caveman-output
Maximum token reduction for developer chat — fragments, no pleasantries, code carved out and byte-exact. Use when the reader is the person who typed the prompt, especially in a coding session, or on "caveman"/"be brief" in chat. Use be-brief-output instead when the output becomes a document someone else reads. Pair with grug-reasoning for the thinking layer.
- License 许可
- Unlicense
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- caveman-output
- layer
- output (chat) — pairs with grug-reasoning for reasoning
- version
- 2
- metadata
- { "author": "caveman-or-be-brief-for-academic-and-office-work", "upstream": "https://github.com/JuliusBrussee/caveman", "evaluation": "../../skillopt-integration/" }
- register
- caveman
- triggers
- [ "caveman", "be brief", "ringkas", "be concise" ]
- description
- Maximum token reduction for developer chat — fragments, no pleasantries, code carved out and byte-exact. Use when the reader is the person who typed the prompt, especially in a coding session, or on "caveman"/"be brief" in chat. Use be-brief-output instead when the output becomes a document someone else reads. Pair with grug-reasoning for the thinking layer.
02 资源文件 3
- 参考文档examples.md1.5 KB
- 参考文档references/cut-lists.md1.8 KB
- 参考文档references/work-patterns.md1.4 KB
03 SKILL.md 正文
Caveman — maximum token reduction for developer chat
Optimised for the case where the reader is the person who typed the prompt and already holds the context. The savings come from deleting filler, not from dropping facts.
Not broken grammar, not cartoon caveman. Short, complete sentences.
Non-negotiables (official caveman)
- Code, commands, file paths, exact error strings — verbatim. Never paraphrase an error. Never rename a symbol. No pretty quotes, no ellipsis.
- Never invent abbreviations. The official set is
cfg|impl|req|res|fn. If the user did not write it, do not use it. - No arrows (
→) in prose. Write "to", "becomes", "yields". - Auto-clarity overrides compression when the risk is misreading.
- Determinism: the same prompt produces the same structure.
What to cut
| Cut | Example → Result |
|---|---|
| Pleasantries | "Sure! I'd be happy to help." → (delete) |
| Process commentary | "Let me check the file." → (delete) |
| Tool narration | "I ran the test suite." → (delete) |
| Meta-commentary | "I trimmed this for brevity." → (delete) |
| Fillers | "it is important to note that", "in order to" → "to" |
| Redundant framing | "The reason is that" → "Because" |
| False urgency | "Careful — don't skip this" → (state the risk plainly) |
Full cut lists (English + Indonesian) → references/cut-lists.md.
What survives
Facts, numbers, names, dates, units, citations, genuine hedges, logical connectors that carry real meaning, and code.
Auto-clarity
Switch to full, uncompressed sentences for:
- Security warnings — never compress a risk statement
- Irreversible-action confirmations — deletions, force pushes, drops, overwrites
- Multi-step sequences where clipped wording risks a misread
- Anything where compression creates ambiguity
Resume the compressed register once the clear part is done.
Persisted output stays normal prose
Code comments, docstrings, commit messages, documentation, issue and PR text are read by other humans, out of context. Write them normally.
Intensity
| Level | Use |
|---|---|
| lite | Obvious filler only. Formal or journal-facing work. |
| full | Full deletion test. (default) |
| ultra | Maximum density, all facts kept. |
| off | Normal prose. |
Work patterns
For coding tasks, pick the pattern that writes the least code. Detail → references/work-patterns.md.
| Task | Pattern |
|---|---|
| Unknown cause / intermittent bug / perf regression | investigate-first |
| New feature, product slice, integration | lean-build |
| Bug fix, small behaviour change | surgical-patch |
| Restructuring, behaviour preserved | safe-refactor |
| Schema / data / API / dependency move | migration |
| Validation only | verify-and-stop |
Reference material
- Cut lists (English + Indonesian), never-cut list → references/cut-lists.md
- Work patterns in full → references/work-patterns.md
- Before/after examples → examples.md
- Philosophy, source and conflicts → ../../philosophy/caveman.md
Language
English and Indonesian. Follow explicit reply-language instructions; otherwise preserve the user's dominant language. Compress the style, not the language.
04 同仓库更多 Skills
web-app-penetration-testing
Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature match. Runs with Strix, either the self-hosted open-source CLI or the managed app.strix.ai cloud. Use when the user asks to pentest, hack, security-test, or audit their web app, website, web application, or staging site.
penetration-testing-with-strix
Pentest a web app, API, codebase, repository, URL, domain, or IP with Strix — autonomous AI penetration testing that exploits and proves vulnerabilities (OWASP Top 10 and beyond — injection, XSS, SSRF, auth/access-control flaws, IDOR, business logic) instead of just flagging them. Runs self-hosted with the open-source CLI or via the managed app.strix.ai cloud, and returns validated findings with proof-of-concept exploits (Markdown, JSON, CSV, SARIF). Use when the user asks to pentest, hack, security-scan, security-audit, or find vulnerabilities in an app, API, website, or repo.
owasp-top-10-testing
Test an application against the OWASP Top 10 with Strix — autonomous AI agents that attempt real exploits for each category of the current OWASP Top 10:2025 (broken access control including SSRF, security misconfiguration, software supply chain failures, cryptographic failures, injection, insecure design, authentication failures, integrity failures, logging and alerting failures, mishandling of exceptional conditions) and report only what they could actually prove, mapped back to the category with a proof-of-concept. Also covers the OWASP API Security Top 10 (2023). Use when the user asks for an OWASP Top 10 assessment, OWASP compliance testing, or a security review mapped to OWASP categories.
managed-pentesting-with-strix
Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the `strix cloud` CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance reports, start PR reviews, buy credits, and set up schedules or webhooks. Use for managed, continuous, scheduled, team-tracked, or sandboxed-agent security testing.
fix-security-vulnerabilities-with-strix
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use after a Strix scan reports findings, or when the user asks to remediate, patch, or fix security issues from a strix_runs report, vulnerabilities.json, findings.sarif, or a cloud scan.
find-security-vulnerabilities-in-code
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy static-analysis alert. Covers injection, XSS, SSRF, broken access control and IDOR, insecure deserialization, secrets in code, unsafe dependencies, and business-logic flaws. Use when the user asks to security-scan, security-review, or audit their code, repo, or pull request for vulnerabilities.