Plain
Re-explain a dense, jargon-loaded, or code-stuffed response in plain, generous
Install
$ agentstack add skill-dtiger1889-ops-claude-harness-toolbox-plain ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-dtiger1889-ops-claude-harness-toolbox-plain) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
plain -- translate a dense/jargon response into plain English
The standing rule this enforces: understandable, digestible English in chat -- every self-invented code glossed in plain words, nothing buried under process narration. It keeps getting violated -- responses come back stuffed with filing codes (F027, B13, PTT, a def_hash...), unexpanded acronyms, and compressed noun-stacks that are a wall to read. This skill is the fix: take that response and SAY IT AGAIN in plain, conversational, generous English.
This is the ANTI-terse skill -- the opposite of /breakdown. Length is fine; losing meaning is not.
What to translate
Default target: the immediately previous assistant message. If the user pasted text or @-mentioned a file/block, translate that instead. If it is ambiguous which, ask once.
How to do it
- RESOLVE every code, tag, and acronym to its real meaning -- do NOT guess. When a
filing code / phase name / gate name / hash appears, look it up in the project files (e.g. findings.md, CHECKPOINT.md, the relevant spec) and state what it actually IS in people-words. If you genuinely cannot find what a code refers to, say "I couldn't find what X refers to" -- never bluff a meaning.
- Re-express, don't summarize. Keep ALL the substance. This is a translation, not a
trimmed recap; dropping detail to be shorter is the failure mode.
- Unpack compressed noun-stacks and nested clauses into short, ordinary sentences.
- Introduce NO new shorthand -- no codes, no project jargon. If a technical term is
genuinely unavoidable, define it inline the first time you use it.
- Structure for reading -- short paragraphs or a plain list, not a block.
Rules
- Plain, conversational English, structured to be digestible: answer first, short
paragraphs, expansive enough to define every term -- never a wall of text.
- Never invent a meaning for a code you couldn't resolve.
- Don't add new analysis, opinions, or next steps -- just make the existing content legible.
If the user wants more, they'll ask.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dtiger1889-ops
- Source: dtiger1889-ops/claude-harness-toolbox
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.