Menu
Skills in this repository
SkillsMP has collected 447 skills from jleechanorg/claude-commands. Open a skill to review its source and details.
jleechanorg/claude-commandsShowing 40 of 447 collected skills.
Bug class — spell-repair LLM function defined but never called, leaving caster characters with "No spell list recorded" until user manually asks "fix my spells". Trigger on /repro when the Spells panel shows the fallback warning OR the LLM-generated spell…
Add, remove, or replace a model provider in Hermes' gateway config (the bidirectional counterpart to add-minimax-provider). Modifies `~/.hermes/config.yaml` (and its `~/.hermes_prod/` mirror), `~/.hermes/scripts/launchd-env-wrapper.sh` env-passthrough, any…
Dispatch a bead-tracked task via ao spawn/ao send, register the mapping, and ack in Slack thread. Includes the `env -i` ARG_MAX wrapper, the `running.json` bootstrap for "lifecycle polling is inactive" errors, the post-spawn branch-reset + copy-briefs + `ao…
Download a Your Project campaign from Firestore, write raw archive + wiki source page. Use when the user says download a campaign, pull this campaign, fetch campaign from firestore, ingest campaign N, copy a campaign by id, or wants to walk a specific WA…
Diagnose and recover dropped Jeffrey messages — threads or standalone messages that got no response within 30 min. Use when Jeffrey asks about missed messages, the script reports drops, the followup cron is silently producing actioned=0 every tick (bot…
Attach local evidence files (PNG/JPG/GIF/MP4/PDF) to Slack threads so they render INLINE — not as bare file paths or `MEDIA:/path` text tokens. v1.3 cluster-anchor; v1.4 gist-raw-URL fallback; v1.5 Pre-Send Gate; v1.6 OAuth preflight + f-string pitfall; v1.7…
Generate the daily executive digest — a single WhatsApp summary of everything needing attention: stalled scheduling, pending intros, unanswered emails, promised follow-ups, open Todoist tasks, and upcoming calendar events. Use when running the daily digest…
Run a comprehensive morning executive assistant sweep for {{OWNER_NAME}}: check today's calendar, scan Gmail for flagged/important emails, review Slack action items, run system probes (load/disk/gateway), scan infra alert channels (worldai-alerts, mcp-mail,…
End-to-end finish protocol for any Slack thread, CLI invocation, or cron task where the user has handed off a goal. Routes to /fs (spec gen) → /f (Dark Factory loop) → drives to a verifiable conclusion (green PR with non-unit-test evidence, finished code…
Break the loop when the Slack/Hermes gateway re-injects old replies, posts empty-body forwards, or sends queued/shutdown/system-housekeeping notes in place of real user content.
Diagnose and fix slow OR expensive GitHub Actions runs: runner-pool saturation analysis, stuck-run cancellation, fetch-depth optimization, billing-API cost-spike triage (hosted-vs-self-hosted runner switch detection, per-SKU cost breakdown, revert-PR…
Recover from a stuck self-hosted Actions runner when jobs hang with no logs retrievable. Use when a job runs to its timeout with `actions/jobs/<id>/logs` returning 404 BlobNotFound, when the same matrix leg fails on consecutive GH Actions runs against the…
Diagnose GitHub Actions failures that look like real CI failures but are actually transient infrastructure (HTTP 503 from `actions/github-script`, GitHub API rate-limit surfaced inside workflow steps, cancelled downstream gate propagated as aggregator…
Audit, rebase, supersede, and ship the jleechanorg/claude-commands export pipeline. Five-session playbook covering consolidation, supersession, fresh export, AND the cleanup-PR + script-patch archetype (Pitfall 10) for excluding content categories like…
Review PRs: diffs, inline comments via gh or REST.
Create, triage, label, assign GitHub issues via gh or REST.
Diagnose and trace unwanted/automated comments on GitHub PRs to their source. Use when a PR is getting spammed by bot comments, AI automation directives, or cron-triggered messages, and you need to identify which system is responsible and how to disable it.
GitHub PR lifecycle: branch, commit, open, CI, merge.
Clone/create/fork repos; manage remotes, releases.
Take an externally-supplied `.patch` file (Slack attachment, PR text, mail attachment) and push it as a GitHub PR — covers triage, multi-canonical-repo discovery, base-SHA verification, auth-vs-baked-in-user mismatch, `git apply` vs `git am` choice, and…
Use when a user asks "verify PR #X covers Y; report gaps", "does PR #X implement feature Y?", or any scope/coverage verification request. Performs a read-only diff audit against the PR head and merge base, then emits a structured JSON gap report with explicit…
Cross-repo PR draft / ready / conflict / review triage combined with cmux terminal status and a ranked next-steps report. Designed for the "review opens on draft PRs and next steps" pattern that Jeffrey uses. Combines `gh pr list --json`, `cmux tree --all`,…
Use when handing a Jeff-approved, setting-agnostic god-mode/divine mechanic to AO — covers "generic" framing rules, the four-mechanic contract set (avatar partition/dual-sheet, original→shell interpolation, shell-vs-original separation, rank-anchored DHP),…
Query and fetch Granola meeting notes from the terminal. Wraps the Granola MCP server via `mcporter` (joelhooks/granola-mcp-plus). Use when Jeffrey asks about "my meetings", "meeting notes", "what did we discuss in <meeting>", action items from a call, or…
Harness-fix meta-skill (slash: /meta) — analyze an agent behavior failure and run /harness to fix the agent, NOT the underlying task. Input: Slack thread URL, pasted conversation, or freeform description of agent misbehavior. Re-anchored on MAST…
Enforce the Hermes deploy pipeline — always write to ~/.hermes first, test, then deploy to ~/.hermes_prod. Use whenever creating or modifying launchd jobs, scripts, configs, or any file that needs to run in the Hermes production environment.
Bootstrap or upgrade a software repository for agent-first engineering. Use when a user wants to improve project-wide development discipline around `AGENTS.md`, progressive-disclosure docs, agent-readable architecture/context, mechanical quality checks,…
Delegate coding change tasks to Agent-Orchestrator (AO). Triggered by the keyword "agento" anywhere in a message, or by default for any coding task. Never use mctrl unless explicitly requested.
Run or maintain the cmux approval worker that scans cmux terminal surfaces for approval dialogs, classifies them with `codex exec`, and sends the matching approval key. Use when testing or operating the launchd-based auto-approver, debugging missed prompts,…
Control cmux terminal multiplexer via its Unix socket API. Use when needing to: (1) List, create, select, or close workspaces; (2) Split panes and manage surfaces; (3) Send text or key presses to terminals; (4) Create notifications; (5) Set sidebar status,…
Dispatch a bead-tracked task via ao spawn/ao send, register the mapping, and ack in Slack thread. Includes the `env -i` ARG_MAX wrapper, the `running.json` bootstrap for "lifecycle polling is inactive" errors, the post-spawn branch-reset + copy-briefs + `ao…
Fix LLM narration drift (LLM improvises formatting because a prompt line is too vague) by adding a worked example in the prompt, NOT by adding backend enforcement. Use when the user reports the LLM is dropping fields, abbreviating formats, or substituting its…
Diagnose whether the prompt content on disk actually reaches the LLM on the wire. The class-level umbrella for any case where the user complaint looks like a prompt-content problem (rule is wrong, format is off, instruction is missing) but the real root cause…
Canonical reference for the SOUL.md COMMIT `mcp-agent-mail-no-passive-slack-listening`. Use when asked to (a) verify MCP Agent Mail is not listening/posting into Slack, (b) re-enable the Slack bridge (rare; requires explicit "ENABLE MCP MAIL SLACK BRIDGE"),…
MCP client: connect servers, register tools (stdio/HTTP).
Capture screen activity to a captioned MP4 video — the full pipeline from screen-recording to a publishable, captioned video. Triggers when the user asks for "captioned MP4 proof", "MP4 with subtitles", "screen recording with captions", "video walkthrough",…
Search across all memory systems — ~/roadmap, beads, claude memories, hermes sqlite, hermes briefings, hermes index, wiki, history, and slack. Use whenever the user asks to search memories, find something in memories, or looks for anything that might have…
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework