agentsclimarketplace

Docs & writing

16,614 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

  • Write a skill

    vincendiary/agents/skills/write-a-skill Skill

    no license0★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Documentation and adrs

    agent-packs/registry/skills/documentation-and-adrs Skill

    no license0★ repo

    Create and maintain useful documentation, public API notes, and architecture decision records. Use when decisions or APIs need durable context.

  • Technical writing

    agent-packs/registry/skills/technical-writing Skill

    no license0★ repo

    Write clear, accurate, and maintainable developer documentation — API references, tutorials, guides, and changelogs. Use when documenting APIs, onboarding new contributors, or creating user-facing technical content.

  • Typescript best practices

    agent-packs/registry/skills/typescript-best-practices Skill

    no license0★ repo

    Write type-safe TypeScript using strict settings, precise types, and disciplined migration patterns. Use when writing TS, reviewing types, or migrating from JavaScript.

  • Finance explainer

    KameronKales/planfi-skills/skills/finance-explainer Skill

    0★ repo

    Turn the depth of the planfi financial toolset into ONE long-form "noob → seasoned expert" blog post by fanning out a workflow of agents that research, distill, architect a table of contents, and write. Runs in two modes: a BROAD whole-of-personal-finance guide, or a DEEP single-topic deep dive (e.g. "529 college investing", "Roth conversions", "rent vs buy"). Invoke when someone says "write a beginner-to-expert personal finance guide", "distill all the planfi tools into a blog post", "write a deep-dive post on <topic>", "explain <topic> from scratch to mastery", "run finance explainer on 529 investing", or wants a single cohesive long-read that takes a complete beginner to confident. Produces a finished markdown article.

  • Writing release notes

    Mike-Jenkins-Org/skill-testing/staging/writing-release-notes Skill

    0★ repo

    Generates release notes from merged pull requests, grouping the changes into features, fixes, and chores so the notes read clearly. Use when the user asks to draft release notes, write a changelog, summarize merged PRs into release notes, or any time you need to write something describing recent code changes.

  • Docs from code

    vishnujchandran/.agents/skills/docs-from-code Skill

    no license0★ repo

    Generate and synchronize documentation from real code, scripts, configs, and tests to prevent documentation drift.

  • Expense report

    holzerjm/AgentDay-Example/projects/everyday/paypah-trail/skills/expense-report Skill

    0★ repo

    Parses receipt files with a deterministic script and assembles a monthly expense report with a CSV ledger. Use whenever asked to summarize receipts or expenses, break down or total spending by category or by month, build a spending ledger, or find duplicate or suspicious receipts.

  • Khub deposition update

    libenxier-beep/codex-custom-skills/skills/khub-deposition-update Skill

    0★ repo

    Use when a validated KHub route-plan must become an Obsidian note creation or append operation with source trace, template mapping, write guards, and execution reporting.

  • Writing plans

    libenxier-beep/codex-custom-skills/skills/writing-plans Skill

    0★ repo

    Use when the user asks for an implementation plan or when a multi-step, high-risk change needs an explicit execution contract before edits begin. Do not use for simple tasks that can be safely implemented and verified directly.

  • Import rca

    stevancris/sre-ai-agent/skills/import-rca Skill

    0★ repo

    Transform any RCA or postmortem document into a reusable knowledge-base pattern. Accepts any company format — Google SRE, Atlassian, PagerDuty, Elastic, plain text, Confluence export, or free-form notes. Extracts and distills the incident into a structured failure pattern that the agent can search in future incidents. Trigger keywords: import rca, convert postmortem, add to knowledge base, import incident, we have an old RCA, transform postmortem, bulk import RCA, add past incident, import from confluence, convert our incident report.

  • Oncall runbook

    stevancris/sre-ai-agent/skills/oncall-runbook Skill

    0★ repo

    Look up, execute, and maintain on-call runbooks. Use when you receive an alert, need step-by-step remediation guidance, want to find the right runbook for a service, or need to create a new runbook for an alert that currently has none. Trigger keywords: runbook, on-call, oncall, alert firing, pagerduty, opsgenie, what do I do, how do I fix, remediation steps, service down, alert triggered, need guidance, step by step.

  • Postmortem

    stevancris/sre-ai-agent/skills/postmortem Skill

    0★ repo

    Create blameless postmortems after incidents are resolved. Use when an incident is over, during post-incident review, or when writing a retrospective. Covers timeline reconstruction, contributing factor analysis, action item generation, and distribution. Trigger keywords: postmortem, post-mortem, post incident review, PIR, retrospective, blameless, lessons learned, what went wrong, action items, incident review, follow-up, write up, incident report.

  • Rfc

    stevancris/sre-ai-agent/skills/rfc Skill

    0★ repo

    Draft, review, and iterate on RFC (Request for Comments) documents for infrastructure, reliability, and platform changes. Use when proposing a significant technical change, new architecture, major process shift, or any decision that needs cross-team alignment before implementation. Covers problem framing, solution options, trade-off analysis, risk assessment, and rollout plan. Trigger keywords: RFC, request for comments, proposal, design doc, design document, architecture proposal, ADR, architecture decision record, technical proposal, propose a change, write a proposal, get alignment, we need to decide, compare options, technical decision, platform change, migration plan, new architecture.

  • Runbook generator

    stevancris/sre-ai-agent/skills/runbook-generator Skill

    0★ repo

    Generate complete, actionable runbooks for services, alerts, and operational procedures. Use when an alert has no runbook, when onboarding a new service, when standardizing operational documentation, or when updating stale runbooks. Trigger keywords: generate runbook, create runbook, write runbook, runbook template, document procedure, operational guide, no runbook exists, runbook missing, new service runbook, need a runbook, write up steps, document this alert, how do I document, onboarding docs, ops documentation.

  • Documentation skill

    ChristinaAgent/OpenSkillBench/examples/documentation-skill Skill

    0★ repo

    Improve technical documentation so it is accurate, task-oriented, and easy for developers to apply.

  • Ingest link

    mike623/agent-skills/skills/ingest-link Skill

    no license0★ repo

    Use when turning any saved link (YouTube/Instagram/TikTok/X reel, article, GitHub repo, paper, or social post) into a source-grounded, cited, deduplicated second-brain note. Three layers: (1) acquire + comprehend the media itself — reads video frames and transcribes audio, not just captions; (2) deep-research the topic on the open web to surface what the source omitted (criticism, alternatives, recency); (3) synthesize a provenance-tagged Markdown note, dedup against the vault, and write it to an Obsidian inbox. Trigger on "ingest this", "ingest-link <url>", "add this to my second brain", or a pasted link to process into a research note.

  • Raindrop bookmark curator

    mike623/agent-skills/skills/raindrop-bookmark-curator Skill

    no license0★ repo

    Curate Raindrop.io bookmarks by scanning recent or state-tracked items, extracting public content, renaming titles, updating bookmark notes/descriptions, adding tags, sorting into collections, optionally writing Markdown/Obsidian notes, and maintaining a safe state file.

  • Loam adding to memory

    scchearn/loam/skills/loam-memory/loam-adding-to-memory Skill

    0★ repo

    Read a local source file or synthesize conversation context, then integrate admitted content directly into topic, entity, concept, and analysis pages in existing memory (the wiki substrate). Use this when the user wants to add a source to the wiki, add a document, ingest a local note, transcript, article, report, or PDF, or explicitly preserve the current conversation as a topic note. For session-learning routing across wiki, guidance, checkpoint, task annotation, or discard, use /loam::learning-from-session. Must not ingest a goal wholesale; admit only independently reusable findings.

  • Loam auditing guidance

    scchearn/loam/skills/loam-memory/loam-auditing-guidance Skill

    0★ repo

    Audit, prune, and improve agent guidance markdown files in repositories. Use when the user asks to check, audit, update, improve, or fix AGENTS.md, CLAUDE.md, or related guidance files. Adds missing commands and gotchas, removes stale entries, deduplicates, and keeps the file small and relevant. Scan for guidance files, evaluate quality against templates, output a quality report, then make targeted updates.

  • Loam normalizing memory

    scchearn/loam/skills/loam-memory/loam-normalizing-memory Skill

    0★ repo

    Inspect an existing memory corpus (wiki substrate) and align it to this repo's Obsidian-friendly note-graph conventions. Use this when the user wants to import, normalize, retrofit, or clean up existing memory, notes folder, vault, docs tree, or mixed markdown knowledge base. In monorepos, also use it to align relevant AGENTS.md and CLAUDE.md files. Excludes goals/ from normalization. Not for routine wiki maintenance; use /loam::linting-memory for that.

  • Loam writing spec

    scchearn/loam/skills/loam-work/loam-writing-spec Skill

    0★ repo

    Research workspace context, APIs, implementation options, or external evidence before planning. The terminal artifact is always a spec at specs/<slug>.md; a plans/research/<slug>.md memo is optional supporting evidence when substantial investigation was needed. Accepts an optional goal path for provenance; see loam::setting-goals.

  • Research practitioner

    OpenBioHack/openbiohack/skills/research-practitioner Skill

    0★ repo

    Practitioner-grounded deep research that extends the standard /research engine with structural enforcement against shallow vendor-flavored synthesis. Use this skill whenever the user says "/research-deep", "deep research", "not just docs", "find practitioners", "what experts who shipped X learned", "deeper research", or asks any research question where prior research output was rejected as superficial. Also trigger automatically when the topic is a fast-moving technical domain (AI agents, LLM infrastructure, novel architectures) where documentation-deep answers reliably mislead and only practitioner experience reports carry signal. Trigger especially when the user is visibly frustrated with a previous shallow research output, when they explicitly ask for named experts/practitioners, when they say "I need to actually understand X", or when the user mentions wanting to build / ship / operate something rather than just compare options. The skill enforces tier-tagged claims, verbatim primary-source quotes, mandatory named-practitioner citations, three-pass adversarial iteration, banned confidence theater, and Norton-safe output. Includes a reference-doc sub-protocol for building structured foundational understanding split across multiple files per question cluster.

  • Spec writing

    Neznakometz/StackForge/spec-prep/skills/spec-writing Skill

    0★ repo

    Writing a project specification from an idea — brainstorm, requirements, acceptance criteria. Apply when creating or editing SPECIFICATION/DESIGN_SPEC/IMPLEMENTATION_PLAN and when turning an idea into a spec.

  • Report writing

    QiRebecca/Agentdemo/skills/report_writing Skill

    0★ repo

    From-scratch agent runtime with task graphs, multi-index RAG, memory, typed tools, reusable skills, handoffs, traces, and smoke tests.

  • Seo content brief

    khymerao/cursor-seo/skills/seo-content-brief Skill

    0★ repo

    Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".

    The same file is in 3 other repositories

  • Content campaign

    himanisharrma/finverge-sales-skills/plugins/finverge-sales-skills/skills/content-campaign Skill

    0★ repo

    Generate and audit LinkedIn/Twitter posts for the FinVerge 3.0 content-led revenue campaign (April 20 – June 30, 2026). Use whenever Himani or any content team member wants to draft a post, audit a draft, or prepare a week's content batch. Triggers on phrases like "draft this week's posts", "audit this post", "generate a LinkedIn post for the NACH owner on Onboarding", "prep the Friday batch", "score this draft against the filter", "the sales head needs a deal story", "give me the brief for W3 Monday", "write the CEO vision post for launch week", and similar. Works with the Master Calendar XLSX (52 posts across 10 weeks), the 4-criteria content filter, and the plugin-wide product KBs (PG/NACH/Collect/Orchestrate). Outputs post drafts (Markdown / plain text) + audit reports (JSON + human-readable summary).

  • Research

    Skillroy-AI/skillroy/.claude/skills/research Skill

    0★ repo

    Gathers cited sources and synthesizes them into a "seed document" — the foundational reference doc a new skill is built on. Prompts for a topic/brief and a set of sources (web pages, local files, pasted notes, plus any sources added by an extension, such as an internal wiki via MCP), retrieves each, and writes a structured, provenance-tracked reference. Use whenever creating a new skill, bootstrapping background documentation, or when the user mentions seed docs, gathering sources, researching a topic for documentation, Confluence/internal-wiki research, or wants source material pulled together into a single reference — even if they don't say "research" outright. Pairs with the `create` skill, which consumes the seed doc this produces.

  • Article writing

    goharabbas321/zeoel/skills/article-writing Skill

    no license0★ repo

    Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

    The same file is in 4 other repositories

  • Baqir docs

    goharabbas321/zeoel/skills/baqir-docs Skill

    no license0★ repo

    Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

  • Brand voice

    goharabbas321/zeoel/skills/brand-voice Skill

    no license0★ repo

    Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

    The same file is in 3 other repositories

  • Changelog generator

    goharabbas321/zeoel/skills/changelog-generator Skill

    no license0★ repo

    Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

    The same file is in 14 other repositories

  • Content research writer

    goharabbas321/zeoel/skills/content-research-writer Skill

    no license0★ repo

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

    The same file is in 15 other repositories

  • Documentation lookup

    goharabbas321/zeoel/skills/documentation-lookup Skill

    no license0★ repo

    Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).

    The same file is in 4 other repositories

  • Zeoel codebase knowledge

    goharabbas321/zeoel/skills/zeoel-codebase-knowledge Skill

    no license0★ repo

    Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

    The same file is in 1 other repository

  • Polishing chinese prose

    vemodalen-x/VEMO_SKILLS/skills/governance/polishing-chinese-prose Skill

    0★ repo

    The canonical Chinese-prose authority — checkable rules for Chinese output, in two bands. 翻译腔 band (R14–R20: active voice, no vague modifiers, sentence-splitting, unambiguous pronouns, consistent terminology, 的/地/得, consistent persona) + 文牍腔 band (R33–R39: verbs over noun-stacks, no self-coined abbreviations, ≤1 arrow-chain per paragraph, ≤1 parenthetical per sentence, the read-aloud test, term-preservation with human prose, no self-coined concept-terms / metaphor-as-jargon) + an EN→zh term table. Use when authoring/reviewing Chinese deliverables, reviewing the README_zh mirror's fluency, or when an agent replies to the user in Chinese. Other skills cite this by name as the prose authority; it does not restate their rules.

  • Attending group mentions

    vemodalen-x/VEMO_SKILLS/skills/orchestration/attending-group-mentions Skill

    0★ repo

    Staff a team group chat — when someone @-mentions the bot, read what they asked and reply to that need. Pull new messages by cursor (per-instance cursor file), filter for @bot mentions since last handled, triage the request (report / data / status / question / over-authority decision), serve what is serviceable (send a file or link as the bot, answer numbers ONLY by quoting the named ledger/report — never fabricate), reply to the asker with a post @-tag, in instance-policy Chinese (via polishing-chinese-prose). Decision-class requests escalate ("已转负责人" + @user), never auto-answered. Use to run group-chat attendance / answer @bot mentions on demand. Identity-decoupled — group id, bot/user identity, cursor + wordlist paths, open_id map are instance values.

  • Publishing deliverables

    vemodalen-x/VEMO_SKILLS/skills/orchestration/publishing-deliverables Skill

    0★ repo

    Publish a project deliverable (proposal / research report / experiment report / design doc) to the project's Feishu (Lark) wiki as a clean technical-report-styled document — tables and flowcharts for structured info. Use when a stage produces a deliverable that should be filed to the team Feishu wiki. Owned by Framework 0 (orchestration); style is constrained by ml-paper-writing + the local style spec.

  • Structuring solution docs

    vemodalen-x/VEMO_SKILLS/skills/research/structuring-solution-docs Skill

    0★ repo

    Structure rules for a technical solution / design document (the research-solution framework's solution_document deliverable). Style-as-rules for document STRUCTURE — arc42 skeleton + MADR per-decision blocks — turned into checkable rules. Use when the research-solution agent authors the solution/design doc after the survey + recommendation. Owned by Framework 1 (research). Generic; project values live in the instance.

  • Visualizing processing pipelines

    vemodalen-x/VEMO_SKILLS/skills/visualization/visualizing-processing-pipelines Skill

    0★ repo

    Generate a single self-contained HTML report that visualizes and explains a multi-step processing pipeline. Each stage gets a before/after drag-to-compare slider, a difference heatmap, inline base64 images, what/why/formula annotations, timing bars, and pass/fail metrics. Use when the user wants to visualize, explain, debug, document, or present an image / data / ML pipeline; build before/after comparison sliders; create an algorithm walkthrough or a parameter-tuning playground; or turn scattered intermediate results into one shareable file. Covers both a static exported .html and an interactive server with live parameter sliders.

  • Hebrew translation assistant

    skillim-hub/skills/hebrew-translation-assistant Skill

    0★ repo

    Assist Hebrew-English translation and adaptation for Israeli small businesses, freelancers, and consumers with register control, idiom handling, terminology checks, and localized ₪ and DD/MM/YYYY formatting.

  • Multilingual support agent

    skillim-hub/skills/multilingual-support-agent Skill

    0★ repo

    Assist Israeli small businesses, freelancers, and consumers with high-coverage customer support in Hebrew, English, Russian, and Arabic.

  • Terminology glossary builder

    skillim-hub/skills/terminology-glossary-builder Skill

    0★ repo

    Create bilingual English-Hebrew glossaries of industry terms for Israeli small businesses, freelancers, and consumers. Produce clear definitions, cite Israeli authoritative sources, flag review risks, and localize dates and currency for Israeli use.

  • Adr writer

    mikulgohil/claude-skills/skills/devex/adr-writer Skill

    0★ repo

    Write Architecture Decision Records in the Nygard format — context, decision, consequences, and alternatives. Use when recording a significant technical decision or populating a docs/decisions/ directory.

  • Proposal writer

    mikulgohil/claude-skills/skills/personal/proposal-writer Skill

    0★ repo

    Draft client proposals, quotes, scopes of work, and engagement letters for service work — project understanding, scope, timeline, pricing presentation, and terms. Use when writing any B2B service engagement document.

  • Report writer

    264Gaurav/DeepAgents/deepagents/skills/report-writer Skill

    0★ repo

    Report writing skill that should be applied AFTER answering any user query. Whenever the deep agent produces a final answer, use this skill to also write a structured markdown report of the interaction (question, approach, findings, answer, sources) and save it as a file using the write_file tool. Use for every substantive answer, and especially when the user asks for a report, summary document, or saved output.

  • Locale typography

    sebastian-software/skills.sebastian-software.com/skills/locale-typography Skill

    0★ repo

    Apply and review locale-appropriate typography in visible prose for German, English, French, Dutch, Luxembourgish, European Spanish (es-ES), Italian, Danish, Norwegian, Swedish, Polish, Czech, and Croatian. Use when writing, editing, localizing, proofreading, or implementing text in Markdown, HTML, JSX, templates, UI copy, documents, or print layouts where quotation marks, punctuation spacing, dashes, apostrophes, non-breaking spaces, numbers, dates, currency, or hyphenation must match a supported language and region.

  • Metro english

    sebastian-software/skills.sebastian-software.com/skills/metro-english Skill

    0★ repo

    Rewrite text into relaxed US metropolitan team English: the kind of natural, direct, human voice used in Slack threads, GitHub or Linear issue comments, PR notes, async updates, and internal team communication. Use this skill whenever the user asks to make writing sound casual, less formal, less AI-generated, more human, more Slack-like, more startup/team-like, or closer to everyday New York, San Francisco, or Silicon Valley professional English. Also use it when the user provides German or stiff English and wants it turned into natural English for team communication. Do not use it for ASD-STE100, Simplified Technical English, controlled technical English, or durable technical documentation; route those tasks to tech-docs.

  • Nonfiction writing

    sebastian-software/skills.sebastian-software.com/skills/nonfiction-writing Skill

    0★ repo

    Plan, write, revise, or critique clear and persuasive nonfiction from supplied ideas and evidence. Use for articles, essays, newsletters, thought leadership, content marketing, reports, case studies, About pages, product descriptions, explanatory prose, and other factual writing; for turning notes into a draft; or for improving structure, clarity, voice, rhythm, credibility, and calls to action without inventing facts.

  • Software validation

    sebastian-software/skills.sebastian-software.com/skills/software-validation Skill

    0★ repo

    Discover, execute, and report existing repository-native software checks. Use when asked to validate a change, run the repository's established checks against a change or package, run the applicable typecheck, static analysis, lint, format, test, benchmark, load, soak, stress, build, package, documentation, doctest, link, generated-reference, or example checks, or explain what validation evidence is still missing. Do not use to invent or install tooling, design new tests, choose architecture quality targets, prioritize repository improvements, or orchestrate delivery.

  • Tech docs

    sebastian-software/skills.sebastian-software.com/skills/tech-docs Skill

    0★ repo

    Design, write, update, and verify technical documentation for product and software users, operators, and contributors, including READMEs, setup and task guides, API and CLI references, migration notes, JSDoc, TSDoc, rustdoc, explanatory code comments, executable examples, and ASD-STE100 Simplified Technical English. Use when asked to create or improve technical docs, document a public interface or migration, write or review English technical text in STE or a controlled language, apply tekom-style rule-based writing or controlled technical German, align documentation with implementation, or validate docs against repository conventions. Do not use for general marketing copy; route repository-wide documentation audits and prioritization to codebase-improvement.

  • Audit decisions

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/audit-decisions Skill

    no license0★ repo

    Read-only, portable decision-registry drift audit. It writes a final drift report, captures registry/link diagnostics, and validates `decision:NNNN` references from Python, Go, Java JDK 17+, bounded Kotlin/JVM, PHP, Ruby, Swift, Rust, and Dart, JavaScript-family, and TypeScript comments plus Markdown/HTML references.

  • Brainstorm ideas

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/brainstorm-ideas Skill

    no license0★ repo

    Generate a batch of candidate ledger intakes for a topic or context file, deduplicate against the existing ledger, and bulk-write the survivors as proposed-state intakes with origin AI-suggestion. The orchestrator does the creative work (reading the topic, current ledger state, project docs, and producing N candidates with title / summary / hypothesis / subsystem_kind / markers); the helper script validates against duplicates and writes. Read .claude/docs/idea-ledger.md when authoring or debugging this skill.

  • Extract existing ideas

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/extract-existing-ideas Skill

    no license0★ repo

    Walk existing prose surfaces (BACKLOG.md, lessons.md, plan files) and propose candidate ledger intakes for the items already named there. Read-only by default — emits a candidates JSON and a report. Hands off to /brainstorm-ideas (via its helper script) for the actual write, so the dedup, validation, and origin discipline stay in one place. Read .claude/docs/idea-ledger.md when authoring or debugging this skill.

  • Find concept divergence

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/find-concept-divergence Skill

    no license0★ repo

    Advisory SUSPECT scan that surfaces concept-name drift between the canonical glossary at `.claude/contracts/concepts.yaml` and the codebase / docs. Detects three drift bands: `avoid_term_hit` (code uses a phrasing the glossary explicitly says is wrong), `competing_term_coexistence` (a `flagged_ambiguities` entry has multiple `competing_terms` present in the same file — drift the glossary author has not yet resolved), and `superseded_co_occurrence` (both a deprecated name and its `superseded_by:` replacement appear in the same file — rename transition drift). Detection only — never edits code or docs.

  • Find layer violation

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/find-layer-violation Skill

    no license0★ repo

    Detect views, tasks, or other entry points that own business logic. AST-walks the target for core signals (fat body, domain loop over queryset, direct LLM/agent call, dispatch bypass via bare `.delay()`, multi-model write in one function), then asks scouts to judge remaining authority in the entry point: raw SQL/cursors, direct external API clients, import/export construction, direct model/file writes, task dispatch, and transaction/resource policy. Produces an extract-service candidates report. Never edits code — hands off to `/fix-workflow layer:<candidate_id>`.

  • Find orphaned ideas

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/find-orphaned-ideas Skill

    no license0★ repo

    Detect ideas that need attention but are not getting it. Seven modes — stale (in-flight, no event in N days), harvest (has-more-potential, not in-flight), plan-dropouts (in a plan file but missing from ledger), todo (TODO/FIXME orphans in source files), stale-plans (non-terminal plans > N days silent without active ledger tracking), dead-prototype (orphan routes/templates from a /find-dormant report), attention-gap (importance-weighted audit per ADR 0016, reads `.engineering/docs/importance-map.md`). Read-only audit by default; can optionally write `stalled` transition events when --apply-stale is set. Read .claude/docs/idea-ledger.md when authoring or debugging this skill, `.engineering/docs/todo-tuning.md` when calibrating --todo, and `.engineering/docs/importance-map.md` (plus ADR 0016) when calibrating --attention-gap.

  • Mature existing ideas

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/mature-existing-ideas Skill

    no license0★ repo

    Research an existing ledger entry (or a batch of entries carrying the needs-research marker), append research-log notes to the ledger through /track-idea, and optionally clear markers as evidence accumulates. The orchestrator does the research (project doc grep, optional external Web/Context7 lookups, prior-art surveys) and uses track-idea/scripts/track.py for every ledger write. Read .claude/docs/idea-ledger.md when authoring or debugging this skill.

  • Rename concept

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/rename-concept Skill

    no license0★ repo

    Assess a domain-concept rename against its full lifecycle and a mandatory two-band completeness gate, read-only. Renaming a concept that lives in the glossary spans many surfaces — identifiers, docs, the cross-tool agent mirrors — and is executed from tribal knowledge with no front door and no completeness gate, so renames land half-applied. This skill (v0, assess-only) reports the scope-gate verdict, blast radius, a per-step lifecycle status table, and the completeness gate. It performs strict lexical assessment of Python, JavaScript, TypeScript, TSX, Go, Java, bounded Kotlin/JVM, PHP, Ruby, Rust, Dart, and Swift text. For `.ts`, `.tsx`, and checked `.js`/`.jsx`/`.mjs`/`.cjs`, a host-pinned TypeScript Compiler API resolves glossary identifier candidates, declarations, and references; it does not claim whole-project type-checking, JSX runtime behavior, or codemod safety. For Go, Go 1.22+ `go/types` classifies project-exported concept declarations and their references while retaining fields, import aliases, locals, inactive source, and diagnostics. The old and new names must not co-occur lexically in live code (/find-concept-divergence superseded_co_occurrence, band 3) AND no retired phrasing may remain (/find-concept-divergence avoid_term_hit, band 1) — both must be CLEAN for a lexical candidate assessment to pass. A TypeScript/TSX, checked-JavaScript, Go, Rust, or Swift host additionally needs a successful native semantic evidence run that resolves old/new identifier candidates. Definition of done is the two-band gate, every lifecycle step resolved, and that evidence where a semantic language is in scope — NOT a codemod having run. Drives the two rename-relevant /find-concept-divergence bands through a required coupled installation; the assessment logic does not duplicate their matching rules. The write half (author + dry-run a codemod plan, scaffold a reintroduction lint, --apply) is a v1 gap pending a codemod harness in this ecosystem (see Deferred, below).

  • Track idea

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/track-idea Skill

    no license0★ repo

    Append an intake, event, or lesson record to the Tier 1 idea ledger at .claude/ideas/log.jsonl. The capture surface for everything that could be reused or forgotten — features, refactors, prompts, harnesses, research probes, workflow tweaks. Validates the record against the schema in .claude/docs/idea-ledger.md before writing, then projects the idea's current state. Read .claude/docs/idea-ledger.md when authoring or debugging this skill.