evidence so another turn does not\nrepeat the same review.\n\n## When to use\n\n- The change crosses subsystems or changes architecture.\n- The change affects security, permissions, data integrity, or another trust boundary.\n- The user asks for an independent review.\n\nFor routine or single-area work, use focused self-review plus `\u002Fvalidate`.\n\n## Model and team policy\n\nInspect the live spawn tool before selecting a model or effort. Use a stronger available\nreview profile for the aggregate reviewer. Do not copy a model ID from prose. Add a\nspecialist only for a concrete risk that the aggregate reviewer cannot cover. Mechanical\nevidence gathering uses the default or cheaper available profile.\n\n## Phase 1: Freeze the review input\n\nThe integration owner records:\n\n```text\nbase revision\nchanged paths, including untracked paths\ndiff fingerprint\nvalidation receipt fingerprint, or \"none\"\nnumbered session decisions\n```\n\nThe reviewer uses this fixed diff. It checks the fingerprint before and after review.\nIf the source changes, it stops and reports that its input became stale. It does not\nsilently switch to the new diff.\n\n## Phase 2: Independent review\n\nSpawn one read-only aggregate reviewer. Give it only the fixed input, repository rules,\nand acceptance criteria. Do not include the implementer's rationale or earlier verdicts.\nThe reviewer checks:\n\n1. Correctness and decision adherence.\n2. Security and trust-boundary failures.\n3. Unchecked callers, interfaces, and cross-file contradictions.\n4. Scope drift, excess machinery, and missing error paths.\n5. Claims not supported by the fixed diff or durable validation receipt.\n\nThe reviewer does not rerun an unchanged full suite. It may run a focused check only for\na named unresolved risk that existing evidence does not cover. It reports the command,\nexit code, and why the extra run was needed.\n\n## Phase 3: Durable findings\n\nWrite the report under `.superpowers\u002Freviews\u002F` with the diff fingerprint in the filename.\nKeep it bounded. Point to source sections and log paths instead of pasting whole files or\nlogs.\n\n```markdown\n# Independent review: \u003Cfingerprint>\n\n## Verdict\nPASS | FIX | BLOCKED\n\n## Fixed input\n- Base: \u003Crevision>\n- Diff fingerprint: \u003Cfingerprint>\n- Validation receipt: \u003Cfingerprint or none>\n\n## Findings\n| Severity | Evidence | Consequence | Smallest repair |\n|----------|----------|-------------|-----------------|\n\n## Coverage and deferred checks\n- Checked: ...\n- Deferred: ... because ...\n```\n\nEvery finding is either confirmed with evidence or marked uncertain with the exact check\nthat would settle it. An unrun check is never a pass.\n\n## Phase 4: Repair and re-review\n\nThe user approves any repair that changes scope or a prior decision. A targeted owner\nimplements each accepted repair and runs its focused regression check. The validation\nowner runs new validation because the content fingerprint changed.\n\nReuse the durable review when the diff fingerprint is unchanged. Run a second independent\nreview only when a material repair changes behavior across the reviewed boundary, or when\nthe first report names a concrete unresolved risk. Record why the second review was needed.\n\n## Completion\n\nThe critique is complete when the report has a verdict, every blocking finding has a\nrecorded disposition, the fixed-input fingerprint still matches, and deferred checks are\nvisible. `\u002Fvalidate` remains the one deterministic full-gate owner. Critique does not run\nthat gate again.\n\n## Red flags\n\n- Review input changes while reviewers are running.\n- Several generic reviewers inspect the same diff.\n- A reviewer repeats the full suite without a named evidence gap.\n- Findings exist only in chat or a transcript.\n- A repair changes the fingerprint but old evidence is called current.\n",{"name":5,"description":24,"disable-model-invocation":25},"Use when a completed multi-file change needs decision-aware independent review, especially for security, trust boundaries, architecture, or cross-cutting behavior. Manual only. NOT for routine focused checks, deterministic validation, or work that is still changing.\n",true,"main","85a41de587b98bb440cccf78f081a6bee67fe90e","cultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fsession-critique","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri","2026-11-15 04:06:30",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":25},[34,37,40],{"tool":35,"command":36},"npx","npx skills add SamyakJhaveri\u002Floam --skill session-critique",{"tool":38,"command":39},"bunx","bunx skills add SamyakJhaveri\u002Floam --skill session-critique",{"tool":41,"command":42},"pnpm","pnpm dlx skills add SamyakJhaveri\u002Floam --skill session-critique","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fsession-critique\u002FSKILL.md",[],[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},"01M7AHGVPTGK3JGQ9XYG5XJ6PR","verify-loam","Prove a Loam change in a real rendered project: copier-render this checkout, then drive headless and interactive Claude Code sessions, stubbed Codex runs and copier updates in the render and capture hook, memory, deny-rule, update and check evidence. Use before shipping any seed, hook, settings or copier.yml change.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.claude\u002Fskills\u002Fverify-loam\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},"01M7AHGEDXX7GWJ32S9BZAEWAJ","hypothesis-tree","Persistent hypothesis tree for multi-step, multi-session investigations. Use when a \"why does X fail\" question branches into sub-hypotheses that must survive across sessions, or when falsifiable claims need tracking with dated, linked evidence. Maintains one markdown file with add, update, review, and prune subcommands, each gated on verifying the cited evidence file exists and supports the claim. NOT for a single-session bug hunt, a one-command question, or general note-taking.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fhypothesis-tree\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},"01M7AHGADA1CX9M0B0QSFJYGW5","fable-prompting","Which Claude Fable 5.2 guide sections you can act on from a session, and which Claude Code already injects. Use before writing a Fable session prompt or brief.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Ffable-prompting\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},"01M7AHG7AGBSQ6HH04C70TSM8H","catchup","Read-only session bootstrap briefing of git state, commits, handoff, tasks and red flags. Use when resuming work, starting a fresh session, or unsure of project state.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fcatchup\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},"01M7AHG52XX2N7AT7JNHS6MN1S","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwriting-for-agents\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},"01M7AHG00SXGAGJA7C6XA193J6","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwizard\u002FSKILL.md",[],[]]