agentsclimarketplace

Docs & writing

16,621 rows, by stacks then stars

3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid

  • Writing voice

    dineshrevunuru/SuperSkills/writing-voice Skill

    1★ repo

    Write any content in Dinesh Reddy Revunuru's voice — automatically choosing the right register. Trigger this skill for ANY writing task Dinesh asks for — case studies, portfolio narratives, articles, blog posts, LinkedIn posts, stakeholder memos, research reports, email drafts, cover letters, or general writing help. Also trigger when he says 'write this in my style,' 'help me write,' 'draft,' 'rewrite this,' or any variant involving producing written content. Auto-selects the best register unless Dinesh specifies one. When in doubt, trigger this skill.

  • Changelog

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/changelog Skill

    1★ repo

    Use when you cut a release or want a CHANGELOG entry derived from conventional commits and PRs without hand-writing it.

  • I18n

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/i18n Skill

    1★ repo

    Use when an app needs localization and you must extract user-facing strings and scaffold translation files without breaking existing copy.

  • Readme badge

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/readme-badge Skill

    1★ repo

    Use when you want to add accurate, up-to-date status badges (build, version, license, coverage, PyPI) to a README and avoid broken, stale, or misleading shields.

  • Release notes

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/release-notes Skill

    1★ repo

    Use when a version is shipping and you need release notes or an announcement that highlights impact for users, not the commit log.

  • Write tests

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/write-tests Skill

    1★ repo

    Use when a module or function lacks tests and you need to generate meaningful unit or integration tests that cover the real behaviour.

  • Xlsx

    nguyenthdat/opencode-starter/skills/xlsx Skill

    1★ repo

    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

  • Engineering docs

    mblauberg/provenant/skills/engineering-docs Skill

    1★ repo

    Use for creating, placing, indexing, updating, or archiving engineering docs and docs structures. Not for prose-only rewriting or session continuity; use engineering-writing or session.

  • Engineering writing

    mblauberg/provenant/skills/engineering-writing Skill

    1★ repo

    Use for drafting or condensing software-engineering prose such as requirements/specs, READMEs, commits, PRs, runbooks, errors, and design notes. Not for general, academic, or Australian legal prose.

  • Legal writing

    mblauberg/provenant/skills/legal-writing Skill

    1★ repo

    Use for drafting, reviewing, condensing, or source-checking Australian legal documents (forms, affidavits, submissions and orders), legal decision overviews, or correspondence. Not for academic, engineering, or general prose; use its specialist.

  • Natural writing

    mblauberg/provenant/skills/natural-writing Skill

    1★ repo

    Use for making general or mixed prose natural and direct while preserving facts, citations, numbers, and intent. Not for engineering, academic, or Australian legal prose; use its specialist.

  • Documentation

    furkangonel/cowrangler/bundled_skills/documentation Skill

    1★ repo

    Code documentation SOP — JSDoc, inline comments, README, and API docs standards

  • Docx

    furkangonel/cowrangler/bundled_skills/docx Skill

    1★ repo

    Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. Trigger for: - [TODO: Add specific triggers for when to use this skill] Don't trigger for: - [TODO: Add anti-triggers for when NOT to use this skill]

  • Localization

    furkangonel/cowrangler/bundled_skills/localization Skill

    1★ repo

    Localize (not just translate) text, UI content, or marketing copy to feel native in the target culture

  • Testing

    furkangonel/cowrangler/bundled_skills/testing Skill

    1★ repo

    Test writing SOP for unit, integration, and e2e tests (TDD) plus exploratory QA for web apps — find bugs, gather evidence, write reports.

  • Xlsx

    furkangonel/cowrangler/bundled_skills/xlsx Skill

    1★ repo

    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \ Trigger for: - [TODO: Add specific triggers for when to use this skill] Don't trigger for: - [TODO: Add anti-triggers for when NOT to use this skill]the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved."

  • Create only idempotent artifact write

    vishuwa2004/cskill-agents/agents/claude-code/skills/create-only-idempotent-artifact-write Skill

    1★ repo

    Persist deterministic artifacts with a create-only write and treat existing files as replay success instead of an error.

    The same file is in 1 other repository

  • Legacy wire name compat translation

    vishuwa2004/cskill-agents/agents/claude-code/skills/legacy-wire-name-compat-translation Skill

    1★ repo

    Translate renamed internal identifiers back to their legacy wire names at serialization boundaries so patch-level consumers keep working until the planned version cutoff.

    The same file is in 1 other repository

  • Create only idempotent artifact write

    vishuwa2004/cskill-agents/agents/codex/skills/create-only-idempotent-artifact-write Skill

    1★ repo

    Persist deterministic artifacts with a create-only write and treat existing files as replay success instead of an error.

    The same file is in 1 other repository

  • Legacy wire name compat translation

    vishuwa2004/cskill-agents/agents/codex/skills/legacy-wire-name-compat-translation Skill

    1★ repo

    Translate renamed internal identifiers back to their legacy wire names at serialization boundaries so patch-level consumers keep working until the planned version cutoff.

    The same file is in 1 other repository

  • Create only idempotent artifact write

    vishuwa2004/cskill-agents/skills/create-only-idempotent-artifact-write Skill

    1★ repo

    Persist deterministic artifacts with a create-only write and treat existing files as replay success instead of an error.

    The same file is in 1 other repository

  • Legacy wire name compat translation

    vishuwa2004/cskill-agents/skills/legacy-wire-name-compat-translation Skill

    1★ repo

    Translate renamed internal identifiers back to their legacy wire names at serialization boundaries so patch-level consumers keep working until the planned version cutoff.

    The same file is in 1 other repository

  • Compare versions

    OC-NeuralSense/reader-first-writing-skills/skills/compare-versions Skill

    1★ repo

    Evaluative. Activate when two versions of the same text exist and the writer wants to know what changed, whether it is actually better, and whether any caveats were lost. Common phrasings: "Show me what changed and whether it's better", "Did my edits drop any important caveats or hedges?", "Explain why the revised version is an improvement". Expected inputs: the original, the revised version, the preservation intent, and the reader-frame. Produces a change-report that classifies each change as meaning-altering or meaning-preserving and lists every dropped qualifier with its original location. Do NOT activate when only one version exists (use diagnose-draft), or when the writer wants the change made rather than judged (use revise-prose / revise-structure). This skill judges two versions; it never edits the text.

  • Diagnose draft

    OC-NeuralSense/reader-first-writing-skills/skills/diagnose-draft Skill

    1★ repo

    Diagnostic skill: report what is wrong with a draft, keeping structural faults and prose faults on separate layers. Reports; does not rewrite. Use when the user says "this draft feels off -- tell me what's wrong", "list the faults and where they are", "where are the problems in this document". Common phrasings: "diagnose this", "what's broken here", "give me a fault list". Inputs: a draft plus a reader-frame. Each finding cites a location and the concrete test it failed, on a distinct structure or prose layer, with blocking/non-blocking severity. NOT for a fast pass that also fixes (use quick-pass), NOT for applying fixes (use revise-structure / revise-prose), NOT for a ship go/no-go (use review-document audit). Depth quick, standard, or deep. Produces a defect-report contract only; it never edits the user's draft.

  • Draft prose

    OC-NeuralSense/reader-first-writing-skills/skills/draft-prose Skill

    1★ repo

    Generative skill: draft continuous prose from an approved, validated outline. Use when the user says "draft the prose from this outline", "write this up from the plan", "turn this approved structure into prose", or hands over a validated argument-blueprint ready to render. Common phrasings: "draft it", "write the body from the plan", "render the outline". Inputs: an argument-blueprint (validated outline) plus a reader-frame. Renders every outline node into prose as revisable raw material and introduces no claim, relation, number, or qualifier the outline does not already contain. NOT for building or validating structure (use build-argument), NOT for fixing an existing draft (use diagnose-draft / revise-prose / revise-structure), NOT when no validated outline exists yet. Produces draft prose plus a node-to-prose map.

  • Frame the brief

    OC-NeuralSense/reader-first-writing-skills/skills/frame-the-brief Skill

    1★ repo

    Diagnostic. Activate when the writer has not yet settled who the document is for, why it exists, or what type it is. Common phrasings: "Who am I writing this for and what do they already know?", "Help me pin down the reader / audience / situation", "What kind of document is this and what must it do?". Expected inputs: a brief or topic, any audience hints, and an optional draft. Produces a reader-frame that every later stage reads from. Do NOT activate when a settled reader profile already exists and the writer wants structure (use build-argument), when they want an existing structure's logic checked (use test-argument), or when they want sentence-level fixes (use revise-prose). This skill only frames; it never outlines, argues, drafts, or edits prose.

  • Review document

    OC-NeuralSense/reader-first-writing-skills/skills/review-document Skill

    1★ repo

    Evaluative. Activate to review or assess a near-final document against its reader-facing goals through the lens its genre calls for, up to a ship decision. Common phrasings: "Review this executive summary", "Review the argument in this paper section", "Review this explainer for a general reader", "Review this technical explanation", "Review this policy memo" (business_analytical sub-case), "Is this ready to ship?" (audit gate). Expected inputs: the document, reader-frame, genre, communicative aim, preservation intent. Produces a defect-report and, at audit depth, a go/no-go ship decision. Deep and audit depth route through an independent reviewer. Do NOT activate for a fast surface once-over (use diagnose-draft quick), or when the writer wants the full multi-perspective run itself (deep-review workflow). Genre is asked, never guessed; this skill judges, it never edits the text.

  • Revise prose

    OC-NeuralSense/reader-first-writing-skills/skills/revise-prose Skill

    1★ repo

    Revisional. Activate to fix the flow, clarity, length, or thinness of sentences and paragraphs for the SAME reader, without changing meaning. One skill, five task modes. Phrasings: "the paragraphs don't hang together, fix the flow" (cohere), "make these sentences clearer" (clarify), "cut this down without losing anything important" (compress), "this part is too thin, expand it" (expand), "fix the grammar / settle this punctuation" (usage). Expected inputs: a passage, a reader-frame, the task_mode, and an optional target length. Produces a revised passage plus a change-report. Do NOT activate when the incoherence is a structural gap (escalate to revise-structure) or when the request is to recalibrate for a DIFFERENT audience (use adapt-to-reader). Same reader, prose surface only; it never rebuilds the argument.

  • Revise structure

    OC-NeuralSense/reader-first-writing-skills/skills/revise-structure Skill

    1★ repo

    Revisional skill: repair a document's structure while holding meaning constant. Use when the user says "fix the structure of this document", "re-group / re-order / re-summarize these points", "the arrangement is wrong", once a structural defect is known. Common phrasings: "restructure this", "reorganize the argument", "the sections are in the wrong order". Operations: re-group, re-order, re-summarize parents, cut claims. The named defect must stop reproducing while the pre/post claim set stays identical -- meaning is the supreme invariant. NOT for sentence flow, clarity, length, or thinness (use revise-prose), NOT for merely detecting faults (use diagnose-draft / test-argument). Inputs: draft-or-outline, argument-blueprint, defect-report. Produces a revised structure plus a change-report; fidelity overrides tidiness.

  • Teach revision

    OC-NeuralSense/reader-first-writing-skills/skills/teach-revision Skill

    1★ repo

    Instructional. Activate when a learner wants to be walked through improving their own draft so they learn to do it themselves, not just handed a fixed version. Common phrasings: "Walk me through improving this so I learn to do it myself", "Teach me why these edits work". Expected inputs: the learner's draft, the learner's level, and the reader-frame. Produces a staged revision in which every move names the defect, the concrete test it failed, and the principle behind the fix, so the learner could re-apply the test unaided. Do NOT activate when the writer just wants the document fixed rather than taught (use the revise-* skills). This skill teaches through revision; it may edit the draft, but only as annotated, tested, explained moves, never a silent fix.

  • Test argument

    OC-NeuralSense/reader-first-writing-skills/skills/test-argument Skill

    1★ repo

    Evaluative. Activate to check whether a set of claims actually supports its conclusion and to find anything unsupported. Common phrasings: "Do these points actually support my conclusion?", "Find any claims here that aren't actually supported", "Is this parent a real summary of its children?". Expected inputs: an argument-blueprint, or a bare conclusion plus its claims. Reports defects on the soundness layer; it NEVER rewrites, re-groups, or drafts. Do NOT activate when the user wants a full layered draft diagnosis across structure and prose (use diagnose-draft), wants the structure built from scratch (use build-argument), or wants defects actually fixed (use revise-structure). This skill only judges soundness and produces a report.

  • Description frontmatter authoring

    jesse-black/docgarden/skills/description-frontmatter-authoring Skill

    1★ repo

    Create or revise Markdown `description` frontmatter so `docgarden match` routes agents to the right repository documents. Use when adding a new routed Markdown document, updating existing frontmatter, fixing noisy or missing match results, tuning skills or docs discovery, or making descriptions more query-aligned without loading document bodies.

  • Gogcli mcp docs

    chrischall/gogcli-mcp/io.github.chrischall/gogcli-mcp-docs MCP server

    1★ repo

    Extended Google Docs for Claude via gogcli — auth + full Docs and comments support

  • Changelog forge mcp

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/changelog-forge-mcp MCP server

    no license1★ repo

    Generate changelogs from git commit history

  • Changelog

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/changelog MCP server

    no license1★ repo

    MCP server for generating changelogs from conventional commits.

  • Markdown

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/markdown MCP server

    no license1★ repo

    MCP server for markdown: tables, TOC, HTML conversion, formatting.

  • Markdown forge mcp

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/markdown-forge-mcp MCP server

    no license1★ repo

    Markdown processing, TOC generation, HTML conversion

  • Readme

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/readme MCP server

    no license1★ repo

    MCP server for README.md generation from project metadata

  • Readme forge mcp

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/readme-forge-mcp MCP server

    no license1★ repo

    Generate professional README.md files from project analysis

  • Knowledgeowl

    m190/usefulapi-mcp/io.usefulapi/knowledgeowl MCP server

    1★ repo

    Read and write knowledge-base articles, categories, snippets, glossary, readers, and search data.

  • Github

    sakydev/claude/skills/github Skill

    no license0★ repo

    Use this skill before creating a branch, writing a commit message, or opening a pull request in this project. Trigger on: "create a branch", "commit this", "write a commit message", "open a PR", "create a pull request", "what should I name this branch", or any time a GitHub workflow action is about to happen.

  • Writing

    sakydev/claude/skills/writing Skill

    no license0★ repo

    Use this skill whenever the user shares writing and asks for feedback, critique, a review, or wants you to "be honest" about their work. Trigger on phrases like "critique this", "what do you think of this", "tear this apart", "give me feedback", "is this working", "how's my prose", or any time the user pastes fiction, journal writing, or prose and asks for an opinion. Do not water down the feedback. This skill exists to make the user a better writer, not to make them feel good.

  • Readme generator

    claudifytech/claude-code-skills-starter/skills/readme-generator Skill

    0★ repo

    Draft or refresh a project README from the codebase, not from guesswork

  • Test writer

    claudifytech/claude-code-skills-starter/skills/test-writer Skill

    0★ repo

    Generate tests that match the project's existing test patterns and framework

  • Editing pass

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/editing-pass Skill

    0★ repo

    Read-and-revise pass for any drafted post. Applies writing-style.md checklist, tightens prose, kills filler. Run after drafting and before ai-slop-check.

    The same file is in 1 other repository

  • Long form weekly newsletter

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/long-form-weekly-newsletter Skill

    0★ repo

    Weekly newsletter — the parent piece of the week. ~600-1200 words. Drafted Sunday. Spawns 5-7 derivative short-form pieces for X / LinkedIn / Threads via /write Phase 5. The recurring Sunday default.

    The same file is in 1 other repository

  • Review

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/review Skill

    0★ repo

    Parallel review of a draft along multiple focuses (voice, structure, slop, hook, closer, optional factual). Spawns N subagents concurrently — each with a single focus and the user's writing-style — then aggregates findings into one severity-grouped report. Use full mode mid-draft or as a pre-publish gate; use delta mode (--since-last / --since <ref>) to review only what changed since the last snapshot or git ref — 3 focuses instead of 5, ~5s instead of ~10s, ~80% fewer tokens.

    The same file is in 1 other repository

  • Write publish

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/write-publish Skill

    0★ repo

    Publishes a `status: ready` draft from the weekly calendar to its configured target (Astro blog collection) and archives social derivatives. Reads scribetronic/publish-config.yaml. Updates calendar history and per-week plan. Optionally archives completed weeks. Does NOT push to social platforms (out of scope v1).

    The same file is in 1 other repository

  • Write

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/write Skill

    0★ repo

    Master writing skill. Orchestrates the full pipeline (seed → draft → edit → slop-check → optional repurpose) for any post type — long-form (long-form-weekly-newsletter, long-form-monthly-devlog, long-form-hot-take, long-form-how-to, long-form-launch-retro, long-form-manifesto) or short-form (short-form-x-vs-y, short-form-listicle, short-form-observation, short-form-motivational, short-form-present-vs-future, short-form-thread-from-longform, short-form-carousel-li). Drafts live inside the active week's calendar directory. Invoke with `/write <type> "<seed>"` or just `/write` to be routed via interview. Interactive by default, autonomous with --auto.

    The same file is in 1 other repository

  • Writing style

    r-bart/scribetronic-plugin/plugins/scribetronic/skills/writing-style Skill

    0★ repo

    The shared style guide every long-form and short-form post inherits. Reference for tone, structure, sentence rhythm, signature moves, and anti-patterns. Always loaded by drafting and editing skills. This is the only skill that should be personalized — every other skill stays format-only.

    The same file is in 1 other repository

  • Coherency check

    giovicordova/skills-gc/skills/coherency-check Skill

    no license0★ repo

    Cross-document and cross-code coherency analysis — finds contradictions, conflicting values, and inconsistencies across multiple files, then researches official sources to resolve factual errors and asks the user only about preference decisions. MUST use this skill whenever the user asks to compare, cross-check, cross-reference, or verify consistency between 2+ files of any type — docs, configs, code, specs, design tokens, changelogs, READMEs. Trigger phrases include but are not limited to: 'check these are consistent', 'do these contradict', 'make sure everything aligns', 'find inconsistencies', 'cross-check', 'cross-reference', 'telling the same story', 'out of sync', 'gotten out of date', 'don't match', 'disagree', 'drifted'. Also trigger when the user names specific files and asks if they conflict, even without using the word coherency. If the user mentions multiple files and wants to know whether they agree — that's this skill. Do NOT skip this skill just because you could read the files yourself; the skill provides structured claim extraction, severity classification, factual-vs-preference triage, official-source research, and interactive resolution that ad-hoc comparison misses.

  • Philosophier

    giovicordova/skills-gc/skills/philosophier Skill

    no license0★ repo

    Compresses verbose text into the shortest precise phrasing that preserves every constraint and leaves zero ambiguity. Use whenever the user wants to shorten, compress, tighten, distill, or cut down any text — CLAUDE.md sections, README files, AGENTS.md personas, CONTRIBUTING.md, commit messages, error messages, package descriptions, or any prose that says too much with too many words. Also use when writing new documentation content from scratch that should be maximally concise. Trigger phrases: 'philosophier', 'distill this', 'make this shorter', 'compress this', 'tighten this up', 'cut it down', 'too wordy', 'too verbose', 'every line should carry weight', 'say more with less'. If a user pastes a paragraph and asks for it shorter — this is the skill. If they link a file and say it's too long — this is the skill.

  • Working backwards

    tomaszstaniak/pm-ai-skills/working-backwards Skill

    0★ repo

    Amazon's Working Backwards product development method based on Colin Bryar and Bill Carr's "Working Backwards". Use this skill whenever the user is discussing a new product, feature, pitch, or launch narrative — even if they do not explicitly say "PR/FAQ," "press release," or "working backwards." Triggers include: (1) writing or reviewing a PR/FAQ for a new product or feature, (2) drafting the launch narrative or announcement story for something not yet built, (3) validating an idea by defining the customer experience first, (4) evaluating an internal idea pitched by a teammate or exec, (5) structuring a 6-pager or narrative memo for an exec review, (6) stress-testing a proposal with pre-mortem analysis, (7) aligning stakeholders around a product vision, (8) deciding whether an idea is worth building before writing code, (9) sharpening a fuzzy product concept into a customer-facing story, (10) running a go/no-go decision meeting on a new initiative.

  • Stakeholder translation

    thinkyou0714/claude-lab-skills/lab-communication-translation/skills/stakeholder-translation Skill

    0★ repo

    技術的な実装内容・判断・リスクを、非エンジニアのステークホルダーが理解できる言葉に変換する。「何が起きているか」「何が必要か」「何を決めてほしいか」を明確に伝える。非エンジニアへ報告・説明するときに使う。

  • Negative result branches

    abedegno/reverse-engineering-companion/plugins/reverse-engineering-companion/skills/negative-result-branches Skill

    0★ repo

    Discipline for preserving failed optimisation experiments. Branch per hypothesis, commit message captures the empirical number, reference branches in docs so future-you doesn't reinvent the failed approach. Use whenever you have an optimisation hypothesis that might pay off but isn't certain — default to "build it on a branch, measure honestly, document the result, leave the branch around even if it didn't win."

  • Editing pass

    r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/editing-pass Skill

    0★ repo

    Read-and-revise pass for any drafted post. Applies writing-style.md checklist, tightens prose, kills filler. Run after drafting and before ai-slop-check.

    The same file is in 1 other repository

  • Long form weekly newsletter

    r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/long-form-weekly-newsletter Skill

    0★ repo

    Weekly newsletter — the parent piece of the week. ~600-1200 words. Drafted Sunday. Spawns 5-7 derivative short-form pieces for X / LinkedIn / Threads via /write Phase 5. The recurring Sunday default.

    The same file is in 1 other repository

  • Review

    r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/review Skill

    0★ repo

    Parallel review of a draft along multiple focuses (voice, structure, slop, hook, closer, optional factual). Spawns N subagents concurrently — each with a single focus and the user's writing-style — then aggregates findings into one severity-grouped report. Use full mode mid-draft or as a pre-publish gate; use delta mode (--since-last / --since <ref>) to review only what changed since the last snapshot or git ref — 3 focuses instead of 5, ~5s instead of ~10s, ~80% fewer tokens.

    The same file is in 1 other repository

  • Write publish

    r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/write-publish Skill

    0★ repo

    Publishes a `status: ready` draft from the weekly calendar to its configured target (Astro blog collection) and archives social derivatives. Reads scribetronic/publish-config.yaml. Updates calendar history and per-week plan. Optionally archives completed weeks. Does NOT push to social platforms (out of scope v1).

    The same file is in 1 other repository

  • Write

    r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/write Skill

    0★ repo

    Master writing skill. Orchestrates the full pipeline (seed → draft → edit → slop-check → optional repurpose) for any post type — long-form (long-form-weekly-newsletter, long-form-monthly-devlog, long-form-hot-take, long-form-how-to, long-form-launch-retro, long-form-manifesto) or short-form (short-form-x-vs-y, short-form-listicle, short-form-observation, short-form-motivational, short-form-present-vs-future, short-form-thread-from-longform, short-form-carousel-li). Drafts live inside the active week's calendar directory. Invoke with `/write <type> "<seed>"` or just `/write` to be routed via interview. Interactive by default, autonomous with --auto.

    The same file is in 1 other repository