Blog Writer
google/adk-recipes
Blog post writing skill with structure templates and style guidelines.
在博客 WQ/WR 双线工作流中连续完成搜索导向调研、写作、图片和载荷;默认做同上下文对抗式自查,高风险升级独立 R。用于研究、撰写、修订和准备人工发布文章包。
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install flaqai/backlink_skills blog-3p-writer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .claude/skills/blog-3p-writer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .claude/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install flaqai/backlink_skills blog-3p-writer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .agents/skills/blog-3p-writer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .agents/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install flaqai/backlink_skills blog-3p-writer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .cursor/skills/blog-3p-writer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .cursor/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/flaqai/backlink_skills.git --path blog-3p-skill-matrix/skills/blog-3p-writer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install flaqai/backlink_skills blog-3p-writer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .gemini/skills/blog-3p-writer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .gemini/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install flaqai/backlink_skills blog-3p-writerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .github/skills/blog-3p-writer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .github/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add flaqai/backlink_skills --skill blog-3p-writer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install flaqai/backlink_skills blog-3p-writer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flaqai/backlink_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/blog-3p-skill-matrix/skills/blog-3p-writer .opencode/skills/blog-3p-writer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "blog-3p-writer" agent skill from https://github.com/flaqai/backlink_skills/tree/main/blog-3p-skill-matrix/skills/blog-3p-writer into .opencode/skills/blog-3p-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-3p-writer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
blog-3p-writer在博客 WQ/WR 双线工作流中连续完成搜索导向调研、写作、图片和载荷;默认做同上下文对抗式自查,高风险升级独立 R。用于研究、撰写、修订和准备人工发布文章包。
Blog 3p Writer is an agent skill from flaqai/backlink_skills. 在博客 WQ/WR 双线工作流中连续完成搜索导向调研、写作、图片和载荷;默认做同上下文对抗式自查,高风险升级独立 R。用于研究、撰写、修订和准备人工发布文章包。
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/cross-language-seo.md`).
The repository describes itself as: Awesome skills for submitting url to free websites. Get more backlinks for your website to get more traffic. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 3c56c94. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Blog 3p Writer loads about 1.4k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 306 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from flaqai/backlink_skills at commit 3c56c94, republished under its MIT licence (© flaqai). 306 words, ~1,450 tokens.
.claude/skills/blog-3p-writer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.先阅读术语约定。你是当前 article_id 的可执行 W:调研与写作构成同一条证据链。普通文章可复用同一可见 W 角色会话,但每次只处理当前文章的隔离路径和契约;blog-writer-merged 只是编辑核心参考,绝不能被启动为第二个 W、第二轮调研或第二份文章包。
默认在 CONTINUOUS_CAMPAIGN_MAIN_SESSION 内的 articles/<article_id>/ 隔离路径工作,使用该文的 context/article-contract.json 和 reviews/review-index.json;WQ 须自行对抗式核验,却不得称作独立 R 审稿。不得跨路径混写、修改范围、决定发布、操作平台或用不可见 CLI 会话冒充角色。Git 工作树只在记录真实并发写入、高风险重写/回滚或用户要求 Git 隔离时使用。公开页差异归 G 批量只读检查,除非用户明确要求修改唯一基准稿或交付页,否则不重开 W。
article_id、有效的 OWNER_PREWRITE_PLAN_CONFIRMED、适用 REQ-*、冻结 topic_slot、语言/市场、必保留 CTA 与适用的平台/账号回执。确认前或方案要求修改时,不创建大纲、图片计划、来源台账、唯一基准稿或正文。冻结 AUTHOR_QA_INTEGRATED / WQ_SHARED_CONTEXT 时,按一条连续工作完成 RESEARCH → DRAFT → VISUALS → PAYLOAD → CANDIDATE_LOCK → ADVERSARIAL_SELF_QA → TARGETED_REPAIR → FINAL_BIND。先在 research/evidence-pack.json 建立证据差异与引用索引,再据此成稿、配图、编译载荷;不为形式等待 RESEARCH_APPROVED 或维护重复研究包。锁定候选稿后,利用共享上下文但从反方读者视角主动质疑核心主张/来源、读者任务、标题和本地用语、必要 CTA、图文邻接与交付保真;真实问题保留稳定 finding ID,聚焦修复后重新检查受影响依赖。最终回执只写实际问题/升级及当前证据包、基准稿、metadata、视觉清单、双载荷和 package 的哈希;零开放问题才可记 AUTHOR_QA_READY,不得写成独立 R 的 APPROVED 或逐项 PASS 清单。
evidence/shared/campaign-evidence-pack.json 有精确匹配且可复用的记录,写可选 campaign_shared_evidence 的 path、sha256、record_ids,并在 article_delta 写 decision、freshness_or_scope_check 与 additional_evidence_refs;只引用实际采用的记录,不复制整包或重写同一观察。两字段都缺表示无命中,正常继续本篇调研,绝不造空缓存。只将会显著改变读者决定或易变的主张(价格/日期、比较、性能、平台政策、高后果内容)标成可核验 material claim;不要把普通背景句机械拆成台账。creative_angle 只能作为编辑角度,不能充当关键词证据。若 Google Trends 数据不足、无结果或无明确趋势,不得反复试探或编造趋势理由:读者问题与选词仍须来自当前品牌站用语、地区 SERP 或已记录的模型翻译兜底;平台画像只可帮助选择技术深度、示例形式和交付结构,绝不能成为关键词、自然变体、搜索意图、当地需求或热门度的证据。CURRENT_BRAND_SITE → REGIONAL_SERP → MODEL_TRANSLATION_FALLBACK:先记录同语言、同地区、同意图的现有品牌页及采用或有据拒绝;再记录地区 SERP 自然变体;只有两次独立地区检索都无可用共识时,才可记录有理由和风险的 MODEL_TRANSLATION_FALLBACK。Google Trends 如可用,仅比较英文种子/英文候选,作为全球相对关注度背景;不能替代本地用语证据,也不能证明搜索量、低基数/高势头、本地需求、商业意图或模型能力。缺少 Breakout 或清晰趋势本身不阻塞研究或写作。topic_slot 内调整。若读者任务、核心意图、市场和承诺都未变,在 topic_slot_alignment 写 ALIGNED 与简短 within_slot_adjustments 即可,不重开 G 或 R。若证据表明本地意图不符、原选题无可靠依据,或必须换成另一个读者问题,写 TOPIC_EVIDENCE_CONFLICT、稳定冲突 ID、理由、证据引用和建议动作,停止换题并交同一 G 决定。G 的 KEEP_SLOT / NARROW_WITHIN_SLOT 决定须在 resolved_conflicts 和既有可见任务账本中对应记录后才可继续;PAUSE / OWNER_RECONFIRM_REQUIRED 不得由 W 绕过。W 绝不能直接修改 topic_slot。reader_intent_basis、platform_profile_use 与 evidence_posture,并记录读者问题、受众、批准变体、事实边界、视觉要求、读者价值承诺、CTA 声明和图片计划。共享包只允许精确引用 GLOBAL_ENGLISH_TRENDS、BRAND_SITE_VARIANT 或 REGIONAL_SERP_VARIANT;易变主张、平台政策/账号状态和 MODEL_TRANSLATION_FALLBACK 仍须本篇独立取证。平台画像如被采用,必须标为 TOPIC_FRAMING 或 FORMAT_ADAPTATION,且不得写入选词或需求证据。METHOD_TEMPLATE_NO_EXECUTION 只能交付读者可自行使用的比较设计、记录模板或试行方法,标题、正文和 CTA 不得暗示已验证、A/B 结果、稳定性或因果结论;DOCUMENTED_EMPIRICAL_RECORD 则须在完整 R 前具备协议、输入/设置、运行日志、评价标准和局限路径。每张计划图片要有章节锚点、相邻主张、独立读者作用、权利/来源、提示词或视觉简报、Alt 和图注。适用 LEAD/MIDDLE/CLOSING 策略时,首图只覆盖 LEAD,其余覆盖区和最低数量同样必须满足,除非用户确认例外。keyword-research.md、brief.md、source-ledger.md、visual-narrative-plan.md 和跨语言说明如有需要只能作为从 evidence pack 派生的查阅视图,不得手工双写或成为额外审批门。platform_title = canonical_title,不得把较短的纯关键词标题送入平台标题字段。关键词自然出现于标题、正文前段、有意义的小节与结尾,不追求密度。当冻结为 INDEPENDENT_R_ESCALATION / WR_INDEPENDENT,W 完成同样研究、成稿、图片和交付页,再交独立 R 作 FULL_REVIEW。仅 SEPARATE_RESEARCH_REVIEW_REQUIRED 的 WR 在写大纲或正文前提交研究部分,并取得 RESEARCH_APPROVED;它不能代替最终完整审稿。WQ 中如发现高后果/易变结论、冲突或缺失关键证据、误导性图片或实测、CTA 依据不清、重大读者传递风险、无法关闭的核心问题,登记触发 ID 与当前候选哈希,向 G 请求一次单向升级 WR;已升级不得自动降回 WQ。普通多语言、无 Trends、例行 CTA、有边界的 MODEL_TRANSLATION_FALLBACK 不是单独升级理由。若改变冻结选题/平台/账号,须用户重新确认,不能伪装质量路线升级。
在 articles/<article_id>/ 下创建唯一基准稿、metadata、evidence pack、visual manifest、reviews/、handoff/ 和 article-package.json。当前 schema-2.14 项目使用 evidence pack schema 1.3 与文章包 schema 1.5:metadata 是标题/SEO 元数据唯一来源,evidence pack 是本篇研究及共享引用唯一来源,visual manifest 是图片最终来源;package 只声明上游及哈希,不反指 handoff,也不双写链接/图片。schema-2.13 的默认独立 R 语义和更早版本保留历史兼容。当前只交接人工原生发布,不提供自动发布分支。
正文、metadata、链接、来源、CTA 与最终图片稳定后,仅从 package 所声明且哈希相符的上游用同一编译器生成 BLOG_3P_VISUAL_PAYLOAD@3 HTML/Markdown;不得手写、二次编辑或用另一正文/metadata。唯一基准稿须在每张图准确位置含独立 <!-- BLOG_3P_IMAGE:NN --> 标记,素材为存在且哈希匹配的编号 PNG/JPG/JPEG;不用聚合图槽或 WebP/GIF/SVG。编译后、WQ 最终自查或 WR 独立 R 前在内容项目根运行 harnessctl.py check-review-ready --workspace <campaign-root> --article-contract articles/<article_id>/context/article-contract.json --review-index articles/<article_id>/reviews/review-index.json --article-package articles/<article_id>/article-package.json。它只校验机械可审性,不产生质量结论。无 COMPANION_DUAL_READ_REQUIRED 时仅 HTML 为语义主面,出现回退才双读。WQ FINAL_BIND 后若读者可见内容/图片/载荷改变,重新锁候选并完成同一 W 的自查和新哈希回执,不使用 R_DELTA;WR 的完整 R 后有限改动才可交同一 R 做有界 R_DELTA,纯视觉可走 R_VISUAL_DELTA,不明风险转完整 R。禁止自行设计页面壳、CSS、脚本、按钮或图片卡;标题标签不证明公开页面结构。
普通修复读取审稿索引、开放问题项证据,保持问题 ID 并更新指纹。WQ 只记录真实问题、定向修复、最终 W 自查回执;WR 有明确批准基线及完整变更摘要才写 reviews/review-delta-N.json 并交同一 R 作有限复审。范围升级、哈希漂移、谱系不清或变更超过风险面时转完整 WR 审稿或用户确认。
维护 requirements-traceability.md,将适用 REQ-* 映射到唯一基准稿和可视化富文本交付页;映射不是质量结论。读者可见改动回到该文 WQ 自查或 WR 同一 R;仅公开页差异不重开写审。
以共享的本地 SEO ISSUES 参考审自查;只在 R 报告、审稿索引或 handoff 中记录实际 FINDING / WARN,不为全绿文章再生成逐项 PASS 副本。它是本地写作标准,不表示外部插件已运行;最终标题层级只能在 HUMAN_ACCEPTED 后由公开读者页渲染视觉确认。
日常先读流程核心、文章契约、审稿索引与本轮所涉证据;仅当范围、交接或传递风险实际相关时,按需读取共享契约或人工发布交接技能的对应段落。机器字段、路径和状态码保持不变。
© flaqai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in blog-3p-skill-matrix/skills/blog-3p-writer of flaqai/backlink_skills.
Open the folder on GitHubat commit 3c56c94
Blog 3p Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Blog 3p Writer this skillflaqai/backlink_skills | 756 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Blog Writergoogle/adk-recipes | 10k | — | ~316 | Automated safety check: Pass | Apache-2.0 | |
| Blog Writersundial-org/awesome-openclaw-skills | 663 | 1 repos | ~1.7k | Automated safety check: Pass | None | |
| Blog Writereunomia-bpf/eunomia.dev | 236 | — | ~361 | Automated safety check: Pass | MIT | |
| Blog WriterKonghaYao/peri | 226 | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Blog Writercaptainflasmr/ollama-buddy | 103 | — | ~2.1k | Automated safety check: Pass | GPL-3.0 |
google/adk-recipes
Blog post writing skill with structure templates and style guidelines.
sundial-org/awesome-openclaw-skills
This skill should be used when writing blog posts, articles, or long-form content in the writer's distinctive writing style.
eunomia-bpf/eunomia.dev
Write or revise bilingual eunomia.dev blog posts from primary sources, verify technical claims, and prepare them for publication without requiring a particular editor or model.
KonghaYao/peri
Peri 项目博客写作风格指南。当用户说"写博客"、"写文章"、"出稿"、 "按风格写"、"博客"时触发。也适用于用户丢过来素材说"帮我写篇博客"的场景。
captainflasmr/ollama-buddy
Write an Emacs blog post in James Dyer's voice for www.emacs.dyerdwelling.family.
sickn33/agentic-awesome-skills
Writes search-intent-led long-form articles with answer-first structure, FAQ coverage, internal links, and conversion paths for SEO and AEO.
flaqai/backlink_skills
SPD V1 Batch. An agent skill from flaqai/backlink_skills.
flaqai/backlink_skills
SPD V2 Quality. An agent skill from flaqai/backlink_skills.
flaqai/backlink_skills
微信公众号文章的选题、研究、写作、改稿、审稿与交付工作流。Use when creating, outlining, researching, rewriting, auditing, or packaging Chinese WeChat Official Account articles, 微信文章, 公众号推文, 公众号长文, 热点解读, 干货教程, 观点文, 故事文, 对比测评…
flaqai/backlink_skills
Build and maintain a reusable backlink-submission candidate pool with global deduplication, fee and brand classification, configurable batch exports, and executor feedback.
flaqai/backlink_skills
LinkedIn-native long-form article and newsletter writing workflow for LinkedIn and Google-to-LinkedIn topic discovery, business-depth research, professional thought leadership, evidence-led…
flaqai/backlink_skills
Medium-native long-form research, author-assistance, writing, editing, review, topic discovery, publication matching, and packaging workflow.
在博客 WQ/WR 双线工作流中连续完成搜索导向调研、写作、图片和载荷;默认做同上下文对抗式自查,高风险升级独立 R。用于研究、撰写、修订和准备人工发布文章包。. Blog 3p Writer is an agent skill from flaqai/backlink_skills.
Run `npx skills add flaqai/backlink_skills --skill blog-3p-writer -a claude-code`. Or copy the skill folder (blog-3p-skill-matrix/skills/blog-3p-writer in flaqai/backlink_skills) into .claude/skills/blog-3p-writer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add flaqai/backlink_skills --skill blog-3p-writer -a codex`. Or copy the skill folder (blog-3p-skill-matrix/skills/blog-3p-writer in flaqai/backlink_skills) into .agents/skills/blog-3p-writer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add flaqai/backlink_skills --skill blog-3p-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blog-3p-writer, .gemini/skills/blog-3p-writer, .github/skills/blog-3p-writer and .opencode/skills/blog-3p-writer in your project.
SKILL.md names no scripts, command-line tools or credentials: Blog 3p Writer is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Blog 3p Writer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Blog 3p Writer: Blog Writer (google/adk-recipes, 10k stars), Blog Writer (sundial-org/awesome-openclaw-skills, 663 stars), Blog Writer (eunomia-bpf/eunomia.dev, 236 stars) and Blog Writer (KonghaYao/peri, 226 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
flaqai (a GitHub organization) maintains it in flaqai/backlink_skills, which has 756 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on September 24, 2026.
Source: flaqai/backlink_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.