claude-harness-toolbox

In the author's own words, from each skill's SKILL.md.

• breakdown

  Decomposes one tangled problem into a smallest next action and a compact plan. Use only for /breakdown, "break this down", "break it down", or "decompose this". For open-ended ideation use fanout; skip when the task is already one clear action.

  skills/breakdown/SKILL.md on GitHub (opens in a new tab)

• checkpoint

  Updates the current project's CHECKPOINT.md in place so another session can resume from verified state. Use for /checkpoint, "save progress", "update checkpoint", a completed unit of work, or impending compaction. Preserves history, records unfinished work, and runs bundled validation and size checks. Project-specific conventions override the default schema.

  skills/checkpoint/SKILL.md on GitHub (opens in a new tab)

• dumb

  Corrects an immediately previous response or action that the user says was wrong, incomplete, lazy, or missed the point. Use for /dumb and corrections such as "that was dumb", "fix it", "that's not done", or "you skipped" directed at the previous work. Delivers the correction and records reusable lessons.

  skills/dumb/SKILL.md on GitHub (opens in a new tab)

• fanout

  Runs five parallel ideation agents with distinct perspectives, then a critic, for an open-ended problem. Use only for /fanout, "run a fanout", "fanout this", or "give me frames on X". Intended for design, naming, strategy, and hypotheses with multiple valid answers; unsuitable for routine verification or debugging with one checkable answer. Uses substantially more model calls than a single review.

  skills/fanout/SKILL.md on GitHub (opens in a new tab)

• grill-me

  Interviews the user before new work, then records an agreed build brief. Use for /grill-me, "interview me first", or the first build of a new project, milestone, app, skill, automation, document, or design. Skip fixes, edits, explanations, one-shot commands, work with an existing spec, and unattended sessions.

  skills/grill-me/SKILL.md on GitHub (opens in a new tab)

• log

  Records reusable facts, corrections, decisions, and rule violations in the document or ledger that owns them. Use for /log, "log this", "capture this", "write that down", "don't lose this", or "log that lapse". Complements checkpoint, which owns project resume state; does not run on every answer.

  skills/log/SKILL.md on GitHub (opens in a new tab)

• necromancy

  Recovers a Claude Code session that ended before its checkpoint was saved, using a deterministic digest of the local session store. Use for /necromancy, "recover the dead session", "resurrect that session", or a crash before checkpointing. Does not recover other agents' stores, editor autosaves, or git artifacts.

  skills/necromancy/SKILL.md on GitHub (opens in a new tab)

• new-project

  Scaffolds a new project folder from the harness templates and -- the load-bearing half -- registers it everywhere it must appear (the project ledger, any container index, its backup lane). Use when the user says "/new-project", "new project", "set up a project for X", or promotes an outgrown scratch folder to a project of its own. Do NOT use for adding a subfolder inside an existing project, or f…

  skills/new-project/SKILL.md on GitHub (opens in a new tab)

• outside

  Checks prior art, related workspace projects, and relevant notes before choosing an approach. Use for /outside, "get an outside view", "check prior art", "are we reinventing the wheel", or "has anyone already built this". Runs one bounded reconnaissance pass without helper agents.

  skills/outside/SKILL.md on GitHub (opens in a new tab)

• plain

  Re-expresses a dense response in plain English while preserving its substance. Use for /plain, "say that in plain English", "de-jargon this", "unpack that", or "explain that like a normal person". Targets the previous assistant message unless the user supplies another passage. Picture mode, only when asked (/plain show, or "show me" about an answer), re-explains with the smallest plain-text pictu…

  skills/plain/SKILL.md on GitHub (opens in a new tab)

• prevent

  Corrects a repeated or documented mistake and strengthens the failing workflow so the rule is encountered or enforced at decision time. Use for /prevent, "we've talked about this", "you should know this", "this is documented", or "why do you keep doing this" about previous work. Delivers a durable workflow change, not a promise.

  skills/prevent/SKILL.md on GitHub (opens in a new tab)

• prove

  Verifies disputed factual claims in a previous response against actual sources. Use for /prove, "prove it", "did you make that up", "source?", or "where did you get that" about an earlier assertion. Reports confirmed, wrong, or unverified claims with citations and corrects the answer.

  skills/prove/SKILL.md on GitHub (opens in a new tab)

• redteam

  Runs one adversarial review of a claim, plan, or answer. Use only for /redteam, "push back on this", "red-team this", or "stress-test this". Identifies failure mechanisms and the cheapest way to test them. For broader ideation use fanout; for source verification use prove.

  skills/redteam/SKILL.md on GitHub (opens in a new tab)

• spec

  Writes or reviews a change or decision spec with explicit tradeoffs and closeout criteria. Use for /spec, "spec this", "write a spec", review of a spec's open questions, or closing, archiving, and promoting a finished spec. Does not authorize implementation by itself.

  skills/spec/SKILL.md on GitHub (opens in a new tab)

• spinoff

  Starts a separate session for a side topic from a short brief rather than copying the whole conversation. Use only for /spinoff, "spin this off", "hand this off to a new session", or "take this to its own session". Does not trigger automatically or replace a conversation fork.

  skills/spinoff/SKILL.md on GitHub (opens in a new tab)

• vet

  Decides whether someone else's repo, skill, plugin or MCP server is worth adding to this workspace, and records the verdict in a ledger where the next session finds it. Use when the user drops a link or a list of links and asks if it is useful, worth adding or worth stealing, says "eval this", "vet these", "should I install this", "is this worth it", or points at a note full of tools to triage; a…

  skills/vet/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 366k stars · 1 skill
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 287k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 223k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 173k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 139k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 133k stars · 1 skill