JRichlen

dev-diary-review

Open a past dev-diary entry and revise it with the user — correct mistakes, enrich a thin or backfilled day with the reasoning only they remember, tighten the writing, or re-pull the day's signals to check facts. Use whenever the user wants to edit, revise, amend, correct, fix, expand, or clean up an existing diary entry, review a backfilled day, or says things like "fix the 07-15 entry", "that day is wrong", "review my backfilled entries", "edit the diary", or invokes /dev-diary-review. This is the editing counterpart to /dev-diary (which writes today's entry); reach for it for any change to a day already on disk.

dev-diary

Run a guided end-of-day loop that discovers everything the user did today from their local Claude Code sessions, git commits, and prompt history, interviews them about what actually mattered, and records a scannable dated entry in the dev-diary journal. Use this whenever the user wants to write a dev diary, daily log, work journal, standup note, changelog entry, or "what did I do today" wrap-up — or says things like "log today", "diary entry", "capture today", "end of day", "what did I get done", "dev-diary", or invokes /dev-diary. Also use it to backfill a past day (pass the date) or to review recent entries.

graveyard

Archive old or unused GitHub repositories into a single private "graveyard" repo as restorable git bundles, then safely delete the originals. Use this whenever the user wants to clean up, retire, back up, archive, mothball, or "put to rest" GitHub repos they no longer actively use — including phrases like "graveyard", "archive my old repos", "I have too many repos", "back up and delete these projects", or "declutter my GitHub". Captures full history (every branch, tag, and PR ref) so nothing is lost, and never deletes an original until its backup is verified present.

AI & Automation Listed

orchestration-patterns

Two reusable multi-agent orchestration templates for research-and-verify work built on Claude Code's Workflow tool: fan out research over dimensions, then adversarially verify the claims that research surfaces. Use this WHENEVER you are about to hand-roll a fan-out of subagents for research, exploration, design comparison, auditing, or "go find out X and check it" — especially any time you catch yourself writing a parallel()/pipeline() of research agents and wondering how to keep them honest. It captures the frozen-ground-truth, per-stage-schema, adversarial-verifier discipline so plausible-but-wrong findings don't survive. Reach for it on phrases like "research and verify", "fan out agents", "explore this thoroughly", "compare these options and fact-check", "audit and confirm", or "orchestrate subagents".

AI & Automation Listed

tailscale-wif

Set up and troubleshoot SECRETLESS GitHub Actions -> Tailscale authentication using Workload Identity Federation (WIF): each run mints a GitHub OIDC token that a Tailscale "Trust Credential" exchanges for a short-lived API token or ephemeral auth key, so no Tailscale API key or OAuth client secret is ever stored. Use this WHENEVER a GitHub Actions workflow needs to talk to Tailscale — pushing an ACL/policy file with tailscale/gitops-acl-action, or joining a CI runner to the tailnet with tailscale/github-action — and you want to drop the stored credential, OR when such a workflow is failing with "token exchange failed with status 403: Unauthorized", "requested tags are invalid or not permitted", or "only one of API Key, OAuth secret, or OAuth client ID and audience". Reach for it on phrases like "Tailscale OIDC", "Tailscale WIF", "federated identity Tailscale", "secretless Tailscale in CI", "remove the Tailscale API key / OAuth secret from Actions", or "Tailscale Trust Credential".

Data & Documents Listed

human-voice

Style for prose a human reads — answers, recommendations, explanations, research summaries, comparisons. Use on every conversational reply that contains prose for a person to read: triage intent, lead with the verdict, keep it scannable, tag claim confidence. Reach for it whenever answering a technical question, comparing options, or making a recommendation, even when the user says nothing about style. Companion to machine-voice, which instead governs standalone machine-read artifacts — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Neither skill applies to code or file contents, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled.

Data & Documents Listed

machine-voice

Compression rules for standalone machine-read artifacts the reader scans — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Applies three layers: lexical compression, markdown structure as navigation, and emojis as typed status markers. Reach for it when emitting one of those artifacts on its own. Companion to human-voice, which governs prose a human reads and also owns any table or block that serves surrounding explanation. Neither skill applies to code or file contents the user will save, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled and uncompressed.

AI & Automation Listed

second-opinion

Offer-only validation pipeline for a verdict or recommendation. Use when the user asks to validate, verify, fact-check, or get a second opinion on a claim or recommendation — "are you sure", "double-check this", "second opinion". Batches fact-checking against sources, adds scoped advisor personas for the angles that need judgment, then re-emits the response grouped into verified, flagged, and conflict, with a mandatory validation delta. Requires a subagent-spawning tool; without one it must decline rather than simulate.

Data & Documents Listed

__fleet_name__-playbook

Curated operating index for the __OWNER__/__GLOB__ fleet. Routes an operator to the right repo, file, and command for cross-fleet tasks. A pointer, not an authority.

plugin-factory

Scaffold a new plugin for this marketplace. Use this whenever the user wants to create, add, bootstrap, or start a new plugin — phrases like "new plugin", "scaffold a plugin", "add a plugin to the marketplace", or "I want to build a plugin that…". It runs a deterministic generator that emits a valid, wired-in, red-by-default skeleton, then guides the invariant-first interview to fill it in.

sample-guard

A minimal known-good plugin used as the calibration baseline for the counterfeit corpus. It emits a destructive cleanup command wrapped in a confirmation guard, so there is a real safety invariant to weaken.