Individual skill

cognitive-input-classifier

任意输入的路由分类器。在输入意图不明确时,判断应走「认知更新路径A(cognitive-capture-fragment)」还是「任务执行路径B(对应任务Skill)」,输出明确路由结论 + 判断理由,不自动触发下游。触发词:「帮我判断这是认知更新还是任务执行」「这个输入是什么类型」「先分类再执行」「路由分类一下」。不应触发:关于计算机网络路由算法的技术问题。

skills/cognitive-input-classifier/SKILL.md

Read pinned source

Source commit 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
Yes
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Claude Code

Destination .claude/skills/cognitive-input-classifier

( set -euo pipefail destination='./.claude/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.claude/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )
Codex

Destination .agents/skills/cognitive-input-classifier

( set -euo pipefail destination='./.agents/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.agents/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )
Cursor

Destination .cursor/skills/cognitive-input-classifier

( set -euo pipefail destination='./.cursor/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.cursor/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )
Gemini CLI

Destination .gemini/skills/cognitive-input-classifier

( set -euo pipefail destination='./.gemini/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.gemini/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )
GitHub Copilot

Destination .github/skills/cognitive-input-classifier

( set -euo pipefail destination='./.github/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.github/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )
OpenCode

Destination .opencode/skills/cognitive-input-classifier

( set -euo pipefail destination='./.opencode/skills/cognitive-input-classifier' if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi work=$(mktemp -d) trap 'rm -rf -- "$work"' EXIT git clone --filter=blob:none --no-checkout -- 'https://github.com/TashanGKD/cognitive-os.git' "$work/repo" git -C "$work/repo" checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22 git -C "$work/repo" archive --format=tar '50267ccd7a3d7db2bd7bc2578c39cd93a3428d22:skills/cognitive-input-classifier' > "$work/skill.tar" mkdir -p -- './.opencode/skills' mkdir -- "$destination" tar -xf "$work/skill.tar" -C "$destination" )

Repository context

Repository stars (not skill ratings)
11
Repository last updated
Mar 26, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# 认知输入分类器(cognitive-input-classifier)

> 强绑定 Rule:R2 NO_FABRICATION(判断理由必须基于输入文本中实际存在的信号词)
> R13 RULE_BEATS_STYLE(准确判断优先于表述流畅)

---

## 核心原则

**判断理由必须基于文本证据**:从用户输入中找到具体信号词,引用它来支撑结论。不允许「感觉上像认知更新」这类无证据判断。

**混合时强制拆分**:同时发现两类信号词时,必须走「AB混合」分支,不允许取占比大的一类压过另一类。

**无法判断时只有两个出口**:追问一次,或默认路径B并告知可纠正。不允许输出「这是一个既有认知又有任务性质的输入」类模糊结论。
Back to top