danmestas

@danmestas source repo

125 skills
0 followers
5 hours ago last updated

▌
Skill Creator · danmestas bundle
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

0
installs
▌
Skill Development · danmestas bundle
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

0
installs
▌
Pocock Git Guardrails · danmestas bundle
Use when working in a git repo and the user wants to prevent destructive git operations — says "add git safety hooks", "block git push/reset", "set up git guardrails", or asks to protect against accidental pushes/force-resets/branch deletes. Installs a PreToolUse hook that blocks dangerous git commands (push, reset --hard, clean -f, branch -D, checkout ., restore .) before they execute.

0
installs
▌
Pocock Setup Pre Commit · danmestas
Use when the user wants to add pre-commit hooks to a JS/TS repo — says "set up Husky", "add pre-commit hooks", "configure lint-staged", or asks for commit-time formatting/typechecking/testing. Installs Husky + lint-staged + Prettier with type-check and test wired into pre-commit.

0
installs
▌
Hipp · danmestas
Use when designing libraries, modules, or data layers that must be simple, reliable, and self-contained. Use when choosing between embedded vs server-based solutions. Use when reviewing code for unnecessary complexity, dependencies, or configuration. Triggers on requests involving zero-config design, embedded systems, long-term maintainability, or first-principles thinking.

0
installs
▌
Farley · danmestas bundle
Use when assessing, designing, fixing, or explaining Continuous Delivery in Dave Farley's style. Triggers on continuous delivery, CD, CI/CD maturity, deployment pipelines, release readiness, trunk-based development, release process audits, DORA metrics, "can we deploy now?", "Farley", or requests to make software releasable safely and frequently. Also use for regulated or legacy systems where the user needs a pragmatic CD adoption plan.

0
installs
▌
Hickey · danmestas
The Rich Hickey lens: pursue simple (un-braided, one role) over easy (familiar, near-at-hand), decomplect concerns that got tangled together, and separate value, identity, state, and time. Apply this whenever "easy," "convenient," or "it's what we already use" is doing the work of justifying a design; when state is braided into logic, policy into mechanism, or data into behavior; when object-soup would be plainer as data; and when a hard design decision is being made at the keyboard under time pressure instead of thought through first. Trigger even when Hickey isn't named — the smell is complecting, and confusing "easy" with "simple."

0
installs
▌
Norman · danmestas
Use when designing, reviewing, or auditing user interfaces and frontend interactions. Use when evaluating UI usability, accessibility, or interaction patterns. Triggers on requests involving button placement, form design, navigation, error messages, onboarding flows, modal dialogs, or when asked to review a UI for usability.

0
installs
▌
Vitaly · danmestas bundle
This skill should be used when generating web form components, auditing form accessibility, reviewing form UX, or when the user asks to "check form accessibility", "audit this form", "apply form best practices", "make this form accessible", "review form UX". Also triggers on form generation tasks where the output is a React form component. Based on Vitaly Friedman's (Smashing Magazine) accessible web form design patterns.

0
installs
▌
Bellard · danmestas
The Fabrice Bellard lens: build the smallest self-contained thing that fully does the job, get performance from insight instead of hardware, and reuse existing machinery instead of reinventing it. Apply this whenever code is growing dependencies, frameworks, services, or infrastructure to solve a problem that a smaller, sharper implementation could handle — or whenever someone says a thing needs a cluster, a big framework, or a rewrite. Use for size/complexity audits, "do we really need this dependency/service?" questions, performance work where the reflex is to add hardware or caching, green-field "should this be one file or a platform?" decisions, and any moment the answer is trending toward "that's impractical, you'd need X." Trigger even when the user doesn't name Bellard — the smell is scope inflation and reaching for resources over insight.

0
installs
▌
Carmack · danmestas
The John Carmack lens: minimize the mutable state you have to reason about, do the simple thing before the clever one, and treat correctness tooling — static analysis, warnings-as-errors, determinism — as non-negotiable. Apply this on sprawling mutable state, "we'll clean it up later," debugging by print- statement whack-a-mole, silenced compiler warnings, nondeterministic or non-reproducible behavior, premature abstraction, perf work that skips measurement, and any "what should we actually work on" prioritization call. Trigger even when Carmack isn't named — the smell is code whose full set of states you can't hold in your head, and effort that isn't ruthlessly focused.

0
installs
▌
Caveman · danmestas
Use when the user wants ultra-compressed responses — says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra.

0
installs
▌
Doppler · danmestas
Use when migrating .env files to Doppler secrets management, setting up Doppler for a project, or when asked to secure environment variables. Triggers on .env files containing API keys, tokens, or secrets that should not be in plaintext on disk.

0
installs
▌
Helland · danmestas
The Pat Helland lens: treat durable data as immutable, append-only facts that carry their own identity and version; and design across service, machine, or org boundaries assuming you cannot have distributed transactions — only idempotent, at-least-once messages that must be reconciled. Apply this on in-place updates and overwrites, "just UPDATE the row," two-phase commit or distributed transactions at scale, exactly-once delivery assumptions, shared mutable state across services, and any data that crosses a boundary of service, machine, org, or time. Trigger even when Helland isn't named — the smell is mutation-in-place and pretending distributed systems can be transactional.

0
installs
▌
Landing · danmestas
Post-merge cleanup workflow. Discusses uncommitted worktree changes per-worktree before deleting; handles local + remote merged branches, stale refs, dist/ build artifacts, and surfaces today's memory entries for review. Use when the user wants to wrap up after merging a PR, clean up worktrees, tidy branches, do post-merge cleanup, "land the plane", "land", remove stale feature branches, or close out a development session.

0
installs
▌
Reflect · danmestas
Use when the user types "/reflect", "review what we just did", "critique the last task", "what could go better", "post-task review", "retro this", or after a meaningful task ships and the agent judges a structured critique would help. Produces a markdown reflection report at ~/.claude/evolution-reports/<project>/reflections/. Does NOT auto-apply changes — output is for human review.

0
installs
▌
Rtk Tdd · danmestas
Use when implementing, testing, refactoring, or bug-fixing Rust code in the rtk CLI proxy — enforces Red-Green-Refactor with anyhow/thiserror error handling, `#[cfg(test)]` modules, and Arrange-Act-Assert structure

0
installs
▌
Takeoff · danmestas
Beginning-of-session inventory and orientation. Surfaces stale worktrees, behind-origin state, recent specs/plans, open PRs, and recent memory entries to help the agent re-orient. Use when starting a new session, asking "where were we", running a takeoff check, beginning work, or wanting a situational report before diving in. Read-only — pure inventory + recommendations, no automatic actions.

0
installs
▌
Cavecrew · danmestas
Use when the user says "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", or "compressed agent output". Decision guide for delegating to caveman-style subagents (`cavecrew-investigator`, `cavecrew-builder`, `cavecrew-reviewer`) whose tool-results return ~60% smaller than vanilla equivalents, so the main context lasts longer across long sessions.

0
installs
▌
CI Watch · danmestas
Use when watching CI/CD checks complete — `gh pr checks`, `gh run watch`, polling PR conclusion, waiting for builds to finish before merge. Triggers: 'watch CI', 'wait for build', 'poll PR', 'check CI status', 'is the build done', '/ci-watch'.

0
installs
▌
Datastar · danmestas
Use when building web applications with Datastar — the hypermedia framework that drives frontend reactivity from the backend using HTML data-* attributes and Server-Sent Events. Triggers on Datastar, data-star, SSE-driven UI, hypermedia framework, backend-driven frontend, data-signals, data-on, PatchElements, or any Go/Python web app using Datastar SDKs.

0
installs
▌
Defuddle · danmestas
Strip clutter from web pages before ingesting into the wiki. Removes ads, navigation, headers, footers, and boilerplate: leaving clean readable markdown that saves 40-60% tokens. Triggers on: defuddle, clean this page, strip this url, fetch and clean, clean web content before ingesting, strip ads, remove clutter, clean URL content, readable markdown from URL.

0
installs
▌
Dx Audit · danmestas
Use when evaluating developer experience or user experience, assessing usability of a CLI/SDK/API/UI, scoring project ergonomics, identifying friction in workflows, or when asked to audit DX or UX. Triggers on "DX score", "UX audit", "developer experience", "user experience", "workflow friction", "usability audit", "how hard is it to use this".

0
installs
▌
Memorize · danmestas
Use when the user types "/memorize", "save this learning", "make this an ADR", "capture this for future sessions", "remember this", "write this down for next time", or "save that proposal". Also auto-fires after /reflect when the user expresses agreement with a proposal. Converts a recent insight or reflection into either a project ADR or a personal memory entry. Always confirms content with the user before writing.

0
installs
▌
Rtk Ship · danmestas
Use when cutting a new rtk release — runs the full pre-release checklist (cargo fmt/clippy/test, hyperfine startup benchmark, integration tests), bumps SemVer in Cargo.toml, creates an annotated git tag, and pushes to trigger the release CI; covers rollback options (patch, yank, revert) and dependency audit

0
installs
▌
Spdd Sync · danmestas
Use after behavior-preserving refactors or implementation cleanup in SPDD to synchronize the REASONS Canvas back to the current code without changing business intent.

0
installs
▌
Linear CLI · danmestas
Use when manipulating Linear issues from the CLI — creating, updating, listing, transitioning, commenting via `acli linear` or the Linear MCP. Triggers: 'create linear issue', 'update issue status', 'list my issues', 'transition to in-progress', 'add comment to LIN-X', '/linear', 'lin issue'.

0
installs
▌
Ousterhout · danmestas
Use when designing modules, classes, APIs, or system architecture. Use when reviewing or refactoring code for complexity. Use when choosing between implementation approaches. Triggers on requests involving abstraction design, interface simplicity, information hiding, or reducing cognitive load.

0
installs
▌
Rtk Triage · danmestas
Use when you want a full rtk repo health pass that runs `/rtk-issue-triage` and `/rtk-pr-triage` in parallel and then cross-references the results — surfaces double-coverage (two PRs for one issue), security findings without PRs, P0/P1 bugs without PRs, our dirty PRs with probable causes, and untracked PRs. Saves the report to `claudedocs/RTK-YYYY-MM-DD.md`. Args: `en`/`fr` (default fr), `save`/`no save`.

0
installs
▌
Ship Issue · danmestas
Drive an issue from triage to merged PR with minimal operator intervention. Runs the full loop — read & label, post agent brief, write a failing test, implement minimally, self-review via subagent, replicate local CI, push, watch CI, squash-merge, clean up, and report with next-step suggestions. Use when the operator says "ship #X", "do issue #X end-to-end", "take #X to merge", "fix and ship #X", "do #X autonomously", or any phrasing that authorizes carrying a single issue all the way through. Also use when the operator follows a /triage call with "do as you'd like", "update the issue then start implementation", or otherwise hands off the rest of the workflow. Do NOT use for purely advisory questions ("what should we do about #X?", "look at #X with me") — those stay in regular triage / discussion mode.

0
installs
▌
Spdd Story · danmestas
Use when a large SPDD requirement needs to be split into independent, deliverable user stories before analysis and REASONS Canvas work.

0
installs
▌
Suit Build · danmestas
Use when building, validating, or scaffolding skills in this monorepo. Triggers: "validate skills", "build suit-build", "scaffold a new skill", "init a hook/agent/rules/plugin", "run suit-build", or any work on the multi-harness skill emission pipeline (Claude Code, APM, Codex, Gemini, Copilot CLI, Pi targets).

0
installs
▌
Tigerstyle · danmestas
Use when writing safety-critical code, systems programming, infrastructure, or when a project needs rigorous coding discipline. Triggers include requests for defensive coding, assertion-heavy development, performance-conscious design, zero-technical-debt policy, or NASA Power of Ten style rules. Also use when reviewing code for correctness, safety, or performance issues.

0
installs
▌
Using Spdd · danmestas
Use when a session is working under Structured-Prompt-Driven Development (SPDD), when prompts/specs must be versioned delivery artifacts, or when logic-heavy changes need a prompt-first closed loop.

0
installs
▌
Vault Lint · danmestas
Health check the Obsidian wiki vault. Finds orphan pages, dead wikilinks, stale claims, missing cross-references, frontmatter gaps, empty sections, misfiled pages, and catalog gaps (pages absent from a bucket _index.md or the master index.md). Creates or updates Dataview dashboards. Generates canvas maps. Triggers on: "lint", "health check", "clean up wiki", "check the wiki", "wiki maintenance", "find orphans", "wiki audit".

0
installs
▌
Vault Save · danmestas
Save the current conversation, answer, or insight into the Obsidian wiki vault as a structured note. Analyzes the chat, determines the right note type, creates frontmatter, files it in the correct wiki folder, and updates index, log, and hot cache. Triggers on: "save this", "save that answer", "/save", "file this", "save to wiki", "save this session", "file this conversation", "keep this", "save this analysis", "add this to the wiki".

0
installs
▌
Vault Query · danmestas
Answer questions using the Obsidian wiki vault. Default skill for "what do you know about", "explain", "summarize", "find in wiki", "search the wiki". Two-mode router: when qkb is installed and not opted out, escalates from curated read (hot.md + index.md + page reads) to qkb's BM25 or graph primitives on questions the curated path can't reach. When qkb is opted out (QKB_DISABLED=1) or not on PATH, runs as pure curated read with honest gap reporting. Supports quick, standard, deep modes; files answers back as wiki pages so knowledge compounds. Triggers on: query:, what is, explain, summarize, find in wiki, search the wiki, based on the wiki, wiki query quick, wiki query deep.

0
installs
▌
Caveman Help · danmestas
Use when the user invokes /caveman-help, says "caveman help", asks "what caveman commands", or asks "how do I use caveman". Displays a one-shot quick-reference card for all caveman modes, skills, and commands. Does not change mode or persist anything.

0
installs
▌
Clone Config · danmestas
Use when bootstrapping a fresh Mac/server, managing dotfiles, tracking shell configs, refreshing a Brewfile, adding ~/.zshrc to a dotfiles repo, or asking how to replicate a machine's config to a new device. Manages macOS (and Linux-compatible) machine config via chezmoi — install once, apply on every machine, edit source not target.

0
installs
▌
Datastar Tao · danmestas
Use when building hypermedia-driven web applications, server-rendered UIs, or any frontend where the backend should own state. Use when choosing between SPA and server-driven architecture. Use when reviewing frontend code for unnecessary client-side state, optimistic updates, or client-side routing. Triggers on requests involving SSE, HTML-over-the-wire, DOM morphing, HTMX, Datastar, signals, or backend-first frontend design.

0
installs
▌
Rtk Tdd Rust · danmestas bundle
Use when adding a new rtk filter (e.g. `rtk newcmd`) or fixing a failing filter test — runs the full Red-Green-Refactor loop with real command fixtures, token-savings assertions (>= 60%), and `insta` snapshot tests

0
installs
▌
Shadcn Forms · danmestas bundle
This skill should be used when generating React form components with shadcn/ui, wiring up react-hook-form with zod validation, choosing the right shadcn/ui input component for each field type, or when the user asks to "build a form with shadcn", "add form validation", "use react-hook-form", "create a zod schema for this form". Provides component selection guidance, validation patterns, and production-ready implementation recipes for shadcn/ui v4 forms.

0
installs
▌
Vault Ingest · danmestas
Ingest sources into the Obsidian wiki vault. Reads a source, extracts entities and concepts, creates or updates wiki pages, cross-references, and logs the operation. Supports files, URLs, and batch mode. Triggers on: ingest, process this source, add this to the wiki, read and file this, batch ingest, ingest all of these, ingest this url.

0
installs
▌
Brainstorming · danmestas bundle
Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when the user wants to design something, brainstorm a feature, or plan a project.

0
installs
▌
Caveman Stats · danmestas
Use when the user invokes /caveman-stats or asks for caveman token-usage stats. Shows real token usage and estimated savings for the current session, read directly from the Claude Code session log — no AI estimation. Output is injected by the `caveman-mode-tracker` hook (vendored alongside this skill), which intercepts the slash command and returns the formatted stats as a blocked-decision reason.

0
installs
▌
Goal Complete · danmestas
Use when you (the model pursuing a long-horizon goal stored in sesh's substrate) believe the objective has been achieved and want to mark the goal as `achieved`. Walks you through a mandatory completion audit BEFORE submitting `update_goal(complete)`. ONLY invoke when you are genuinely ready to claim completion — not as a routine status check. Triggers when you say "I think we're done", "this looks complete", "objective met", or when you are about to call sesh-ops goal complete.

0
installs
▌
Linear Method · danmestas
Use when creating, organizing, or prioritizing issues in Linear. Use when managing backlogs, setting up cycles, scoping projects, writing issue titles/descriptions, or deciding how to structure work in Linear. Also use when asked about Linear best practices.

0
installs
▌
Rtk Pr Review · danmestas
Use when batch-reviewing rtk PRs from simplest to most complex — checks each PR's state (conflicts, CLA, CHANGES_REQUESTED), reads the full diff, presents one PR at a time with a 2-4 sentence summary and explicit merge prompt, never merges without a typed "ok", and posts boldguy-tone comments on blocked PRs (rebase needed, CLA missing). Args: `triage` to chain `/rtk-triage` first; `from:<num>` to resume.

0
installs
▌
Rtk Pr Triage · danmestas bundle
Use when auditing open GitHub PRs on the rtk repo — sizes XS/S/M/L/XL, detects overlapping diffs (>50% shared files), flags clusters from prolific authors, separates "our PRs" from external, runs parallel `code-reviewer` agents on selected PRs, drafts review comments, and posts after explicit validation. Args: `all` for deep review of every external PR, PR numbers to focus, `en`/`fr` for language.

0
installs
▌
Spdd Analysis · danmestas
Use after SPDD alignment to analyze requirements against relevant code, domain concepts, risks, gaps, strategy, and acceptance coverage before writing a REASONS Canvas.

0
installs
▌
Spdd API Test · danmestas
Use in SPDD when API or system-boundary behavior must be verified with executable scenarios covering normal, boundary, and error cases from the REASONS Canvas.

0
installs
▌
Spdd Generate · danmestas
Use when implementing code from an approved SPDD REASONS Canvas, following Operations in order and staying inside the canvas Norms and Safeguards.

0
installs
▌
Status Update · danmestas
Format a status update, progress report, summary of work, or explanation of how concerns are being addressed — in plain prose suitable for handoff to a non-technical stakeholder. Use whenever the user asks for a status update, an explanation of work, a summary of what's been done, or how something is being addressed. The output should read like a confident pilot-engineer wrote it, not an AI.

0
installs
▌
Writing Plans · danmestas bundle
Use when you have a spec or requirements for a multi-step task, before touching code — produces a structured task plan with assignments and leaf-level steps

0
installs
▌
Apple Contacts · danmestas
Search, list, create, update, and delete Apple Contacts via the `contactbook` CLI on macOS. Look up contacts by name, phone, email, or organization. Manage contact groups.

0
installs
▌
Caveman Commit · danmestas
Use when the user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit, or when staging changes. Generates ultra-compressed Conventional Commits messages — subject ≤50 chars, body only when "why" isn't obvious. Cuts noise while preserving intent.

0
installs
▌
Caveman Review · danmestas
Use when the user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review, or when reviewing pull requests. Generates ultra-compressed code review comments — one line per finding: location, problem, fix. Cuts noise while preserving actionable signal.

0
installs
▌
Course Correct · danmestas
Rewind a bad chunk of work by capturing what was tried + learned to a summary file, then telling the user how to rewind their session context per harness. Use when an approach has failed, work has gone down the wrong path, the agent went in circles, the user wants to undo recent decisions, or the user says "course correct", "rewind", "we went down the wrong path", "this isn't working start over", or "roll back what we just did". Captures session learnings without destroying git history or the working tree.

0
installs
▌
Obsidian Bases · danmestas
Create and edit Obsidian Bases (.base files): Obsidian's native database layer for dynamic tables, card views, list views, filters, formulas, and summaries over vault notes. Triggers on: create a base, add a base file, obsidian bases, base view, filter notes, formula, database view, dynamic table, task tracker base, reading list base.

0
installs
▌
Pocock Caveman · danmestas
Use when the user wants ultra-compressed responses — says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.

0
installs
▌
Pocock Handoff · danmestas
Use when the user wants to compact the current conversation into a handoff document for another agent — says "handoff", "write a handoff", "summarize this session for a fresh agent", or invokes /handoff. Produces a doc the next session can pick up cold.

0
installs
▌
Publish To NPM · danmestas
Publish a new package to npm under an existing scope, with GitHub Actions release automation, provenance attestations, and a path to trusted publishing (OIDC). Use when the operator says "publish this to npm", "push this package", "release v0.x", "set up CI for npm publishing", "set up trusted publishing", or "ship this as an npm package". Pairs with `doppler` skill when the npm token lives there.

0
installs
▌
Rtk Repo Recap · danmestas
Use when you want a shareable Markdown recap of the rtk repository state — open PRs (grouped into ours / external-reviewable / external-problematic), open issues with priorities, recent releases, executive summary, and a clipboard copy. Pass `en` or `fr` for language (defaults to French)

0
installs
▌
Spdd Alignment · danmestas
Use before SPDD analysis or implementation to lock business intent, domain language, scope boundaries, acceptance criteria, dependencies, and hard constraints.

0
installs
▌
Spy On Session · danmestas
Audit how a tool integrates with a Claude Code session — fingerprint files before and after the tool's bootstrap, monitor the live transcript JSONL and any event streams the tool publishes, classify findings as bugs / inconveniences / improvements with severity, source pointer, observed, expected, and repro hint. Use whenever the user wants to spy on a Claude Code integration, audit how a hook / skill / MCP / sidecar behaves in a real session, find what a tool is silently breaking, watch a Claude session running with <some tool> to surface rough edges, run a tool's bootstrap on a project and report what's broken, or generally "find what <tool> gets wrong on <project>" — even if they don't use the word "spy". For tools that already have a specialised spy skill (e.g. `spy-on-bones-session`), prefer that and use this only as a reference.

0
installs
▌
Stuck Detector · danmestas
Use when the user says "stuck", "I'm stuck", "this isn't working", "tool keeps failing", "give up on this", "we're going in circles", "/stuck", or when the agent itself notices it has hit N consecutive tool errors in a session window. Generates a handoff summary so progress can resume in a fresh session, escalate to a stronger model, or pause for user input. Stops the doom-loop of blind retries.

0
installs
▌
Using Spec Kit · danmestas
Use when the user wants spec-driven development on a non-trivial change (e.g. "let's spec this", "write a constitution", "/speckit.*", or any staff-tier workflow starting from "what should this be" rather than "what should this do"). Drives spec → plan → tasks → impl via GitHub spec-kit, with artifacts in .agent-config/specs/.

0
installs
▌
Vault Overview · danmestas bundle
Claude + Obsidian knowledge companion. Sets up a persistent wiki vault, scaffolds structure from a one-sentence description, and routes to specialized sub-skills. Use for setup, scaffolding, cross-project referencing, and hot cache management. Triggers on: "set up wiki", "scaffold vault", "create knowledge base", "/wiki", "wiki setup", "obsidian vault", "knowledge base", "second brain setup", "running notetaker", "persistent memory", "llm wiki".

0
installs
▌
Writing Skills · danmestas
Use when creating new skills, editing existing skills, or verifying skills work before deployment

0
installs
▌
Executing Plans · danmestas
Execute a plan task-by-task in a single session. The coordinator enumerates tasks from the plan, claims one at a time, and marks each complete on finish. Use when running a plan inline (single agent, single session); use subagent-driven-development instead for parallel agent work.

0
installs
▌
Golang Patterns · danmestas bundle
Use when writing, reviewing, or refactoring Go code. Triggers on .go files, go.mod presence, or any task involving Go programming — concurrency (goroutines, channels, context), interfaces, generics, error handling, table-driven testing, or microservice/CLI architecture. Pairs with the `golang-pro` agent, which delegates pattern detail here.

0
installs
▌
Obsidian Canvas · danmestas bundle
Visual layer of the wiki. Add images, text cards, PDFs, and wiki pages to Obsidian canvas files with auto-positioning inside zones. Integrates with /banana for image capture. Triggers on: /canvas, canvas new, canvas add image, canvas add text, canvas add pdf, canvas add note, canvas zone, canvas list, canvas from banana, add to canvas, put this on the canvas, open canvas, create canvas.

0
installs
▌
Pocock Diagnose · danmestas bundle
Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. Disciplined diagnosis loop: reproduce -> minimise -> hypothesise -> instrument -> fix -> regression-test.

0
installs
▌
Rtk Performance · danmestas
Use when investigating, benchmarking, or fixing rtk performance regressions — enforces <10ms startup, <5MB resident memory, 60-90% token savings, <5MB stripped binary; covers lazy_static regex, zero-copy parsing, dependency minimisation, and flamegraph workflow

0
installs
▌
Career Interview · danmestas bundle
This skill should be used when the user asks to "interview me", "build my career profile", "let's work on my resume background", "career interview", "start a career session", "update my profile", "let's talk about my experience", or invokes /career-interview. Conducts deep conversational interviews to build structured career profiles for technical professionals.

0
installs
▌
Caveman Compress · danmestas bundle
Use when the user invokes /caveman-compress FILEPATH, says "compress memory file", or otherwise asks to compress natural-language memory files (CLAUDE.md, todos, preferences). Rewrites the file into caveman format to save input tokens, preserving all technical substance, code, URLs, and structure. The compressed version overwrites the original; a human-readable backup is saved as FILE.original.md.

0
installs
▌
Cloudflare Email · danmestas bundle
Use when sending outbound transactional or one-off emails from a Cloudflare-managed domain without running a mail server or paying for a mailbox provider. Triggers on needs to send email programmatically from a custom domain, send-from-my-domain requests, or replacing SMTP relays. Cloudflare Email Service is REST API + Workers only — no SMTP, so it is NOT compatible with Gmail "Send mail as", Outlook, or any SMTP client.

0
installs
▌
Evolution Engine · danmestas
Use when the user wants to "analyze sessions", "find patterns in my agent history", "evolve config", "/evolve", "what's been frustrating you", or asks for automated suggestions for improving skills/configs based on session transcripts. Triggers on requests to surface recurring friction, propose allowlist additions, find stale memory, or generate diff-shaped recommendations against existing skills, settings, and memory files.

0
installs
▌
Gh Project Setup · danmestas bundle
Use when creating new GitHub projects, setting up project boards, configuring kanban/scrum/roadmap boards, or applying project templates. Provides context-aware template suggestions based on repository analysis and conversation. Supports 6 templates: kanban, bug-tracker, feature-development, roadmap, research, release-planning. Handles multi-repo and organization projects.

0
installs
▌
Midscene Testing · danmestas bundle
Use when performing ad-hoc browser testing, smoke testing workflows, validating UI after frontend changes, or testing Datastar/HTMX/SSE reactive features that unit tests cannot cover. Also use when consolidating Midscene HTML reports into a single navigable document.

0
installs
▌
Pikchr Generator · danmestas bundle
Author production-grade technical diagrams in Pikchr — a deterministic, text-defined diagram DSL that compiles to a single self-contained SVG. Use whenever the user asks for a flowchart, sequence diagram, system architecture, state machine, data pipeline, swim lane, or any boxes-and-arrows technical illustration AND has expressed a preference for text-defined / source-controlled diagrams (over excalidraw, figma, or hand-drawn art). Also use when the user says "draw the architecture", "diagram this flow", "show the states", "graph this topology", or mentions pikchr by name. Output is themed SVG (16 themes via --theme NAME) that renders inline in any Markdown surface that accepts SVG (GitHub, GitLab, Obsidian, mdBook, agent multimodal Read, etc.). Do NOT use for freeform sketches with curves and pen strokes (excalidraw), real Gantt/pie charts (a chart library), or rich data viz.

0
installs
▌
Rtk Issue Triage · danmestas bundle
Use when auditing open GitHub issues on the rtk repo (or any project) — categorises by Bug/Feature/Enhancement/Question, scores risk red/yellow/green, detects duplicates via Jaccard similarity, cross-references open PRs (`fixes #N`), flags stale issues, runs deep analysis via parallel agents on demand, and posts validated draft comments. Args: `all` for deep on every issue, issue numbers to focus, `en`/`fr` for language.

0
installs
▌
Vault Query Bm25 · danmestas
Fast BM25 (lexical-only) retrieval over the Flight Planner wiki via qkb. No LLM, no graph, no rerank — cheap and deterministic. Use for known-term questions (proper nouns, acronyms, exact phrases), AB-test baselines against the full pipeline, and quick smoke checks. Triggers on: vault-query-bm25, bm25 vault query, lexical vault search, fast keyword search the wiki, qkb bm25, search the wiki without LLM.

0
installs
▌
Datastar Patterns · danmestas
Use when implementing UI patterns with Datastar — search, inline editing, infinite scroll, file upload, validation, bulk operations, polling, lazy loading, progress indicators, or keyboard shortcuts. Triggers on data-* attributes, @get/@post/@put/@patch helpers, SSE response formatting, or any "how do I do X in Datastar" implementation question.

0
installs
▌
Gh Project Shared · danmestas bundle
Shared utilities for GitHub project management. Not directly invoked by agents. Provides: gh CLI validation, authentication checking, config file management (.github/project-config.json), context detection for template suggestions, and error handling with logging.

0
installs
▌
Obsidian Markdown · danmestas
Write correct Obsidian Flavored Markdown: wikilinks, embeds, callouts, properties, tags, highlights, math, and canvas syntax. Reference this when creating or editing any wiki page. Triggers on: write obsidian note, obsidian syntax, wikilink, callout, embed, obsidian markdown, wikilink format, callout syntax, embed syntax, obsidian formatting, how to write obsidian markdown.

0
installs
▌
Orchestrator Mode · danmestas
Use at session start in the Darkish Factory repo to prime as the pipeline orchestrator (host mode). Loads the §7 loop, the 13-role roster, the escalation classifier, and the rules for converting subagent muscle memory into subharness dispatch. Invoke whenever the operator types a task and you're in this repo.

0
installs
▌
Orchestrator Suit · danmestas
Use when you are the orchestrator session driving role-shaped subharness children. Loads when the orchestrator outfit is active. Documents the spawn loop — receive intent → classify → spawn role-shaped child via stateless suit + harness-spawn → monitor → cherry-pick worktree → escalate → audit log. Triggers on "orchestrate", "dispatch a worker", "spawn an implementer / reviewer / planner / spy", "run the multi-role pipeline", "drive child harnesses", "spawn a worker session".

0
installs
▌
Publish HTML Page · danmestas bundle
Publish a self-contained HTML file to a shareable encrypted Cloudflare-hosted artifact URL using html-artifact-publisher. Use when asked to upload, publish, share, or host a generated HTML page/artifact/explainer via artifacts.craftdesign.group or the HTML artifact publisher.

0
installs
▌
Simple Brainstorm · danmestas
Lightweight brainstorming for small-to-medium creative or architectural decisions. Use when scoping a feature, choosing between approaches, or planning a focused change without needing a full design-doc cycle. Optimized for speed-to-decision over ceremony.

0
installs
▌
Skill Eval Runner · danmestas
Use when the user types "/eval skill X", "test skill X", "run evals on", "regression test skill", "eval skill", or asks whether a skill's description still triggers correctly. Also fires PostToolUse on edits to any skills/*/SKILL.md so a freshly-edited skill's triggers are immediately checked. Runs binary pass/fail evals (no scoring) per MindStudio's research.

0
installs
▌
Using Bones Swarm · danmestas
Open, work in, and close a bones swarm session — the slot-shaped lane that bundles a worktree, a claimed task, and an open hub branch. Use when starting feature work that needs isolation from current workspace, before executing implementation plans, or when you need a worktree for parallel work in a bones workspace.

0
installs
▌
Using Superpowers · danmestas
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

0
installs
▌
Vault Query Graph · danmestas
Pure graph-traversal retrieval over the Flight Planner Obsidian wiki vault. Uses qkb's graph layer directly (LINKS_TO / EMBEDS / REFERENCES edges across 1800+ typed nodes) — no BM25, no vector, no LLM expansion, no rerank. Use for entity-relation questions ("what does X link to / depend on / feed"), structural mapping ("what's connected to Y"), and following established wikilinks across the corpus. Triggers on: vault-query-graph, graph vault query, what does X link to, what feeds X, what depends on X, how does X relate to Y, graph traversal, walk the graph from X.

0
installs
▌
Atlassian CLI Jira · danmestas
Use when working with Atlassian CLI (acli) to install, authenticate, and manage Jira Cloud work items/issues from the command line: search (JQL), view, create, edit, assign, transition, comment, link, watch, attach, archive/unarchive, bulk operations, and project/board/sprint discovery.

0
installs
▌
Description Linter · danmestas
Use when the user types "lint my skills", "check skill descriptions", "/lint-skills", "validate skill triggers", "audit skill descriptions", or asks whether two skills conflict on the same prompt. Also fires PostToolUse on edits to any skills/*/SKILL.md. Static-analyzes SKILL.md frontmatter for trigger quality, length, naming, and cross-skill conflicts. Does NOT auto-fix — only reports.

0
installs
▌
Gh Project Charter · danmestas bundle
Use when creating project charters, documenting project goals/scope, defining success criteria, updating project documentation, or tracking scope changes

0
installs
▌
Skill Gap Detector · danmestas
Use when the user wants to "find missing skills", "what skills should I have", "what am I explaining over and over", "/skill-gap", "audit my repeated instructions", or asks which skills they're missing based on session history. Also weekly cron-friendly. Scans recent session transcripts for "I had to explain X 3+ times" patterns and drafts proposed new SKILL.md files for human review. Does NOT auto-install.

0
installs
▌
Spdd Prompt Update · danmestas
Use in SPDD when requirements, behavior, acceptance criteria, business rules, or safeguards change; update the REASONS Canvas before changing code.

0
installs
▌
Using Bones Powers · danmestas bundle
Use when starting any conversation in a bones workspace - establishes how to find and use bones-powers skills, requiring Skill tool invocation before ANY response including clarifying questions

0
installs

125 published skills · page 1 of 2