[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D7735DTC7ASQ238RDPWSCZ":3,"skill-same:01M6D7735DTC7ASQ238RDPWSCZ":201},{"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":23,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6D7735DTC7ASQ238RDPWSCZ","customer-feedback",null,"Ingest and synthesize customer feedback — categorize findings against ICP and journey map, maintain a running log","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbusiness-research\u002Fcodex\u002Fcustomer-feedback\u002Farchive\u002Fv0.1\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"customer","feedback","customer feedback","research","file","text","v0","log","ingest","categorize","maintain","journey","map","synthesize","empty","icp","2026-11-10 10:12:30",false,"---\nname: customer-feedback\ndescription: Ingest and synthesize customer feedback — categorize findings against ICP and journey map, maintain a running log\ntype: research\nversion: v0.1\nargument-hint: \"[file path, pasted text, or empty to be prompted]\"\n---\n\n## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `$pack install \u003Cpack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.\n\n# Customer Feedback — Ingest & Synthesize\n\nInvoke as `$customer-feedback`.\n\n## Report-First Approval Gate\n\nDefault to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research\u002Freport writes.\n\nWhen stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.\n\nAppend-only skill that ingests customer feedback, categorizes findings against ICP and journey map, and maintains a running synthesis. Each run adds a session; the synthesis section regenerates across all sessions.\n\n## Soft Prerequisites\n\n- Read `research\u002Ficp.md` (or `research\u002F{app}\u002Ficp.md` in monorepo mode) if it exists — grounds categorization in ICP segments and pain points.\n- Read `research\u002Fjourney-map.md` (or `research\u002F{app}\u002Fjourney-map.md` in monorepo mode) if it exists — tags findings to journey stages.\n\nThese are not required. The skill works without them but categorization will be less precise.\n\n## Process\n\n### 0. App Scope Resolution (Monorepo Support)\n\nBefore checking prerequisites, determine the app scope:\n\n1. If `$ARGUMENTS` specifies an app name matching a subdirectory of `research\u002F`, use it.\n2. If `research\u002F` contains subdirectories (excluding files), list them and ask the user which app to target. If the session is already in Plan mode and there are 2-3 concrete choices, prefer `request_user_input`; otherwise ask in plain text. If only one subdirectory exists, use it automatically.\n3. If no subdirectories exist, proceed with flat structure (single-product mode).\n\nWhen app scope `{app}` is active:\n- Read\u002Fwrite research from `research\u002F{app}\u002F` instead of `research\u002F`\n- Read\u002Fwrite specs from `specs\u002F{app}\u002F` instead of `specs\u002F`\n- Also read `research\u002Ficp.md` (cross-app overview) for broader context\n\n### 1. Load Context\n\n- Read `research\u002Ficp.md` (or `research\u002F{app}\u002Ficp.md`) if it exists — extract ICP segments, user profiles, pain points, value props\n- Read `research\u002Fjourney-map.md` (or `research\u002F{app}\u002Fjourney-map.md`) if it exists — extract journey stages, use cases, critical moments\n- Read `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`) if it exists — load all previous sessions for synthesis context\n\n### 2. Ingest Feedback\n\nCheck `$ARGUMENTS`:\n- **File path provided**: Read the file and use its contents as the feedback input\n- **Text provided**: Use the argument text directly as feedback\n- **Empty**: Ask the user to paste or describe the feedback. If the session is already in Plan mode and there are 2-3 concrete input-source choices, prefer `request_user_input`; otherwise ask in plain text.\n\nAccept any format: interview notes, support tickets, survey responses, NPS comments, user testing observations, sales call notes, social media mentions, app store reviews.\n\n### 3. Categorize Findings\n\nFor each distinct finding in the feedback:\n\n1. **Classification**: One of:\n   - **Confirmed** — validates an existing ICP assumption, pain point, or journey step\n   - **Wrong** — contradicts an ICP assumption, pain point, or mapped journey\n   - **New** — reveals something not captured in ICP or journey map\n\n2. **ICP Tag** (when `research\u002Ficp.md` exists): Which ICP section does this relate to? (pain point, value prop, user profile, trigger event, etc.)\n\n3. **Journey Stage** (when `research\u002Fjourney-map.md` exists): Which journey stage does this touch? (discovery, evaluation, onboarding, aha moment, retention, etc.)\n\n4. **Severity**: High \u002F Medium \u002F Low — based on how many users it affects and how strongly\n\n5. **Quote or Evidence**: The specific words or behavior that support this finding\n\n### 4. Present & Validate\n\nPresent the categorized findings to the user. If the session is already in Plan mode and there are 2-3 concrete validation choices, prefer `request_user_input`; otherwise ask in plain text:\n\n- Show each finding with its classification, tags, and evidence\n- Ask: \"Does this categorization look right? Any findings I've miscategorized or missed?\"\n- If the user corrects anything, update before writing\n\n### 5. Check Staleness Triggers\n\nCount the number of **Wrong** and **New** findings across ALL sessions (including previous ones):\n\n- If 3+ **Wrong** findings relate to ICP assumptions: recommend re-running `$icp`\n- If 3+ **Wrong** findings relate to journey stages: recommend re-running `$journey-map`\n- If 3+ **New** findings suggest an unserved segment: recommend re-running `$icp`\n\nDisplay these recommendations after the categorized findings.\n\n### 6. Populate Next Steps\n\nBefore writing, check which files exist and synthesis results to populate the `## Next Steps` section contextually. Include a **Recommended** item (the single highest-impact next step given current project state) with a one-line reason, followed by **Other options** (2–4 alternatives). Use this format in the output:\n\n### Next Steps\n\n**Recommended:** [recommended skill] — [one-line reason why this is the highest-impact next action given current state]\n\nOther options:\n- `$skill` — [description]\n- ...\n\n**Recommendation priority** (first applicable becomes the recommendation):\n1. IF downstream impact is **Major**: recommend `$reconcile-research` — [N] conflicts found in downstream docs need resolution before other work\n2. IF staleness alert for ICP: recommend `$icp` — feedback has invalidated key ICP assumptions that other research depends on\n3. IF staleness alert for journey map: recommend `$journey-map` — real user behavior differs from mapped experience\n4. IF 3+ New findings: recommend `$brainstorm` — newly revealed customer needs deserve solution exploration\n5. IF no staleness alerts and no major findings: recommend `$research-roadmap` — check overall project status for the next priority\n\n**Other options** (include all applicable items not chosen as recommended):\n- IF staleness alert for ICP: `$icp` — Re-run discovery — feedback has invalidated key assumptions\n- IF staleness alert for journey map: `$journey-map` — Re-map journeys — real behavior differs from mapped experience\n- IF 3+ New findings: `$brainstorm` — Generate ideas for newly revealed customer needs\n- IF New findings relate to a gap: `$ux-variations [topic]` — Explore UX solutions for the most impactful finding\n- IF no staleness alerts: `$research-roadmap` — Check overall project status\n- IF feedback came from experiment results: `$assumption-tracker` — Update assumption validation status with experiment findings\n- IF 3+ research docs exist and no `research\u002Fassumption-tracker.md`: `$assumption-tracker` — Build the assumptions register to track what feedback is validating\n\n**Impact-aware adjustments:**\n- IF downstream impact is **Minor**: annotate relevant skill suggestions with \"(stale — [brief description])\"\n- If downstream impact has not been classified yet, run the downstream impact check against the proposed output before selecting the final recommendation. Do not emit a Minor\u002FMajor impact recommendation speculatively.\n\n### 7. Write Output\n\nOnly after the user validates, write to `research\u002Fcustomer-feedback.md`:\n\n**If the file doesn't exist**: Create it with the structure below.\n**If the file exists**: Append the new session section, then regenerate the `## Synthesis` section at the top.\n\n### 8. Downstream Impact Check\n\nAfter writing, check for downstream research documents that may be affected by what was just decided. Only check documents that exist on disk.\n\n**Downstream documents to check** (use `{app}\u002F` prefix when app scope is active):\n- `research\u002Fgtm.md`\n- `research\u002Fmonetization.md`\n\nFor each existing downstream document:\n1. Read it — focus on `> Based on:` header, `## Summary`, and sections that reference concepts this skill just defined or changed\n2. Identify **specific conflicts**: claims, assumptions, or references that contradict what was just decided. Examples:\n   - Customer language or pain point framing in GTM messaging that feedback has invalidated\n   - Pricing assumptions in monetization anchored to customer willingness-to-pay signals that have shifted\n   - Channel strategy built on customer behavior patterns that new feedback contradicts\n3. Note each conflict: downstream file, section, the stale claim (quote it), and what it should now say\n\n**Classify the impact**:\n- **None**: No downstream documents exist, or no conflicts found. Skip display entirely.\n- **Minor** (1–2 small conflicts): Display conflicts to user inline.\n- **Major** (3+ conflicts OR a foundational assumption changed — e.g., primary pain point invalidated, willingness-to-pay signals contradicted, key customer behavior pattern disproved): Display conflicts and strongly recommend `$reconcile-research`.\n\nDisplay to the user after showing the written file confirmation. This should be quick — one read per downstream doc, scan for conflicts against key decisions. Not a deep reconciliation.\n\n## Output\n\n### `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`)\n\n```markdown\n# Customer Feedback\n\n> Last updated: [current date]\n> Sessions: [total count]\n\n## Synthesis\n\n[Regenerated each run. Summarizes patterns across ALL sessions:]\n\n### Confirmed Assumptions\n[ICP and journey assumptions that feedback consistently validates]\n\n### Invalidated Assumptions\n[ICP and journey assumptions that feedback contradicts — with evidence count]\n\n### New Discoveries\n[Findings not captured in any existing research — potential ICP updates or new journey stages]\n\n### Staleness Alerts\n[If 3+ Wrong\u002FNew findings accumulated, list which research docs should be re-run and why]\n\n\u003C!-- Only include the Downstream Impact section when impact is Minor or Major. Omit entirely for None. -->\n### Downstream Impact\n\n> Checked: [list of downstream docs checked]\n> Impact: Minor | Major\n\n#### Conflicts Found\n\n1. **research\u002F[file].md** — [Section Name]\n   - **Stale**: \"[exact quote from downstream doc]\"\n   - **Now**: [what this skill's output says instead]\n\n[For Major only:]\n> **Recommended action**: Run `$reconcile-research` to audit and fix all affected downstream documents.\n\n### Next Steps\n\n**Recommended:** `$skill` — [one-line reason]\n\nOther options:\n- [conditional items from step 6 — only include items whose conditions are met]\n\n---\n\n## Feedback Session: [date]\n\n> Source: [file path, \"pasted text\", or \"interview\"]\n> ICP context: [yes\u002Fno — whether research\u002Ficp.md was loaded]\n> Journey context: [yes\u002Fno — whether research\u002Fjourney-map.md was loaded]\n\n### Findings\n\n| # | Finding | Classification | ICP Tag | Journey Stage | Severity |\n|---|---------|---------------|---------|---------------|----------|\n| 1 | [finding] | Confirmed\u002FWrong\u002FNew | [tag] | [stage] | H\u002FM\u002FL |\n\n### Details\n\n#### Finding 1: [title]\n**Classification**: [Confirmed\u002FWrong\u002FNew]\n**Evidence**: \"[quote or observation]\"\n**ICP Tag**: [which ICP section]\n**Journey Stage**: [which stage]\n**Severity**: [High\u002FMedium\u002FLow]\n**Implication**: [what this means for the product]\n\n[Repeat for each finding]\n\n---\n\n[Previous sessions remain below, newest first]\n```\n\nCreate the `research\u002F` directory if it doesn't exist.\n\n## Task Classification\n\nWhen this skill produces follow-up work, file it by execution semantics:\n\n- Immediately actionable implementation or documentation work goes in `tasks\u002Ftodo.md`.\n- Human-only external actions tied to automated steps go in `tasks\u002Fmanual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI\u002FAPI work stay in `tasks\u002Ftodo.md`.\n- One-time condition-gated records, baselines, or future measurements go in `tasks\u002Frecord-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.\n- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks\u002Frecurring-todo.md` with cadence, owner\u002Fagent, next due, evidence path, and escalation conditions.\n- Do not put non-blocking records or recurring obligations in `tasks\u002Ftodo.md` unless they have been explicitly promoted into current execution work.\n\n## Constraints\n\n- **Append-only.** Never delete or overwrite previous sessions in `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`). Only the `## Synthesis` section at the top is regenerated.\n- **Present before writing.** Never write until the user validates the categorization.\n- **Tag to existing research.** When ICP and journey map exist, every finding must be tagged. When they don't exist, skip tagging but note \"no ICP\u002Fjourney context\" in the session header.\n- **Count across sessions.** Staleness triggers are based on cumulative findings, not just the current session.\n- **Accept any format.** The skill should handle messy, unstructured input gracefully.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcustomer-feedback-{topic}.html`.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n","## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `$pack install \u003Cpack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.\n\n# Customer Feedback — Ingest & Synthesize\n\nInvoke as `$customer-feedback`.\n\n## Report-First Approval Gate\n\nDefault to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research\u002Freport writes.\n\nWhen stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.\n\nAppend-only skill that ingests customer feedback, categorizes findings against ICP and journey map, and maintains a running synthesis. Each run adds a session; the synthesis section regenerates across all sessions.\n\n## Soft Prerequisites\n\n- Read `research\u002Ficp.md` (or `research\u002F{app}\u002Ficp.md` in monorepo mode) if it exists — grounds categorization in ICP segments and pain points.\n- Read `research\u002Fjourney-map.md` (or `research\u002F{app}\u002Fjourney-map.md` in monorepo mode) if it exists — tags findings to journey stages.\n\nThese are not required. The skill works without them but categorization will be less precise.\n\n## Process\n\n### 0. App Scope Resolution (Monorepo Support)\n\nBefore checking prerequisites, determine the app scope:\n\n1. If `$ARGUMENTS` specifies an app name matching a subdirectory of `research\u002F`, use it.\n2. If `research\u002F` contains subdirectories (excluding files), list them and ask the user which app to target. If the session is already in Plan mode and there are 2-3 concrete choices, prefer `request_user_input`; otherwise ask in plain text. If only one subdirectory exists, use it automatically.\n3. If no subdirectories exist, proceed with flat structure (single-product mode).\n\nWhen app scope `{app}` is active:\n- Read\u002Fwrite research from `research\u002F{app}\u002F` instead of `research\u002F`\n- Read\u002Fwrite specs from `specs\u002F{app}\u002F` instead of `specs\u002F`\n- Also read `research\u002Ficp.md` (cross-app overview) for broader context\n\n### 1. Load Context\n\n- Read `research\u002Ficp.md` (or `research\u002F{app}\u002Ficp.md`) if it exists — extract ICP segments, user profiles, pain points, value props\n- Read `research\u002Fjourney-map.md` (or `research\u002F{app}\u002Fjourney-map.md`) if it exists — extract journey stages, use cases, critical moments\n- Read `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`) if it exists — load all previous sessions for synthesis context\n\n### 2. Ingest Feedback\n\nCheck `$ARGUMENTS`:\n- **File path provided**: Read the file and use its contents as the feedback input\n- **Text provided**: Use the argument text directly as feedback\n- **Empty**: Ask the user to paste or describe the feedback. If the session is already in Plan mode and there are 2-3 concrete input-source choices, prefer `request_user_input`; otherwise ask in plain text.\n\nAccept any format: interview notes, support tickets, survey responses, NPS comments, user testing observations, sales call notes, social media mentions, app store reviews.\n\n### 3. Categorize Findings\n\nFor each distinct finding in the feedback:\n\n1. **Classification**: One of:\n   - **Confirmed** — validates an existing ICP assumption, pain point, or journey step\n   - **Wrong** — contradicts an ICP assumption, pain point, or mapped journey\n   - **New** — reveals something not captured in ICP or journey map\n\n2. **ICP Tag** (when `research\u002Ficp.md` exists): Which ICP section does this relate to? (pain point, value prop, user profile, trigger event, etc.)\n\n3. **Journey Stage** (when `research\u002Fjourney-map.md` exists): Which journey stage does this touch? (discovery, evaluation, onboarding, aha moment, retention, etc.)\n\n4. **Severity**: High \u002F Medium \u002F Low — based on how many users it affects and how strongly\n\n5. **Quote or Evidence**: The specific words or behavior that support this finding\n\n### 4. Present & Validate\n\nPresent the categorized findings to the user. If the session is already in Plan mode and there are 2-3 concrete validation choices, prefer `request_user_input`; otherwise ask in plain text:\n\n- Show each finding with its classification, tags, and evidence\n- Ask: \"Does this categorization look right? Any findings I've miscategorized or missed?\"\n- If the user corrects anything, update before writing\n\n### 5. Check Staleness Triggers\n\nCount the number of **Wrong** and **New** findings across ALL sessions (including previous ones):\n\n- If 3+ **Wrong** findings relate to ICP assumptions: recommend re-running `$icp`\n- If 3+ **Wrong** findings relate to journey stages: recommend re-running `$journey-map`\n- If 3+ **New** findings suggest an unserved segment: recommend re-running `$icp`\n\nDisplay these recommendations after the categorized findings.\n\n### 6. Populate Next Steps\n\nBefore writing, check which files exist and synthesis results to populate the `## Next Steps` section contextually. Include a **Recommended** item (the single highest-impact next step given current project state) with a one-line reason, followed by **Other options** (2–4 alternatives). Use this format in the output:\n\n### Next Steps\n\n**Recommended:** [recommended skill] — [one-line reason why this is the highest-impact next action given current state]\n\nOther options:\n- `$skill` — [description]\n- ...\n\n**Recommendation priority** (first applicable becomes the recommendation):\n1. IF downstream impact is **Major**: recommend `$reconcile-research` — [N] conflicts found in downstream docs need resolution before other work\n2. IF staleness alert for ICP: recommend `$icp` — feedback has invalidated key ICP assumptions that other research depends on\n3. IF staleness alert for journey map: recommend `$journey-map` — real user behavior differs from mapped experience\n4. IF 3+ New findings: recommend `$brainstorm` — newly revealed customer needs deserve solution exploration\n5. IF no staleness alerts and no major findings: recommend `$research-roadmap` — check overall project status for the next priority\n\n**Other options** (include all applicable items not chosen as recommended):\n- IF staleness alert for ICP: `$icp` — Re-run discovery — feedback has invalidated key assumptions\n- IF staleness alert for journey map: `$journey-map` — Re-map journeys — real behavior differs from mapped experience\n- IF 3+ New findings: `$brainstorm` — Generate ideas for newly revealed customer needs\n- IF New findings relate to a gap: `$ux-variations [topic]` — Explore UX solutions for the most impactful finding\n- IF no staleness alerts: `$research-roadmap` — Check overall project status\n- IF feedback came from experiment results: `$assumption-tracker` — Update assumption validation status with experiment findings\n- IF 3+ research docs exist and no `research\u002Fassumption-tracker.md`: `$assumption-tracker` — Build the assumptions register to track what feedback is validating\n\n**Impact-aware adjustments:**\n- IF downstream impact is **Minor**: annotate relevant skill suggestions with \"(stale — [brief description])\"\n- If downstream impact has not been classified yet, run the downstream impact check against the proposed output before selecting the final recommendation. Do not emit a Minor\u002FMajor impact recommendation speculatively.\n\n### 7. Write Output\n\nOnly after the user validates, write to `research\u002Fcustomer-feedback.md`:\n\n**If the file doesn't exist**: Create it with the structure below.\n**If the file exists**: Append the new session section, then regenerate the `## Synthesis` section at the top.\n\n### 8. Downstream Impact Check\n\nAfter writing, check for downstream research documents that may be affected by what was just decided. Only check documents that exist on disk.\n\n**Downstream documents to check** (use `{app}\u002F` prefix when app scope is active):\n- `research\u002Fgtm.md`\n- `research\u002Fmonetization.md`\n\nFor each existing downstream document:\n1. Read it — focus on `> Based on:` header, `## Summary`, and sections that reference concepts this skill just defined or changed\n2. Identify **specific conflicts**: claims, assumptions, or references that contradict what was just decided. Examples:\n   - Customer language or pain point framing in GTM messaging that feedback has invalidated\n   - Pricing assumptions in monetization anchored to customer willingness-to-pay signals that have shifted\n   - Channel strategy built on customer behavior patterns that new feedback contradicts\n3. Note each conflict: downstream file, section, the stale claim (quote it), and what it should now say\n\n**Classify the impact**:\n- **None**: No downstream documents exist, or no conflicts found. Skip display entirely.\n- **Minor** (1–2 small conflicts): Display conflicts to user inline.\n- **Major** (3+ conflicts OR a foundational assumption changed — e.g., primary pain point invalidated, willingness-to-pay signals contradicted, key customer behavior pattern disproved): Display conflicts and strongly recommend `$reconcile-research`.\n\nDisplay to the user after showing the written file confirmation. This should be quick — one read per downstream doc, scan for conflicts against key decisions. Not a deep reconciliation.\n\n## Output\n\n### `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`)\n\n```markdown\n# Customer Feedback\n\n> Last updated: [current date]\n> Sessions: [total count]\n\n## Synthesis\n\n[Regenerated each run. Summarizes patterns across ALL sessions:]\n\n### Confirmed Assumptions\n[ICP and journey assumptions that feedback consistently validates]\n\n### Invalidated Assumptions\n[ICP and journey assumptions that feedback contradicts — with evidence count]\n\n### New Discoveries\n[Findings not captured in any existing research — potential ICP updates or new journey stages]\n\n### Staleness Alerts\n[If 3+ Wrong\u002FNew findings accumulated, list which research docs should be re-run and why]\n\n\u003C!-- Only include the Downstream Impact section when impact is Minor or Major. Omit entirely for None. -->\n### Downstream Impact\n\n> Checked: [list of downstream docs checked]\n> Impact: Minor | Major\n\n#### Conflicts Found\n\n1. **research\u002F[file].md** — [Section Name]\n   - **Stale**: \"[exact quote from downstream doc]\"\n   - **Now**: [what this skill's output says instead]\n\n[For Major only:]\n> **Recommended action**: Run `$reconcile-research` to audit and fix all affected downstream documents.\n\n### Next Steps\n\n**Recommended:** `$skill` — [one-line reason]\n\nOther options:\n- [conditional items from step 6 — only include items whose conditions are met]\n\n---\n\n## Feedback Session: [date]\n\n> Source: [file path, \"pasted text\", or \"interview\"]\n> ICP context: [yes\u002Fno — whether research\u002Ficp.md was loaded]\n> Journey context: [yes\u002Fno — whether research\u002Fjourney-map.md was loaded]\n\n### Findings\n\n| # | Finding | Classification | ICP Tag | Journey Stage | Severity |\n|---|---------|---------------|---------|---------------|----------|\n| 1 | [finding] | Confirmed\u002FWrong\u002FNew | [tag] | [stage] | H\u002FM\u002FL |\n\n### Details\n\n#### Finding 1: [title]\n**Classification**: [Confirmed\u002FWrong\u002FNew]\n**Evidence**: \"[quote or observation]\"\n**ICP Tag**: [which ICP section]\n**Journey Stage**: [which stage]\n**Severity**: [High\u002FMedium\u002FLow]\n**Implication**: [what this means for the product]\n\n[Repeat for each finding]\n\n---\n\n[Previous sessions remain below, newest first]\n```\n\nCreate the `research\u002F` directory if it doesn't exist.\n\n## Task Classification\n\nWhen this skill produces follow-up work, file it by execution semantics:\n\n- Immediately actionable implementation or documentation work goes in `tasks\u002Ftodo.md`.\n- Human-only external actions tied to automated steps go in `tasks\u002Fmanual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI\u002FAPI work stay in `tasks\u002Ftodo.md`.\n- One-time condition-gated records, baselines, or future measurements go in `tasks\u002Frecord-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.\n- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks\u002Frecurring-todo.md` with cadence, owner\u002Fagent, next due, evidence path, and escalation conditions.\n- Do not put non-blocking records or recurring obligations in `tasks\u002Ftodo.md` unless they have been explicitly promoted into current execution work.\n\n## Constraints\n\n- **Append-only.** Never delete or overwrite previous sessions in `research\u002Fcustomer-feedback.md` (or `research\u002F{app}\u002Fcustomer-feedback.md`). Only the `## Synthesis` section at the top is regenerated.\n- **Present before writing.** Never write until the user validates the categorization.\n- **Tag to existing research.** When ICP and journey map exist, every finding must be tagged. When they don't exist, skip tagging but note \"no ICP\u002Fjourney context\" in the session header.\n- **Count across sessions.** Staleness triggers are based on cumulative findings, not just the current session.\n- **Accept any format.** The skill should handle messy, unstructured input gracefully.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcustomer-feedback-{topic}.html`.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n",{"name":5,"type":27,"version":45,"description":7,"argument-hint":46},"v0.1","[file path, pasted text, or empty to be prompted]","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fbusiness-research\u002Fcodex\u002Fcustomer-feedback\u002Farchive\u002Fv0.1",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill customer-feedback",{"tool":63,"command":64},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill customer-feedback",{"tool":66,"command":67},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill customer-feedback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbusiness-research\u002Fcodex\u002Fcustomer-feedback\u002Farchive\u002Fv0.1\u002FSKILL.md",true,[71,77,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"concepts\u002Fdistribution-methods.md","REFERENCE","参考文档",348,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fconcepts\u002Fdistribution-methods.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"concepts\u002Fjwt-authentication.md",362,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fconcepts\u002Fjwt-authentication.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"concepts\u002Fsession-lifecycle.md",360,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fconcepts\u002Fsession-lifecycle.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"concepts\u002Ftwo-roles-pattern.md",1389,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fconcepts\u002Ftwo-roles-pattern.md",{"path":90,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":91,"sourceHtmlUrl":92},"examples\u002Fagent-integration.md",217,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fagent-integration.md",{"path":94,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":95,"sourceHtmlUrl":96},"examples\u002Fannotations.md",224,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fannotations.md",{"path":98,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":99,"sourceHtmlUrl":100},"examples\u002Fauto-reconnection.md",213,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fauto-reconnection.md",{"path":102,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":103,"sourceHtmlUrl":104},"examples\u002Fbyop-custom-pin.md",223,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fbyop-custom-pin.md",{"path":106,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":107,"sourceHtmlUrl":108},"examples\u002Fcustomer-integration.md",222,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fcustomer-integration.md",{"path":110,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":111,"sourceHtmlUrl":112},"examples\u002Fmulti-tab-persistence.md",228,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fmulti-tab-persistence.md",{"path":114,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":115,"sourceHtmlUrl":116},"examples\u002Fprivacy-masking.md",218,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fprivacy-masking.md",{"path":118,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":119,"sourceHtmlUrl":120},"examples\u002Fremote-assist.md",231,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fremote-assist.md",{"path":122,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":123,"sourceHtmlUrl":124},"examples\u002Fsession-events.md",220,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fexamples\u002Fsession-events.md",{"path":126,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":127,"sourceHtmlUrl":128},"get-started.md",14944,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Fget-started.md",{"path":130,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Fapi-official.md",1676,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fapi-official.md",{"path":134,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Fapi-reference.md",117,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fapi-reference.md",{"path":138,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":139,"sourceHtmlUrl":140},"references\u002Fapi.md",74,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fapi.md",{"path":142,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fauthorization-official.md",2001,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fauthorization-official.md",{"path":146,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":147,"sourceHtmlUrl":148},"references\u002Fauthorization.md",104,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fauthorization.md",{"path":150,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Fenvironment-variables.md",778,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fenvironment-variables.md",{"path":154,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":155,"sourceHtmlUrl":156},"references\u002Ferror-codes.md",190,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Ferror-codes.md",{"path":158,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":159,"sourceHtmlUrl":160},"references\u002Ffeatures-official.md",1925,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Ffeatures-official.md",{"path":162,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":163,"sourceHtmlUrl":164},"references\u002Ffeatures.md",89,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Ffeatures.md",{"path":166,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":167,"sourceHtmlUrl":168},"references\u002Fget-started-official.md",2003,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fget-started-official.md",{"path":170,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":171,"sourceHtmlUrl":172},"references\u002Fget-started.md",98,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fget-started.md",{"path":174,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":175,"sourceHtmlUrl":176},"references\u002Fsession-events.md",150,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fsession-events.md",{"path":178,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":179,"sourceHtmlUrl":180},"references\u002Fsettings-reference.md",193,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Freferences\u002Fsettings-reference.md",{"path":182,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":183,"sourceHtmlUrl":184},"RUNBOOK.md",2769,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002FRUNBOOK.md",{"path":186,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":187,"sourceHtmlUrl":188},"troubleshooting\u002Fbrowser-compatibility.md",227,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Ftroubleshooting\u002Fbrowser-compatibility.md",{"path":190,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":191,"sourceHtmlUrl":192},"troubleshooting\u002Fcommon-issues.md",2538,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Ftroubleshooting\u002Fcommon-issues.md",{"path":194,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":195,"sourceHtmlUrl":196},"troubleshooting\u002Fcors-csp.md",283,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Ftroubleshooting\u002Fcors-csp.md",{"path":198,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":199,"sourceHtmlUrl":200},"troubleshooting\u002Ferror-codes.md",216,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fcobrowse-sdk\u002Ftroubleshooting\u002Ferror-codes.md",[202,214,224,236,249,260],{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":40},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[209,210,211,212,30,213],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"publishedAt":40},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[221,222,223,213,211,30],"deck install valid","deck","install",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":40},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[231,232,233,213,234,235,211,30],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":240,"categories":241,"keywords":245,"publishedAt":40},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[242],{"categoryNo":243,"categoryName":244,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[246,247,213,234,30,248,211],"codex missing skill valid","missing","fallback",{"skillNo":250,"name":251,"nameZh":6,"description":252,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":253,"categories":254,"keywords":256,"publishedAt":40},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[255],{"categoryNo":243,"categoryName":244,"taxonomyType":21,"taxonomyTypeDesc":22},[213,234,248,257,258,259,30,211],"base skill","codex base skill fallback valid","base",{"skillNo":261,"name":262,"nameZh":6,"description":263,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":264,"categories":265,"keywords":266,"publishedAt":40},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[213,233,232,267,235,30,211],"claude pack guard valid"]