[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71QPMJMSDGNCTJC802D5B8V":3,"skill-same:01M71QPMJMSDGNCTJC802D5B8V":84},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M71QPMJMSDGNCTJC802D5B8V","method-sprint",null,"Opens, closes, and reports scoped analysis sprints with a named reviewer, planned SAP outputs, and data-lock checks. Use when the user opens, closes, or checks a sprint.","sajor2000\u002Fmethodsmith","sajor2000","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F126191042?v=4","01M71QG4M3561SH49E3S7J3GKT","JC Rojas ","01M71QG4N56X2P61YTJSRP95VD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"sprint","method sprint","name","with","use","outputs","scoped","sap","sprints","data","start","status","jcr","close","reports","lock","reviewer","analysis","when","scope","2026-11-10 13:02:02",false,"---\nname: method-sprint\ndescription: \"Opens, closes, and reports scoped analysis sprints with a named reviewer, planned SAP outputs, and data-lock checks. Use when the user opens, closes, or checks a sprint.\"\nargument-hint: \"\u003Cstart|close|status>, optional name and reviewer, e.g. start sprint-01 reviewer=jcr scope=SAP-5.1,SAP-5.2\"\n---\n\n# Sprint Cadence with Human Audit Gates\n\n\n## Skill Value\n\n- **Problem it solves:** Analysis work becomes unbounded without explicit scope, reviewer, planned outputs, and closure checks.\n- **Use when:** The user wants an auditable analysis sprint, human signoff, scoped SAP execution, or sprint closeout.\n- **Output:** Sprint log\u002Fstatus with scope, reviewer, planned-vs-actual outputs, and closeout findings.\n- **Ask only if:** Only when sprint name, reviewer, scope, or planned output rows are missing.\n- **Do not do:** Do not open a sprint without entry criteria or close one without checking planned outputs.\n- **Interaction:** Check repo\u002Fconfig\u002Fchat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.\n\nWraps `method-work` in bounded sprints with explicit entry\u002Fexit criteria and human reviewer sign-off. The frictionless feel of `method-work` is preserved; the sprint adds structure around it so analyses can be audited unit-by-unit.\n\n## When this skill activates\n\n- Before starting analysis work that needs human sign-off (most academic \u002F regulated work)\n- After `method-plan` SAP and `method-sap-workbook` are done and the SAP is locked\n- Manual: `method-sprint start sprint-02 reviewer=jcr scope=SAP-5.1,SAP-5.2`\n- Closing a sprint: `method-sprint close`\n\n## Prerequisites\n\n- A locked SAP exists (`analysis\u002Fsap.md` with `sap_version` frontmatter)\n- `analysis\u002Fsap-tables\u002F02-outputs.csv` exists (from `method-sap-workbook`)\n- A locked data wave exists in `analysis\u002Fdata-waves.md` (and `.methodsmith\u002Fdata-state.yaml` when that optional state file is used)\n\n## Core workflow\n\n### `method-sprint start \u003Cname>`\n\n1. Check that no other sprint is currently `open` in `analysis\u002Fsprint-log.yaml` (the canonical top-level audit-trail file written by `scripts\u002Fsprint.py`). Refuse to open a second concurrent sprint -- one in flight at a time. Use `method-sprint close` first.\n\n2. Resolve the scope. The user passes `scope=SAP-5.1,SAP-5.2` (SAP section ids) or `scope=table:T1,T2` (table ids from sap-tables). Resolve to a list of rows from `02-outputs.csv` whose `Script Section` or legacy `analysis_section` matches. Ignore section banner rows where only the first cell is populated.\n\n3. Resolve the reviewer. The user passes `reviewer=\u003Cname>` or, if absent, prompt for one. The named human is the person who will sign the sprint summary. Their name lands in `sprint-log.yaml` -- this is the audit-trail anchor.\n\n4. Check entry criteria:\n   - Prior sprint (if any) has status `signed_off`\n   - Data wave is `locked`\n   - SAP `sap_version` is committed (no uncommitted SAP edits)\n   - Stack profile is set\n\n   If any fails, refuse to open the sprint and report what's blocking.\n\n5. Append the new sprint entry to `analysis\u002Fsprint-log.yaml` (top-level, one file per project — every sprint becomes a list item under `sprints:`). Set `SKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";`, then run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" open \u003Cname> --scope \u003CSAP-section-csv> --reviewer \u003Creviewer>`; it refuses if a sprint is open or the name exists, writes `name`, `status: open`, `scope`, `reviewer`, `opened_at`, `commit_open`, and empty `outputs_planned`\u002F`outputs_actual`, and prints `__CE_SPRINT__ action=open ...`. Then fill `outputs_planned` from step 2 and add `entry_criteria` to that entry:\n\n```yaml\nsprints:\n  - name: sprint-02\n    status: open\n    scope: [SAP-5.1, SAP-5.2]\n    reviewer: jcr\n    opened_at: 2025-04-28T09:00:00Z\n    commit_open: \u003Csha>\n    outputs_planned:\n      - { id: T3, output_file: table-mortality-by-arm.csv, subfolder: tables\u002F, sap_section: SAP-5.1 }\n      - { id: F2, output_file: km-curve-overall.png, subfolder: figures\u002F, sap_section: SAP-5.2 }\n    outputs_actual: []\n    entry_criteria:\n      sap_version: 2\n      data_wave_id: wave_2025_03_15\n      prior_sprint: sprint-01 (signed off 2025-04-20)\n```\n\n6. Print a one-line summary and hand off to `method-work` with the planned-outputs list as the task seed. The user works inside the sprint as they would inside `method-work` normally; the sprint just bounds what's in scope.\n\n### `method-sprint close`\n\nStatus flow in `analysis\u002Fsprint-log.yaml`: `open` -> `pending_review` (script, awaiting audit) -> `closed_pending_signoff` (audit passed) -> `signed_off` (human reviewer). A failing audit returns the sprint to `open`.\n\n1. Set `SKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";` (the shell starts in the project root, not the skill directory), then run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" close \u003Cname>` (`\u003Cname>` defaults to the currently open sprint). The script flips status to `pending_review`, captures `closed_at` and `commit_close`, and prints a human-readable `__CE_SPRINT__ action=close ...` line, a machine-parseable dispatch hint, and a `next:` reminder:\n\n   ```\n   __CE_SPRINT_AUDIT_DISPATCH__ sprint=\u003Cname> reviewer=method-sprint-audit-reviewer human_reviewer=\u003Cname> scope=\u003Ccsv> commit_open=\u003Csha> commit_close=\u003Csha>\n   ```\n\n2. Parse the `__CE_SPRINT_AUDIT_DISPATCH__` line into its key=value fields and dispatch `method-sprint-audit-reviewer` through the platform's subagent primitive (`Agent`\u002F`Task` in Claude Code, `spawn_agent` in Codex, or `subagent` in Pi). Omit permission-mode overrides. If no subagent primitive exists, run the audit sequentially in the current agent. Use this prompt contract:\n\n   ```\n   Agent: method-sprint-audit-reviewer\n   Description: Audit sprint \u003Cname>\n   Prompt:\n       Sprint name:   \u003Cname>\n       Human reviewer: \u003Chuman_reviewer>\n       Scope (SAP sections in this sprint): \u003Cscope>\n       Commit range: \u003Ccommit_open>..\u003Ccommit_close>\n\n       Verify, in order:\n       1. Every row in analysis\u002Fsap-tables\u002F02-outputs.csv whose\n          `Script Section` or legacy `analysis_section` is in \u003Cscope> has a\n          corresponding artifact at the expected `Output File (SITE_ID_ prefix\n          added automatically)` or legacy `output_file` under the expected\n          `Subfolder` or legacy `subfolder`.\n       2. No files outside \u003Cscope>'s SAP-section ownership were edited\n          between \u003Ccommit_open> and \u003Ccommit_close>\n          (use `git diff --name-only \u003Ccommit_open> \u003Ccommit_close>`).\n       3. Outputs produced that are NOT in 02-outputs.csv: list them\n          (warn-level, not blocking).\n       4. All planned Quarto\u002Fnotebook chunks in scope ran without errors\n          (look for `Error in ...` in any *.log captured during the sprint).\n       5. Reproducibility re-check: hash each declared output and compare to\n          the hash captured at last execution if available.\n\n       Return JSON:\n         {\n           \"verdict\": \"pass\" | \"fail\",\n           \"p0_count\": \u003Cint>,\n           \"p1_count\": \u003Cint>,\n           \"p2_count\": \u003Cint>,\n           \"blocking_findings\": [ {file, line, severity, title}, ... ],\n           \"advisory_findings\": [ ... ]\n         }\n   ```\n\n3. On a passing audit verdict, write the sprint summary to `analysis\u002Fsprints\u002F\u003Cname>\u002Fsummary.md`. On a failing verdict, flip the sprint back to `status: open` so the user can address findings; do not write a summary.\n\n```\n# Sprint \u003Cname> Summary\n\nReviewer: \u003Cname>\nOpened: ... Closed: ...\nScope: SAP-5.1, SAP-5.2\n\n## Outputs produced\n| ID | File | Hash | Status |\n| T3 | tables\u002Ftable-mortality-by-arm.csv | abc123 | ok |\n| F2 | figures\u002Fkm-curve-overall.png      | def456 | ok |\n\n## Out-of-scope edits detected\nNone\n\n## Audit reviewer findings\n- 0 P0, 1 P1 (minor table-1 column-order drift), 0 P2\n\n## Sign-off\nReviewer (\u003Cname>): ☐\nDate: ____________\n```\n\n4. Update `sprint-log.yaml`:\n\n```yaml\nstatus: closed_pending_signoff\naudit_reviewer_findings: { P0: 0, P1: 1, P2: 0 }\n```\n\n5. If the project uses publication review packs, append or update an entry in the `method-signoff` signoff ledger that points to `analysis\u002Fsprints\u002F\u003Cname>\u002Fsummary.md`, the audit verdict, and the named reviewer. Do not mark it approved until the human reviewer has signed.\n\n6. Print `__CE_SPRINT_CLOSED__ name=\u003Cname> findings_p0=\u003Cn> awaiting_signoff=true` and prompt the user to share the summary with the reviewer. For manuscript-facing projects, suggest `method-signoff` to build the PI-facing package and validate the signoff ledger.\n\n7. After the named reviewer signs off, record it with `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" signoff \u003Cname> --by \u003Creviewer>` (same `SKILL_DIR` anchor as step 1). The script refuses unless the sprint is `closed_pending_signoff` and `\u003Creviewer>` is the sprint's named reviewer, then writes `status: signed_off`, `signed_off_by`, and `signed_off_at`. Never hand-edit these fields; confirm the `__CE_SPRINT__ action=signoff` line with the user.\n\n### `method-sprint status`\n\nWith `SKILL_DIR` set as above, run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" status [--name \u003Cname>]` and print the current sprint state plus the audit-reviewer findings if closed-pending. Useful for \"where am I?\".\n\n## What this skill does NOT do\n\n- Does not run analysis itself (that's `method-work`)\n- Does not pick the scope -- the user picks SAP sections\n- Does not bypass `method-review` -- code review still runs as normal during the sprint; the sprint audit is at close time only\n- Does not enforce sprint duration -- a sprint can be 1 hour or 3 weeks; what matters is the bounded scope and the named reviewer\n\n## References\n\n@.\u002Freferences\u002Fsprint-log-schema.yaml\n\n@.\u002Freferences\u002Faudit-checklist.md\n","# Sprint Cadence with Human Audit Gates\n\n\n## Skill Value\n\n- **Problem it solves:** Analysis work becomes unbounded without explicit scope, reviewer, planned outputs, and closure checks.\n- **Use when:** The user wants an auditable analysis sprint, human signoff, scoped SAP execution, or sprint closeout.\n- **Output:** Sprint log\u002Fstatus with scope, reviewer, planned-vs-actual outputs, and closeout findings.\n- **Ask only if:** Only when sprint name, reviewer, scope, or planned output rows are missing.\n- **Do not do:** Do not open a sprint without entry criteria or close one without checking planned outputs.\n- **Interaction:** Check repo\u002Fconfig\u002Fchat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.\n\nWraps `method-work` in bounded sprints with explicit entry\u002Fexit criteria and human reviewer sign-off. The frictionless feel of `method-work` is preserved; the sprint adds structure around it so analyses can be audited unit-by-unit.\n\n## When this skill activates\n\n- Before starting analysis work that needs human sign-off (most academic \u002F regulated work)\n- After `method-plan` SAP and `method-sap-workbook` are done and the SAP is locked\n- Manual: `method-sprint start sprint-02 reviewer=jcr scope=SAP-5.1,SAP-5.2`\n- Closing a sprint: `method-sprint close`\n\n## Prerequisites\n\n- A locked SAP exists (`analysis\u002Fsap.md` with `sap_version` frontmatter)\n- `analysis\u002Fsap-tables\u002F02-outputs.csv` exists (from `method-sap-workbook`)\n- A locked data wave exists in `analysis\u002Fdata-waves.md` (and `.methodsmith\u002Fdata-state.yaml` when that optional state file is used)\n\n## Core workflow\n\n### `method-sprint start \u003Cname>`\n\n1. Check that no other sprint is currently `open` in `analysis\u002Fsprint-log.yaml` (the canonical top-level audit-trail file written by `scripts\u002Fsprint.py`). Refuse to open a second concurrent sprint -- one in flight at a time. Use `method-sprint close` first.\n\n2. Resolve the scope. The user passes `scope=SAP-5.1,SAP-5.2` (SAP section ids) or `scope=table:T1,T2` (table ids from sap-tables). Resolve to a list of rows from `02-outputs.csv` whose `Script Section` or legacy `analysis_section` matches. Ignore section banner rows where only the first cell is populated.\n\n3. Resolve the reviewer. The user passes `reviewer=\u003Cname>` or, if absent, prompt for one. The named human is the person who will sign the sprint summary. Their name lands in `sprint-log.yaml` -- this is the audit-trail anchor.\n\n4. Check entry criteria:\n   - Prior sprint (if any) has status `signed_off`\n   - Data wave is `locked`\n   - SAP `sap_version` is committed (no uncommitted SAP edits)\n   - Stack profile is set\n\n   If any fails, refuse to open the sprint and report what's blocking.\n\n5. Append the new sprint entry to `analysis\u002Fsprint-log.yaml` (top-level, one file per project — every sprint becomes a list item under `sprints:`). Set `SKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";`, then run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" open \u003Cname> --scope \u003CSAP-section-csv> --reviewer \u003Creviewer>`; it refuses if a sprint is open or the name exists, writes `name`, `status: open`, `scope`, `reviewer`, `opened_at`, `commit_open`, and empty `outputs_planned`\u002F`outputs_actual`, and prints `__CE_SPRINT__ action=open ...`. Then fill `outputs_planned` from step 2 and add `entry_criteria` to that entry:\n\n```yaml\nsprints:\n  - name: sprint-02\n    status: open\n    scope: [SAP-5.1, SAP-5.2]\n    reviewer: jcr\n    opened_at: 2025-04-28T09:00:00Z\n    commit_open: \u003Csha>\n    outputs_planned:\n      - { id: T3, output_file: table-mortality-by-arm.csv, subfolder: tables\u002F, sap_section: SAP-5.1 }\n      - { id: F2, output_file: km-curve-overall.png, subfolder: figures\u002F, sap_section: SAP-5.2 }\n    outputs_actual: []\n    entry_criteria:\n      sap_version: 2\n      data_wave_id: wave_2025_03_15\n      prior_sprint: sprint-01 (signed off 2025-04-20)\n```\n\n6. Print a one-line summary and hand off to `method-work` with the planned-outputs list as the task seed. The user works inside the sprint as they would inside `method-work` normally; the sprint just bounds what's in scope.\n\n### `method-sprint close`\n\nStatus flow in `analysis\u002Fsprint-log.yaml`: `open` -> `pending_review` (script, awaiting audit) -> `closed_pending_signoff` (audit passed) -> `signed_off` (human reviewer). A failing audit returns the sprint to `open`.\n\n1. Set `SKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";` (the shell starts in the project root, not the skill directory), then run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" close \u003Cname>` (`\u003Cname>` defaults to the currently open sprint). The script flips status to `pending_review`, captures `closed_at` and `commit_close`, and prints a human-readable `__CE_SPRINT__ action=close ...` line, a machine-parseable dispatch hint, and a `next:` reminder:\n\n   ```\n   __CE_SPRINT_AUDIT_DISPATCH__ sprint=\u003Cname> reviewer=method-sprint-audit-reviewer human_reviewer=\u003Cname> scope=\u003Ccsv> commit_open=\u003Csha> commit_close=\u003Csha>\n   ```\n\n2. Parse the `__CE_SPRINT_AUDIT_DISPATCH__` line into its key=value fields and dispatch `method-sprint-audit-reviewer` through the platform's subagent primitive (`Agent`\u002F`Task` in Claude Code, `spawn_agent` in Codex, or `subagent` in Pi). Omit permission-mode overrides. If no subagent primitive exists, run the audit sequentially in the current agent. Use this prompt contract:\n\n   ```\n   Agent: method-sprint-audit-reviewer\n   Description: Audit sprint \u003Cname>\n   Prompt:\n       Sprint name:   \u003Cname>\n       Human reviewer: \u003Chuman_reviewer>\n       Scope (SAP sections in this sprint): \u003Cscope>\n       Commit range: \u003Ccommit_open>..\u003Ccommit_close>\n\n       Verify, in order:\n       1. Every row in analysis\u002Fsap-tables\u002F02-outputs.csv whose\n          `Script Section` or legacy `analysis_section` is in \u003Cscope> has a\n          corresponding artifact at the expected `Output File (SITE_ID_ prefix\n          added automatically)` or legacy `output_file` under the expected\n          `Subfolder` or legacy `subfolder`.\n       2. No files outside \u003Cscope>'s SAP-section ownership were edited\n          between \u003Ccommit_open> and \u003Ccommit_close>\n          (use `git diff --name-only \u003Ccommit_open> \u003Ccommit_close>`).\n       3. Outputs produced that are NOT in 02-outputs.csv: list them\n          (warn-level, not blocking).\n       4. All planned Quarto\u002Fnotebook chunks in scope ran without errors\n          (look for `Error in ...` in any *.log captured during the sprint).\n       5. Reproducibility re-check: hash each declared output and compare to\n          the hash captured at last execution if available.\n\n       Return JSON:\n         {\n           \"verdict\": \"pass\" | \"fail\",\n           \"p0_count\": \u003Cint>,\n           \"p1_count\": \u003Cint>,\n           \"p2_count\": \u003Cint>,\n           \"blocking_findings\": [ {file, line, severity, title}, ... ],\n           \"advisory_findings\": [ ... ]\n         }\n   ```\n\n3. On a passing audit verdict, write the sprint summary to `analysis\u002Fsprints\u002F\u003Cname>\u002Fsummary.md`. On a failing verdict, flip the sprint back to `status: open` so the user can address findings; do not write a summary.\n\n```\n# Sprint \u003Cname> Summary\n\nReviewer: \u003Cname>\nOpened: ... Closed: ...\nScope: SAP-5.1, SAP-5.2\n\n## Outputs produced\n| ID | File | Hash | Status |\n| T3 | tables\u002Ftable-mortality-by-arm.csv | abc123 | ok |\n| F2 | figures\u002Fkm-curve-overall.png      | def456 | ok |\n\n## Out-of-scope edits detected\nNone\n\n## Audit reviewer findings\n- 0 P0, 1 P1 (minor table-1 column-order drift), 0 P2\n\n## Sign-off\nReviewer (\u003Cname>): ☐\nDate: ____________\n```\n\n4. Update `sprint-log.yaml`:\n\n```yaml\nstatus: closed_pending_signoff\naudit_reviewer_findings: { P0: 0, P1: 1, P2: 0 }\n```\n\n5. If the project uses publication review packs, append or update an entry in the `method-signoff` signoff ledger that points to `analysis\u002Fsprints\u002F\u003Cname>\u002Fsummary.md`, the audit verdict, and the named reviewer. Do not mark it approved until the human reviewer has signed.\n\n6. Print `__CE_SPRINT_CLOSED__ name=\u003Cname> findings_p0=\u003Cn> awaiting_signoff=true` and prompt the user to share the summary with the reviewer. For manuscript-facing projects, suggest `method-signoff` to build the PI-facing package and validate the signoff ledger.\n\n7. After the named reviewer signs off, record it with `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" signoff \u003Cname> --by \u003Creviewer>` (same `SKILL_DIR` anchor as step 1). The script refuses unless the sprint is `closed_pending_signoff` and `\u003Creviewer>` is the sprint's named reviewer, then writes `status: signed_off`, `signed_off_by`, and `signed_off_at`. Never hand-edit these fields; confirm the `__CE_SPRINT__ action=signoff` line with the user.\n\n### `method-sprint status`\n\nWith `SKILL_DIR` set as above, run `python3 \"$SKILL_DIR\u002Fscripts\u002Fsprint.py\" status [--name \u003Cname>]` and print the current sprint state plus the audit-reviewer findings if closed-pending. Useful for \"where am I?\".\n\n## What this skill does NOT do\n\n- Does not run analysis itself (that's `method-work`)\n- Does not pick the scope -- the user picks SAP sections\n- Does not bypass `method-review` -- code review still runs as normal during the sprint; the sprint audit is at close time only\n- Does not enforce sprint duration -- a sprint can be 1 hour or 3 weeks; what matters is the bounded scope and the named reviewer\n\n## References\n\n@.\u002Freferences\u002Fsprint-log-schema.yaml\n\n@.\u002Freferences\u002Faudit-checklist.md\n",{"name":5,"description":7,"argument-hint":44},"\u003Cstart|close|status>, optional name and reviewer, e.g. start sprint-01 reviewer=jcr scope=SAP-5.1,SAP-5.2","main","893bccb980e4dce1345919e9f675f5a9dcbed364","plugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint",0,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith","https:\u002F\u002Fsajor2000.github.io\u002Fmethodsmith\u002F","https:\u002F\u002Fgithub.com\u002Fsajor2000","Critical care physician-scientist at Rush University. @Common-Longitudinal-ICU-data-Format contributor building open ICU data tools & clinical AI","2026-11-01 01:56:01",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add sajor2000\u002Fmethodsmith --skill method-sprint",{"tool":60,"command":61},"bunx","bunx skills add sajor2000\u002Fmethodsmith --skill method-sprint",{"tool":63,"command":64},"pnpm","pnpm dlx skills add sajor2000\u002Fmethodsmith --skill method-sprint","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint\u002FSKILL.md",true,[68,74,78],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Faudit-checklist.md","REFERENCE","参考文档",2514,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint\u002Freferences\u002Faudit-checklist.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fsprint-log-schema.yaml",2074,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint\u002Freferences\u002Fsprint-log-schema.yaml",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fsprint.py","SCRIPT","脚本",7797,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-sprint\u002Fscripts\u002Fsprint.py",[85,101,114,126,135,144],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":96,"publishedAt":39},"01M71QQY0KE1184AF58EC1J5C1","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[97,98,99,100],"one","skill one","sample","sample skill",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":39},"01M71QQW3PNK9AYB5HBMAPM72J","disabled-skill","A skill with model invocation disabled","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fdisabled-skill\u002FSKILL.md",[107],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[109,110,111,22,112,113],"disabled skill","a skill","with model","true","model",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":39},"01M71QQSY02X7DNZQRAGJ6YFGY","claude-only-skill","A skill restricted to Claude Code only","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fclaude-only-skill\u002FSKILL.md",[120],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[122,123,124,110,125],"claude only","claude only skill","only","code",{"skillNo":127,"name":128,"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":129,"categories":130,"keywords":132,"publishedAt":39},"01M71QQRPZ76X623V5P7T1E3DD","default-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[131],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[133,134],"default","default skill",{"skillNo":136,"name":137,"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":138,"categories":139,"keywords":141,"publishedAt":39},"01M71QQQG3FF2HFQHVH8VHA08R","custom-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[140],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[142,143],"custom skill","custom",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":39},"01M71QQMBNC76141GHXBSMENSH","method-write","Drafts, revises, and audits evidence-bound manuscripts, sections, abstracts, and reviewer responses with claim provenance. Use when scientific prose must be written or revised (entry point).","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-write\u002FSKILL.md",[],[151,152,153,154,155,156,23,37,157,35,22,158,159,160],"write","method write","point","evidence","entry","claim","provenance","scientific","prose","drafts"]