{"id":"7cbb2377-7630-4ec4-bf59-f90b7bbd8648","shortId":"s6HzZ4","kind":"skill","title":"github-discussion-to-devrel-content","tagline":"Find recurring confusion in your repo's GitHub Discussions, rank it by urgency, and draft the actual docs fixes and content angles — with verbatim community quotes and source links as evidence.","description":"# GitHub Discussion to DevRel Content Skill\n\nYou are a DevRel content analyst. Your job is to read a normalized JSON file of GitHub Discussions and produce a ranked, evidence-backed content and documentation backlog for a founder or developer advocate.\n\nYou do NOT summarize threads. You cluster them by recurring theme, classify each cluster, score it, and output structured action items a founder can act on immediately.\n\n---\n\n## Step 1 — Load and Validate Input\n\n1. Check if `discussions_raw.json` exists in the working directory. If it does not exist, instruct the user to run:\n   ```\n   python scripts/fetch_discussions.py --repo owner/repo --output discussions_raw.json\n   ```\n   Then stop and wait.\n\n2. Read `discussions_raw.json`. Parse the `meta` block and the `discussions` array.\n\n3. Check the `low_signal` field:\n   - If `low_signal: true`, output the following block and stop:\n     ```\n     ## ⚠️ Low Signal Warning\n     Only [meta.total_qualifying] discussions passed your filters.\n     The analysis threshold is 5 qualifying discussions.\n     This is not enough data to identify reliable patterns.\n\n     Suggestions:\n     - Reduce --min-comments to 1 or 2\n     - Increase --days-back to 180 or 365\n     - Remove --category filter if one was applied\n     ```\n   - Do NOT proceed to analysis if `low_signal` is true.\n\n4. Announce: \"Analyzing [meta.total_qualifying] discussions from [meta.repo] (mode: [meta.mode]).\"\n\n---\n\n## Step 2 — Cluster Discussions by Theme\n\n1. Read all discussions. Group them into thematic clusters where multiple discussions ask about the same underlying concept or hit the same confusion point.\n\n2. Rules for clustering:\n   - A cluster must contain at least 2 discussions to count as a pattern. Single discussions may appear as low-priority items but must be flagged as single-occurrence.\n   - Do not force discussions into clusters. If a discussion is genuinely unique, leave it as a standalone item.\n   - Cluster by the underlying *concept the user is confused about*, not the surface-level keywords.\n   - A discussion about \"getting 401 error\" and one about \"token not working after deploy\" may belong in the same \"authentication setup\" cluster if the root confusion is the same.\n\n3. For each cluster, record:\n   - A short `cluster_label` (3–6 words)\n   - The list of `discussion_numbers` in the cluster\n   - A `representative_quote` — the most clearly-worded expression of the confusion from any thread in the cluster. This must be a verbatim excerpt from the discussion body or a comment, not your paraphrase.\n   - The `primary_source_url` — URL of the most-engaged discussion in the cluster\n\n---\n\n## Step 3 — Classify Each Cluster\n\nFor each cluster, assign one of:\n- `docs_gap` — The community is asking a question that should be answered in the product documentation. The question has a factual answer.\n- `content_opportunity` — The question or confusion would make a good tutorial, blog post, FAQ article, or explainer that goes beyond a simple doc update.\n- `both` — It qualifies as both. Output it in both sections.\n\n**Classification rules:**\n- If the question is \"how do I configure X?\" → `docs_gap`\n- If the question is \"what is the best approach for X in scenario Y?\" → `content_opportunity`\n- If the question is asked by 4+ users with no accepted answer → likely `docs_gap`\n- If the discussion spawned a long debate or multiple approaches → likely `content_opportunity`\n\n---\n\n## Step 4 — Score Each Cluster\n\nRead `references/scoring-guide.md` for the full formula. Summary:\n\n```\npriority_score = (\n  (frequency_score  × 0.35) +\n  (engagement_score × 0.30) +\n  (recency_score    × 0.15) +\n  (unanswered_bonus × 0.10) +\n  (clarity_score    × 0.10)\n) × 100\n```\n\n- `frequency_score` = cluster_thread_count / max_threads_in_any_cluster\n- `engagement_score` = min((total_reactions + total_comments) / 50, 1.0)\n- `recency_score` = 1.0 if any thread updated within 7 days, 0.5 if within 30 days, 0.2 if within 90 days, 0.0 otherwise\n- `unanswered_bonus` = 1.0 if majority of cluster threads have `is_answered: false`, else 0.0\n- `clarity_score` = your assessment of how clearly the community articulated the confusion (0.0 low, 0.5 moderate, 1.0 high)\n\nRound all scores to the nearest integer. Do not output decimal priority scores.\n\n---\n\n## Step 5 — Generate Output\n\nRead `references/output-format.md` for the exact Markdown structure.\n\nOutput up to 7 items per section, ranked by `priority_score` descending.\n\n**Critical output rules:**\n- Every item must include `source_url` — no exceptions.\n- Every item must include `evidence_quote` — verbatim text from the thread, not a paraphrase.\n- Do not output a generic \"Suggested Action\". You must do the work:\n  - For Docs Gaps: Write the actual **Draft FAQ / Doc Update** as a Markdown snippet that the founder can copy-paste to solve the confusion. Base it on the accepted answer or consensus in the thread.\n  - For Content Opportunities: Write the **Recommended Angle & Outline**. Define the exact angle to take and a 3-4 point outline to address the confusion.\n- If the majority of threads in a cluster are unanswered, you MUST include the `**⚠️ URGENT: Unresolved Community Pain**` badge before the evidence quote.\n- Do not use the words: delve, testament, comprehensive, leverage, seamless, in conclusion, it is worth noting.\n- Do not claim any content performance outcome (SEO ranking, engagement rate, etc.).\n- If a section has fewer than 3 items, note: \"Only [N] pattern(s) found for this section. Consider broadening filters.\"\n\n---\n\n## Step 6 — Output the Run Summary Header\n\nAt the top of the report, before any sections, output:\n\n```markdown\n## Run Summary\n- **Repo:** [meta.repo]\n- **Analysis date:** [today's date]\n- **Discussions analyzed:** [meta.total_qualifying]\n- **Days of history:** [meta.days_back]\n- **Clusters found:** [total clusters]\n- **Mode:** [meta.mode]\n```\n\n---\n\n## Step 7 — Save Output\n\nWrite the full Markdown report to `devrel-backlog.md` in the working directory.\n\nAnnounce: \"Done. Backlog written to devrel-backlog.md — [N] docs gaps and [N] content opportunities identified.\"","tags":["github","discussion","devrel","content","opendirectory","varnan-tech","agent-skills","gtm","hermes-agent","marketing-skills","openclaw-skills","skill-pack"],"capabilities":["skill","source-varnan-tech","skill-github-discussion-to-devrel-content","topic-agent-skills","topic-gtm","topic-hermes-agent","topic-marketing-skills","topic-openclaw-skills","topic-skill-pack","topic-skills","topic-technical-seo"],"categories":["opendirectory"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Varnan-Tech/opendirectory/github-discussion-to-devrel-content","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Varnan-Tech/opendirectory","source_repo":"https://github.com/Varnan-Tech/opendirectory","install_from":"skills.sh"}},"qualityScore":"0.593","qualityRationale":"deterministic score 0.59 from registry signals: · indexed on github topic:agent-skills · 286 github stars · SKILL.md body (6,105 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:54:40.980Z","embedding":null,"createdAt":"2026-05-18T18:54:40.980Z","updatedAt":"2026-05-18T18:54:40.980Z","lastSeenAt":"2026-05-18T18:54:40.980Z","tsv":"'-4':786 '0.0':626,641,654 '0.10':582,585 '0.15':579 '0.2':621 '0.30':576 '0.35':573 '0.5':616,656 '1':107,112,200,244 '1.0':605,608,630,658 '100':586 '180':208 '2':141,202,239,268,278 '3':152,365,374,434,785,850 '30':619 '365':210 '4':228,535,558 '401':340 '5':182,674 '50':604 '6':375,865 '7':614,687,907 '90':624 'accept':539,762 'act':103 'action':98,727 'actual':23,738 'address':790 'advoc':78 'analysi':179,222,886 'analyst':49 'analyz':230,892 'angl':28,775,780 'announc':229,921 'answer':455,465,540,638,763 'appear':288 'appli':217 'approach':521,553 'array':151 'articl':480 'articul':651 'ask':256,449,533 'assess':645 'assign':441 'authent':355 'back':68,206,899 'backlog':72,923 'badg':811 'base':758 'belong':351 'best':520 'beyond':485 'block':147,165 'blog':477 'bodi':412 'bonus':581,629 'broaden':862 'categori':212 'check':113,153 'claim':834 'clariti':583,642 'classif':500 'classifi':90,435 'clear':391,648 'clearly-word':390 'cluster':85,92,240,252,271,273,307,320,357,368,372,384,402,432,437,440,561,589,596,634,800,900,903 'comment':198,415,603 'communiti':31,447,650,809 'comprehens':823 'concept':261,324 'conclus':827 'configur':509 'confus':9,266,328,361,396,471,653,757,792 'consensus':765 'consid':861 'contain':275 'content':6,27,42,48,69,466,527,555,770,836,932 'copi':752 'copy-past':751 'count':281,591 'critic':696 'data':189 'date':887,890 'day':205,615,620,625,895 'days-back':204 'debat':550 'decim':670 'defin':777 'delv':821 'deploy':349 'descend':695 'develop':77 'devrel':5,41,47 'devrel-backlog.md':916,926 'directori':120,920 'discuss':3,15,39,61,150,174,184,233,241,247,255,279,286,305,310,337,380,411,429,546,891 'discussions_raw.json':115,136,143 'doc':24,444,488,511,542,734,741,928 'document':71,459 'done':922 'draft':21,739 'els':640 'engag':428,574,597,841 'enough':188 'error':341 'etc':843 'everi':699,707 'evid':37,67,711,814 'evidence-back':66 'exact':681,779 'except':706 'excerpt':408 'exist':116,125 'explain':482 'express':393 'factual':464 'fals':639 'faq':479,740 'fewer':848 'field':157 'file':58 'filter':177,213,863 'find':7 'fix':25 'flag':297 'follow':164 'forc':304 'formula':567 'found':857,901 'founder':75,101,749 'frequenc':571,587 'full':566,912 'gap':445,512,543,735,929 'generat':675 'generic':725 'genuin':312 'get':339 'github':2,14,38,60 'github-discussion-to-devrel-cont':1 'goe':484 'good':475 'group':248 'header':870 'high':659 'histori':897 'hit':263 'identifi':191,934 'immedi':105 'includ':702,710,805 'increas':203 'input':111 'instruct':126 'integ':666 'item':99,293,319,688,700,708,851 'job':51 'json':57 'keyword':335 'label':373 'least':277 'leav':314 'level':334 'leverag':824 'like':541,554 'link':35 'list':378 'load':108 'long':549 'low':155,159,168,224,291,655 'low-prior':290 'major':632,795 'make':473 'markdown':682,745,881,913 'max':592 'may':287,350 'meta':146 'meta.days':898 'meta.mode':237,905 'meta.repo':235,885 'meta.total':172,231,893 'min':197,599 'min-com':196 'mode':236,904 'moder':657 'most-engag':426 'multipl':254,552 'must':274,295,404,701,709,729,804 'n':854,927,931 'nearest':665 'normal':56 'note':831,852 'number':381 'occurr':301 'one':215,343,442 'opportun':467,528,556,771,933 'otherwis':627 'outcom':838 'outlin':776,788 'output':96,135,162,495,669,676,684,697,723,866,880,909 'owner/repo':134 'pain':810 'paraphras':418,720 'pars':144 'pass':175 'past':753 'pattern':193,284,855 'per':689 'perform':837 'point':267,787 'post':478 'primari':420 'prioriti':292,569,671,693 'proceed':220 'produc':63 'product':458 'python':131 'qualifi':173,183,232,492,894 'question':451,461,469,504,515,531 'quot':32,387,712,815 'rank':16,65,691,840 'rate':842 'reaction':601 'read':54,142,245,562,677 'recenc':577,606 'recommend':774 'record':369 'recur':8,88 'reduc':195 'references/output-format.md':678 'references/scoring-guide.md':563 'reliabl':192 'remov':211 'repo':12,133,884 'report':876,914 'repres':386 'root':360 'round':660 'rule':269,501,698 'run':130,868,882 'save':908 'scenario':525 'score':93,559,570,572,575,578,584,588,598,607,643,662,672,694 'scripts/fetch_discussions.py':132 'seamless':825 'section':499,690,846,860,879 'seo':839 'setup':356 'short':371 'signal':156,160,169,225 'simpl':487 'singl':285,300 'single-occurr':299 'skill':43 'skill-github-discussion-to-devrel-content' 'snippet':746 'solv':755 'sourc':34,421,703 'source-varnan-tech' 'spawn':547 'standalon':318 'step':106,238,433,557,673,864,906 'stop':138,167 'structur':97,683 'suggest':194,726 'summar':82 'summari':568,869,883 'surfac':333 'surface-level':332 'take':782 'testament':822 'text':714 'themat':251 'theme':89,243 'thread':83,399,590,593,611,635,717,768,797 'threshold':180 'today':888 'token':345 'top':873 'topic-agent-skills' 'topic-gtm' 'topic-hermes-agent' 'topic-marketing-skills' 'topic-openclaw-skills' 'topic-skill-pack' 'topic-skills' 'topic-technical-seo' 'total':600,602,902 'true':161,227 'tutori':476 'unansw':580,628,802 'under':260,323 'uniqu':313 'unresolv':808 'updat':489,612,742 'urgenc':19 'urgent':807 'url':422,423,704 'use':818 'user':128,326,536 'valid':110 'verbatim':30,407,713 'wait':140 'warn':170 'within':613,618,623 'word':376,392,820 'work':119,347,732,919 'worth':830 'would':472 'write':736,772,910 'written':924 'x':510,523 'y':526","prices":[{"id":"a7e341d0-c310-4690-ac64-cfc24c166363","listingId":"7cbb2377-7630-4ec4-bf59-f90b7bbd8648","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Varnan-Tech","category":"opendirectory","install_from":"skills.sh"},"createdAt":"2026-05-18T18:54:40.980Z"}],"sources":[{"listingId":"7cbb2377-7630-4ec4-bf59-f90b7bbd8648","source":"github","sourceId":"Varnan-Tech/opendirectory/github-discussion-to-devrel-content","sourceUrl":"https://github.com/Varnan-Tech/opendirectory/tree/main/skills/github-discussion-to-devrel-content","isPrimary":false,"firstSeenAt":"2026-05-18T18:54:40.980Z","lastSeenAt":"2026-05-18T18:54:40.980Z"}],"details":{"listingId":"7cbb2377-7630-4ec4-bf59-f90b7bbd8648","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Varnan-Tech","slug":"github-discussion-to-devrel-content","github":{"repo":"Varnan-Tech/opendirectory","stars":286,"topics":["agent-skills","gtm","hermes-agent","marketing-skills","openclaw-skills","skill-pack","skills","technical-seo"],"license":"mit","html_url":"https://github.com/Varnan-Tech/opendirectory","pushed_at":"2026-05-18T18:27:10Z","description":" AI Agent Skills built for Founders who hate Marketing","skill_md_sha":"a09b9d5b51f5830b1acc259e4defa88b0b4bca4c","skill_md_path":"skills/github-discussion-to-devrel-content/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Varnan-Tech/opendirectory/tree/main/skills/github-discussion-to-devrel-content"},"layout":"multi","source":"github","category":"opendirectory","frontmatter":{"name":"github-discussion-to-devrel-content","description":"Find recurring confusion in your repo's GitHub Discussions, rank it by urgency, and draft the actual docs fixes and content angles — with verbatim community quotes and source links as evidence.","compatibility":"[claude-code, gemini-cli, github-copilot]"},"skills_sh_url":"https://skills.sh/Varnan-Tech/opendirectory/github-discussion-to-devrel-content"},"updatedAt":"2026-05-18T18:54:40.980Z"}}