[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MWAWMZF1FCQNFDX6DNT88C":3,"skill-same:01M6MWAWMZF1FCQNFDX6DNT88C":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6MWAWMZF1FCQNFDX6DNT88C","forbotsake-retro",null,"Stage 9: MEASURE. Reviews what you published, analyzes performance data,\nand produces a retro report with evidence-based recommendations.\nTells you what to double down on, what to drop, and what to try next.\nUse when: \"what worked\", \"marketing retro\", \"measure results\", \"review performance\",\n\"which content performed best\", \"should I keep doing this\".\nProactively invoke one week after \u002Fforbotsake-publish was last run.","forbotsake\u002Fforbotsake","forbotsake","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273708741?v=4","01M6MW9A04DY7WQBA8YF96SVJE","01M6MW9A47HYRVBBQ642740E75",5,"MIT","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fforbotsake-retro\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000019","营销推广","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"forbotsake retro","retro","drop","what worked","down","which","reviews","you","keep","recommendations","stage","review","next","evidence","use","marketing","data","publish","run","performance","2026-11-10 10:12:30",false,"---\nname: forbotsake-retro\ndescription: >\n  Stage 9: MEASURE. Reviews what you published, analyzes performance data,\n\n  and produces a retro report with evidence-based recommendations.\n\n  Tells you what to double down on, what to drop, and what to try next.\n\n  Use when: \"what worked\", \"marketing retro\", \"measure results\", \"review\n  performance\",\n\n  \"which content performed best\", \"should I keep doing this\".\n\n  Proactively invoke one week after \u002Fforbotsake-publish was last run.\n---\n\n# \u002Fforbotsake-retro\n\nMeasure. Learn. Decide. The feedback loop that makes marketing compound.\n\n## Preamble\n\n```bash\nFORBOTSAKE_HOME=\"${FORBOTSAKE_HOME:-$HOME\u002F.forbotsake}\"\nmkdir -p \"$FORBOTSAKE_HOME\"\n\n# Discover forbotsake install directory\n_FBS_ROOT=\"\"\nfor _FBS_CANDIDATE in \"$HOME\u002F.codex\u002Fskills\u002Fforbotsake\" \"$HOME\u002F.agents\u002Fskills\u002Fforbotsake\"; do\n  [ -d \"$_FBS_CANDIDATE\" ] && _FBS_ROOT=\"$_FBS_CANDIDATE\" && break\ndone\nif [ -z \"$_FBS_ROOT\" ]; then\n  echo \"WARNING: forbotsake not found. Install: bash \u003C(curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fforbotsake\u002Fforbotsake\u002Fmain\u002Fbin\u002Finstall.sh)\"\nfi\n\n# Check for updates\n_UPD=\"\"\n[ -n \"$_FBS_ROOT\" ] && [ -x \"$_FBS_ROOT\u002Fbin\u002Fforbotsake-update-check\" ] && _UPD=$(\"$_FBS_ROOT\u002Fbin\u002Fforbotsake-update-check\" 2>\u002Fdev\u002Fnull || true)\n[ -n \"$_UPD\" ] && echo \"$_UPD\" || true\n_BRANCH=$(git branch --show-current 2>\u002Fdev\u002Fnull || echo \"unknown\")\necho \"BRANCH: $_BRANCH\"\n```\n\n```bash\n\n# Check for published log\nif [ -f published-log.md ]; then\n  echo \"PUBLISHED_LOG: yes\"\n  wc -l published-log.md\nelse\n  echo \"PUBLISHED_LOG: no\"\nfi\n\n# Check for strategy.md\nif [ -f strategy.md ]; then\n  echo \"STRATEGY: yes\"\nelse\n  echo \"STRATEGY: no\"\nfi\n\n# Check for existing retro reports\nif [ -d retros\u002F ]; then\n  echo \"RETRO_DIR: yes\"\n  ls -1 retros\u002F 2>\u002Fdev\u002Fnull | tail -5\nelse\n  echo \"RETRO_DIR: no\"\nfi\n```\n\nIf output shows `UPGRADE_AVAILABLE \u003Cold> \u003Cnew>`: read the forbotsake-upgrade SKILL.md\nat `$_FBS_ROOT\u002Fforbotsake-upgrade\u002FSKILL.md` (where `_FBS_ROOT` is the variable already\nresolved in the preamble bash above) and follow the \"Inline upgrade flow\" section **Step 1\nonly**. If Step 1 results in \"Yes\" or \"Always\" (proceed with upgrade), continue through\nSteps 2-7 of the inline flow. If Step 1 results in \"Not now\" or \"Never\" (declined),\nskip Steps 2-7 entirely and continue with this skill immediately.\n\nIf output shows `JUST_UPGRADED \u003Cold> \u003Cnew>`: tell user\n\"Running forbotsake v{new} (just updated from v{old})!\" and continue.\n\nIf `PUBLISHED_LOG` is `no`: \"No published-log.md found. I need to know what you published to analyze results. Either run `\u002Fforbotsake-publish` to ship content (it logs automatically), or tell me what you published and I'll work from that.\"\nAsk the user directly in conversation to let the user provide publishing history manually.\n\nIf `STRATEGY` is `no`: \"No strategy.md found. I can still run a retro, but I won't be able to compare results against your goals. Consider running `\u002Fforbotsake-marketing-start` after this retro to set a baseline strategy.\"\n\n## Phase 1: Read the Record\n\nRead `published-log.md` completely. For each entry, note:\n- Date published\n- Platform\u002Fchannel\n- Content title or description\n- Source file (read it if still in content\u002F)\n- Any links or notes\n\nRead `strategy.md` to understand:\n- The ICP (who are we trying to reach?)\n- Channel strategy (which channels were prioritized?)\n- The 2-week experiment plan (what were the success criteria?)\n- Decision criteria (what number means \"keep going\" vs \"pivot\"?)\n\nIf previous retro reports exist in `retros\u002F`, read the most recent one to understand trends.\n\nPresent a summary:\n\n> \"Here's what I found in your published-log.md:\n>\n> {list of published content with dates and platforms}\n>\n> Your strategy.md says you're targeting {ICP} on {channels} with a success metric of {metric}.\n>\n> Now I need the numbers. Let's go through each piece.\"\n\n## Phase 2: Gather Results\n\nAsk the user directly in conversation for each published piece. Ask ONE piece at a time to keep it manageable.\n\n> \"For {content title} published on {date} to {platform}:\n>\n> What results did you see? Share whatever numbers you have:\n>\n> **Reach\u002FImpressions:**\n> - Views\u002Fimpressions?\n> - Follower count change?\n>\n> **Engagement:**\n> - Likes\u002Freactions?\n> - Comments\u002Freplies?\n> - Shares\u002Fretweets\u002Freposts?\n> - Saves\u002Fbookmarks?\n>\n> **Conversion:**\n> - Link clicks?\n> - Signups\u002Ftrials?\n> - Revenue?\n>\n> **Qualitative:**\n> - Any notable replies or DMs?\n> - Did anyone share it with their audience?\n> - Any surprises?\n>\n> Share what you have. Zeros and 'I don't know' are valid answers.\"\n\nIf the user doesn't have exact numbers, accept estimates. Note which metrics are estimates vs. actual in the analysis.\n\nIf the user has results for multiple pieces, accept them in batch. Don't force one-at-a-time if the user wants to dump everything at once.\n\n## Phase 3: Analyze\n\nAfter collecting all results, analyze across three dimensions:\n\n### Content Performance\n\nRank all published pieces by engagement rate (engagement \u002F reach). Identify:\n- **Best performer:** Which piece got the most engagement relative to reach?\n- **Worst performer:** Which piece underperformed?\n- **Pattern:** What do the top performers have in common? (topic, format, tone, time of day)\n\n### Channel Performance\n\nCompare channels if multiple were used:\n- **Reach per effort:** Which channel delivered the most reach per hour of founder time?\n- **Engagement quality:** Which channel produced meaningful interactions (replies, DMs, signups) vs vanity metrics (likes)?\n- **Conversion:** Which channel drove actual business outcomes?\n\n### Experiment Evaluation\n\nCompare results against the success criteria from strategy.md:\n- Did the 2-week experiment meet the \"keep going\" threshold?\n- If not, did it show enough signal to continue with adjustments?\n- Or is it time to pivot to channel #2?\n\n## Phase 4: Write the Retro Report\n\nCreate the retros\u002F directory if it doesn't exist:\n```bash\nmkdir -p retros\u002F\n```\n\nWrite the report to `retros\u002F{YYYY-MM-DD}-retro.md`:\n\n```markdown\n---\nschema_version: 1\ngenerated_by: forbotsake\ngenerated_at: {ISO timestamp}\nperiod: {start date} to {end date}\n---\n# Marketing Retro: {date range}\n\nGenerated by \u002Fforbotsake-retro on {date}\n\n## Summary\n\n{2-3 sentence overview: what was published, what worked, what the data says}\n\n## What Worked (with evidence)\n\n{For each thing that worked:}\n- **{Finding}:** {evidence — specific numbers, quotes, or observations}\n  - Why it worked: {analysis}\n  - Implication: {what to do about it}\n\n## What Didn't Work (with evidence)\n\n{For each thing that underperformed:}\n- **{Finding}:** {evidence — specific numbers or lack thereof}\n  - Why it likely failed: {analysis — be honest, not diplomatic}\n  - Implication: {what to change or stop}\n\n## Content Ranking\n\n| Content | Platform | Reach | Engagement | Eng. Rate | Conversions | Verdict |\n|---------|----------|-------|------------|-----------|-------------|---------|\n{ranked by engagement rate, best to worst}\n\n## Channel Comparison\n\n| Channel | Pieces Published | Avg. Reach | Avg. Engagement | Conversions | ROI\u002FHour | Verdict |\n|---------|-----------------|------------|-----------------|-------------|----------|---------|\n{ranked by ROI per hour of effort}\n\n## Experiment Verdict\n\n- **Goal:** {from strategy.md}\n- **Result:** {actual numbers}\n- **Decision:** {KEEP GOING \u002F ADJUST \u002F PIVOT}\n- **Reasoning:** {why this decision}\n\n## Recommendations\n\n### Double Down\n{What to do more of, with specific actions}\n\n### Adjust\n{What to change — messaging, timing, format, frequency}\n\n### Drop\n{What to stop doing — channels, content types, or tactics that aren't working}\n\n## Updated 2-Week Experiment Plan\n\nBased on these learnings:\n\n- **Channel:** {primary channel for next 2 weeks}\n- **Content plan:** {what to create and publish}\n- **Cadence:** {how often}\n- **Success metric:** {what to measure}\n- **Decision criteria:** {threshold for keep\u002Fpivot}\n\n## Open Questions\n\n{Things we still don't know. Hypotheses to test. Data we need.}\n```\n\n## Phase 5: Suggest Strategy Updates\n\nBased on the retro findings, identify specific changes to strategy.md:\n\n> \"Based on this retro, here are suggested updates to your strategy.md:\n>\n> {list specific changes — channel scores, messaging adjustments, ICP refinements}\n>\n> Want me to apply these updates?\"\n\nIf the user says yes, use Edit to update strategy.md. Preserve the existing structure. Add a revision note at the top:\n\n```markdown\n\u003C!-- Revised {date} based on \u002Fforbotsake-retro findings -->\n```\n\nUpdate the specific sections that need changing (channel scores, messaging pillars, experiment plan). Do NOT rewrite the whole file.\n\n## Phase 6: Next Steps\n\nTell the user:\n\n> \"Retro report saved to retros\u002F{filename}.\n>\n> Based on the results:\n>\n> {If KEEP GOING:}\n> Your current approach is working. Run `\u002Fforbotsake-content-plan` to plan next week's content,\n> then `\u002Fforbotsake-create` to write it.\n>\n> {If ADJUST:}\n> The channel is right but the approach needs tweaking. Run `\u002Fforbotsake-content-plan`\n> with the adjusted strategy, then `\u002Fforbotsake-create` for new content.\n>\n> {If PIVOT:}\n> Time to try a different channel or major messaging shift.\n> Run `\u002Fforbotsake-marketing-start` again if the strategy needs a major revision,\n> or `\u002Fforbotsake-content-plan` for next week's content with the updated approach.\n>\n> Run `\u002Fforbotsake-retro` again next week to keep the loop going.\"\n","# \u002Fforbotsake-retro\n\nMeasure. Learn. Decide. The feedback loop that makes marketing compound.\n\n## Preamble\n\n```bash\nFORBOTSAKE_HOME=\"${FORBOTSAKE_HOME:-$HOME\u002F.forbotsake}\"\nmkdir -p \"$FORBOTSAKE_HOME\"\n\n# Discover forbotsake install directory\n_FBS_ROOT=\"\"\nfor _FBS_CANDIDATE in \"$HOME\u002F.codex\u002Fskills\u002Fforbotsake\" \"$HOME\u002F.agents\u002Fskills\u002Fforbotsake\"; do\n  [ -d \"$_FBS_CANDIDATE\" ] && _FBS_ROOT=\"$_FBS_CANDIDATE\" && break\ndone\nif [ -z \"$_FBS_ROOT\" ]; then\n  echo \"WARNING: forbotsake not found. Install: bash \u003C(curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fforbotsake\u002Fforbotsake\u002Fmain\u002Fbin\u002Finstall.sh)\"\nfi\n\n# Check for updates\n_UPD=\"\"\n[ -n \"$_FBS_ROOT\" ] && [ -x \"$_FBS_ROOT\u002Fbin\u002Fforbotsake-update-check\" ] && _UPD=$(\"$_FBS_ROOT\u002Fbin\u002Fforbotsake-update-check\" 2>\u002Fdev\u002Fnull || true)\n[ -n \"$_UPD\" ] && echo \"$_UPD\" || true\n_BRANCH=$(git branch --show-current 2>\u002Fdev\u002Fnull || echo \"unknown\")\necho \"BRANCH: $_BRANCH\"\n```\n\n```bash\n\n# Check for published log\nif [ -f published-log.md ]; then\n  echo \"PUBLISHED_LOG: yes\"\n  wc -l published-log.md\nelse\n  echo \"PUBLISHED_LOG: no\"\nfi\n\n# Check for strategy.md\nif [ -f strategy.md ]; then\n  echo \"STRATEGY: yes\"\nelse\n  echo \"STRATEGY: no\"\nfi\n\n# Check for existing retro reports\nif [ -d retros\u002F ]; then\n  echo \"RETRO_DIR: yes\"\n  ls -1 retros\u002F 2>\u002Fdev\u002Fnull | tail -5\nelse\n  echo \"RETRO_DIR: no\"\nfi\n```\n\nIf output shows `UPGRADE_AVAILABLE \u003Cold> \u003Cnew>`: read the forbotsake-upgrade SKILL.md\nat `$_FBS_ROOT\u002Fforbotsake-upgrade\u002FSKILL.md` (where `_FBS_ROOT` is the variable already\nresolved in the preamble bash above) and follow the \"Inline upgrade flow\" section **Step 1\nonly**. If Step 1 results in \"Yes\" or \"Always\" (proceed with upgrade), continue through\nSteps 2-7 of the inline flow. If Step 1 results in \"Not now\" or \"Never\" (declined),\nskip Steps 2-7 entirely and continue with this skill immediately.\n\nIf output shows `JUST_UPGRADED \u003Cold> \u003Cnew>`: tell user\n\"Running forbotsake v{new} (just updated from v{old})!\" and continue.\n\nIf `PUBLISHED_LOG` is `no`: \"No published-log.md found. I need to know what you published to analyze results. Either run `\u002Fforbotsake-publish` to ship content (it logs automatically), or tell me what you published and I'll work from that.\"\nAsk the user directly in conversation to let the user provide publishing history manually.\n\nIf `STRATEGY` is `no`: \"No strategy.md found. I can still run a retro, but I won't be able to compare results against your goals. Consider running `\u002Fforbotsake-marketing-start` after this retro to set a baseline strategy.\"\n\n## Phase 1: Read the Record\n\nRead `published-log.md` completely. For each entry, note:\n- Date published\n- Platform\u002Fchannel\n- Content title or description\n- Source file (read it if still in content\u002F)\n- Any links or notes\n\nRead `strategy.md` to understand:\n- The ICP (who are we trying to reach?)\n- Channel strategy (which channels were prioritized?)\n- The 2-week experiment plan (what were the success criteria?)\n- Decision criteria (what number means \"keep going\" vs \"pivot\"?)\n\nIf previous retro reports exist in `retros\u002F`, read the most recent one to understand trends.\n\nPresent a summary:\n\n> \"Here's what I found in your published-log.md:\n>\n> {list of published content with dates and platforms}\n>\n> Your strategy.md says you're targeting {ICP} on {channels} with a success metric of {metric}.\n>\n> Now I need the numbers. Let's go through each piece.\"\n\n## Phase 2: Gather Results\n\nAsk the user directly in conversation for each published piece. Ask ONE piece at a time to keep it manageable.\n\n> \"For {content title} published on {date} to {platform}:\n>\n> What results did you see? Share whatever numbers you have:\n>\n> **Reach\u002FImpressions:**\n> - Views\u002Fimpressions?\n> - Follower count change?\n>\n> **Engagement:**\n> - Likes\u002Freactions?\n> - Comments\u002Freplies?\n> - Shares\u002Fretweets\u002Freposts?\n> - Saves\u002Fbookmarks?\n>\n> **Conversion:**\n> - Link clicks?\n> - Signups\u002Ftrials?\n> - Revenue?\n>\n> **Qualitative:**\n> - Any notable replies or DMs?\n> - Did anyone share it with their audience?\n> - Any surprises?\n>\n> Share what you have. Zeros and 'I don't know' are valid answers.\"\n\nIf the user doesn't have exact numbers, accept estimates. Note which metrics are estimates vs. actual in the analysis.\n\nIf the user has results for multiple pieces, accept them in batch. Don't force one-at-a-time if the user wants to dump everything at once.\n\n## Phase 3: Analyze\n\nAfter collecting all results, analyze across three dimensions:\n\n### Content Performance\n\nRank all published pieces by engagement rate (engagement \u002F reach). Identify:\n- **Best performer:** Which piece got the most engagement relative to reach?\n- **Worst performer:** Which piece underperformed?\n- **Pattern:** What do the top performers have in common? (topic, format, tone, time of day)\n\n### Channel Performance\n\nCompare channels if multiple were used:\n- **Reach per effort:** Which channel delivered the most reach per hour of founder time?\n- **Engagement quality:** Which channel produced meaningful interactions (replies, DMs, signups) vs vanity metrics (likes)?\n- **Conversion:** Which channel drove actual business outcomes?\n\n### Experiment Evaluation\n\nCompare results against the success criteria from strategy.md:\n- Did the 2-week experiment meet the \"keep going\" threshold?\n- If not, did it show enough signal to continue with adjustments?\n- Or is it time to pivot to channel #2?\n\n## Phase 4: Write the Retro Report\n\nCreate the retros\u002F directory if it doesn't exist:\n```bash\nmkdir -p retros\u002F\n```\n\nWrite the report to `retros\u002F{YYYY-MM-DD}-retro.md`:\n\n```markdown\n---\nschema_version: 1\ngenerated_by: forbotsake\ngenerated_at: {ISO timestamp}\nperiod: {start date} to {end date}\n---\n# Marketing Retro: {date range}\n\nGenerated by \u002Fforbotsake-retro on {date}\n\n## Summary\n\n{2-3 sentence overview: what was published, what worked, what the data says}\n\n## What Worked (with evidence)\n\n{For each thing that worked:}\n- **{Finding}:** {evidence — specific numbers, quotes, or observations}\n  - Why it worked: {analysis}\n  - Implication: {what to do about it}\n\n## What Didn't Work (with evidence)\n\n{For each thing that underperformed:}\n- **{Finding}:** {evidence — specific numbers or lack thereof}\n  - Why it likely failed: {analysis — be honest, not diplomatic}\n  - Implication: {what to change or stop}\n\n## Content Ranking\n\n| Content | Platform | Reach | Engagement | Eng. Rate | Conversions | Verdict |\n|---------|----------|-------|------------|-----------|-------------|---------|\n{ranked by engagement rate, best to worst}\n\n## Channel Comparison\n\n| Channel | Pieces Published | Avg. Reach | Avg. Engagement | Conversions | ROI\u002FHour | Verdict |\n|---------|-----------------|------------|-----------------|-------------|----------|---------|\n{ranked by ROI per hour of effort}\n\n## Experiment Verdict\n\n- **Goal:** {from strategy.md}\n- **Result:** {actual numbers}\n- **Decision:** {KEEP GOING \u002F ADJUST \u002F PIVOT}\n- **Reasoning:** {why this decision}\n\n## Recommendations\n\n### Double Down\n{What to do more of, with specific actions}\n\n### Adjust\n{What to change — messaging, timing, format, frequency}\n\n### Drop\n{What to stop doing — channels, content types, or tactics that aren't working}\n\n## Updated 2-Week Experiment Plan\n\nBased on these learnings:\n\n- **Channel:** {primary channel for next 2 weeks}\n- **Content plan:** {what to create and publish}\n- **Cadence:** {how often}\n- **Success metric:** {what to measure}\n- **Decision criteria:** {threshold for keep\u002Fpivot}\n\n## Open Questions\n\n{Things we still don't know. Hypotheses to test. Data we need.}\n```\n\n## Phase 5: Suggest Strategy Updates\n\nBased on the retro findings, identify specific changes to strategy.md:\n\n> \"Based on this retro, here are suggested updates to your strategy.md:\n>\n> {list specific changes — channel scores, messaging adjustments, ICP refinements}\n>\n> Want me to apply these updates?\"\n\nIf the user says yes, use Edit to update strategy.md. Preserve the existing structure. Add a revision note at the top:\n\n```markdown\n\u003C!-- Revised {date} based on \u002Fforbotsake-retro findings -->\n```\n\nUpdate the specific sections that need changing (channel scores, messaging pillars, experiment plan). Do NOT rewrite the whole file.\n\n## Phase 6: Next Steps\n\nTell the user:\n\n> \"Retro report saved to retros\u002F{filename}.\n>\n> Based on the results:\n>\n> {If KEEP GOING:}\n> Your current approach is working. Run `\u002Fforbotsake-content-plan` to plan next week's content,\n> then `\u002Fforbotsake-create` to write it.\n>\n> {If ADJUST:}\n> The channel is right but the approach needs tweaking. Run `\u002Fforbotsake-content-plan`\n> with the adjusted strategy, then `\u002Fforbotsake-create` for new content.\n>\n> {If PIVOT:}\n> Time to try a different channel or major messaging shift.\n> Run `\u002Fforbotsake-marketing-start` again if the strategy needs a major revision,\n> or `\u002Fforbotsake-content-plan` for next week's content with the updated approach.\n>\n> Run `\u002Fforbotsake-retro` again next week to keep the loop going.\"\n",{"name":5,"description":7},"main","d91f0c567548c80403f85619693a405ed65d2b60",".agents\u002Fskills\u002Fforbotsake-retro",1,"https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake","https:\u002F\u002Fgithub.com\u002Fforbotsake","2026-08-17 21:39:59",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add forbotsake\u002Fforbotsake --skill forbotsake-retro",{"tool":66,"command":67},"bunx","bunx skills add forbotsake\u002Fforbotsake --skill forbotsake-retro",{"tool":69,"command":70},"pnpm","pnpm dlx skills add forbotsake\u002Fforbotsake --skill forbotsake-retro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fforbotsake-retro\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"openai.yaml","REFERENCE","参考文档",479,"https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fforbotsake-retro\u002Fopenai.yaml",[81,102,126,149,156,190],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":48},"01M6MWS487CZVEME2DWGT48C58","forbotsake-upgrade","Upgrade forbotsake to the latest version. Detects install type (git clone\nvs vendored), runs the upgrade, and shows what's new.\nUse when: \"upgrade forbotsake\", \"update forbotsake\", \"get latest version\",\n\"forbotsake update\".","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-upgrade\u002FSKILL.md",[],[88,89,9,90,91,92,93,94,95,42,96,97,98,99,100,101],"upgrade","forbotsake upgrade","update","git","Bash","read","write","install","version","git clone","get","type","latest","clone",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":111,"publishedAt":48},"01M6MWRZ7XD9Q73JTRBQ0N8682","forbotsake-spy","Stage 3: RESEARCH (competitors). Analyzes 3-5 competitors to find messaging whitespace\nand positioning gaps. Produces competitor-analysis.md with a messaging matrix showing\nwhat each competitor says, what's missing, and where you can win.\nUse when: \"competitor analysis\", \"competitive research\", \"what are others doing\",\n\"market landscape\", \"who am I competing with\", \"spy on competitors\",\n\"messaging whitespace\", \"differentiation research\".\nProactively invoke when the user mentions competitors or asks how to differentiate.","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-spy\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[112,9,113,114,115,92,116,93,94,117,42,118,119,120,121,122,123,35,124,125],"forbotsake spy","messaging","analysis","how","competitors","edit","positioning","landscape","missing","how to","differentiation","competitive","websearch","matrix",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":135,"publishedAt":48},"01M6MWRPHXWYB38V08BZM8SSRE","forbotsake-sharpen","Stage 4.5: SHARPEN. Takes a specific outreach target (person or organization) and\nproduces a deep execution plan with contextual research, relationship mapping,\nangle selection, and a multi-touch sequence. Reads your founder profile and strategy\nto leverage warm paths and unfair advantages.\nUse when: \"refine this plan\", \"go deeper on this\", \"sharpen execution\",\n\"how do I approach [person]\", \"outreach to [person]\", \"target [person\u002Forg]\",\n\"approach [person]\", \"engage [org]\".\nProactively invoke when the user mentions approaching a specific person or\norganization as part of their marketing strategy.\nRequires: strategy.md (from \u002Fforbotsake-marketing-start).","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-sharpen\u002FSKILL.md",[132,133,134],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[136,137,9,138,115,92,139,93,94,117,140,141,142,143,144,145,146,147,124,148],"sharpen","forbotsake sharpen","start","plan","selection","relationship","organization","refine","deeper","deep","leverage","paths","sequence",{"skillNo":150,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":155,"publishedAt":48},"01M6MWRHXHECX1N4WNHBJJQKER","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-retro\u002FSKILL.md",[153,154],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[29,28,9,39,47,46,45,44,92,43,93,94,117,40,30,37,35,34,33,31],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":174,"publishedAt":48},"01M6MWRB8GN0AZTEVTQD1GBA8K","forbotsake-publish","Stage 8: SHIP. Two modes: POST (auto-post via Claude for Chrome) or COPY\n(format for copy-paste). Handles X\u002FTwitter threads, LinkedIn posts, blog posts,\nand more. Logs everything for retrospective analysis.\nFor auto-posting, the user needs the Claude for Chrome extension installed.\nWithout it, the skill falls back to COPY mode automatically.\nUse when: \"publish this\", \"format for twitter\", \"post to X\", \"ship this content\",\n\"format for blog\", \"send this email\", \"ready to publish\", \"auto-post\",\n\"post this to X\", \"publish to LinkedIn\".\nProactively invoke when the user has content in content\u002F and says they want to ship it.","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-publish\u002FSKILL.md",[162,165,168,171],{"categoryNo":163,"categoryName":164,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":166,"categoryName":167,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":169,"categoryName":170,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":172,"categoryName":173,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000036","内容创作者",[45,175,9,176,177,178,179,180,181,93,94,117,182,183,184,185,186,187,188,189],"forbotsake publish","MCP","image","create","logs","ship","text","context","auto","ready","chrome extension","posts","paste","mode","send",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":198,"publishedAt":48},"01M6MWR5K98QN9BDH4179Y47F0","forbotsake-marketing-start","The starting point for marketing your product. Reads your codebase to understand\nwhat you built, asks 5 hard questions about positioning, audience, and channels,\nthen produces strategy.md with your marketing strategy and first concrete move.\nUse when: \"how should I market this\", \"go-to-market\", \"GTM\", \"positioning\",\n\"I don't know how to sell this\", \"help me market\", \"marketing strategy\".\nProactively invoke when the user asks about marketing, growth, or getting users\nand no strategy.md exists yet.","https:\u002F\u002Fgithub.com\u002Fforbotsake\u002Fforbotsake\u002Fblob\u002Fmain\u002Fforbotsake-marketing-start\u002FSKILL.md",[196,197],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[138,43,199,9,200,201,115,92,93,94,117,202,118,203,121,204,205,35,124,206],"forbotsake marketing start","go","product","me","gtm","go-to-market","move","for"]