← All skills
run-system-spec-elicit
97 / 100 · Low risk
Fine to try.
By daishiman/harness-dev (GitHub) · other · 10 stars · scanned at commit 3e1b394
システム仕様のヒアリングを開始するとき、システム構築の要件をカテゴリ×プラットフォームの収集マトリクスで往復ヒアリングして spec-state.json に確定させたいときに使う。
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed.
Found in 19 places.
Show 16 more
- plugins/system-spec-harness/skills/run-system-spec-elicit/tests/test_spec_transition.py, line 191
proc = subprocess.run( - plugins/system-spec-harness/tests/test_guard_hook.py, line 432
'bash -c "echo x > system-spec/database.md"', - plugins/system-spec-harness/tests/test_guard_hook.py, line 713
return subprocess.run( - plugins/system-spec-harness/tests/test_guard_hook.py, line 745
proc = subprocess.run( - plugins/system-spec-harness/hooks/guard-confirmed-chapter-overwrite.py, line 55
bash -c / eval は中身を同じ規則で再帰的に解析する。heredoc の本文はコードとして実行される - plugins/system-spec-harness/hooks/hooks.json, line 10
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/guard-confirmed-chapter-overwrite.py\"", - plugins/system-spec-harness/hooks/hooks.json, line 22
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/record-audit-fork.py\"", - plugins/system-spec-harness/hooks/hooks.json, line 33
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/record-audit-fork.py\" --event subagent-stop", - plugins/system-spec-harness/hooks/references/hook-guard-protection-scope.md, line 48
4. **入れ子の shell**: `bash -c` / `sh -c` / `eval` / shell の heredoc は中身を同じ規則で再帰的に解析する (深さ上限 3)。 - plugins/system-spec-harness/hooks/tests/test_guard_confirmed_chapter_overwrite.py, line 184
self.assertEqual(self.bash("env -i F=system-spec/spec-state.json sh -c 'cp x $F'"), 2) - plugins/system-spec-harness/hooks/tests/test_guard_confirmed_chapter_overwrite.py, line 341
入れ子 shell 経由 (`env -i F=... sh -c 'cp x $F'`) は bash -c の再帰解析で塞がり、 - plugins/system-spec-harness/hooks/tests/test_record_audit_fork.py, line 353
def _run(self, payload: dict, ledger: Path) -> subprocess.CompletedProcess: - plugins/system-spec-harness/hooks/tests/test_record_audit_fork.py, line 357
return subprocess.run( - plugins/system-spec-harness/hooks/tests/test_record_audit_fork.py, line 451
def run_one(index: int) -> subprocess.CompletedProcess: - plugins/system-spec-harness/hooks/tests/test_record_audit_fork.py, line 471
proc = subprocess.run( - plugins/system-spec-harness/hooks/tests/test_record_audit_fork.py, line 564
proc = subprocess.run(
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'run-system-spec-elicit' ] || [ -L ~/.agents/skills/'run-system-spec-elicit' ]; then echo 'A skill folder named run-system-spec-elicit already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/daishiman/harness-dev' "$d" && git -C "$d" checkout --quiet '3e1b394bd699e07d0b030acd44ee12f9143f89eb' -- 'plugins/system-spec-harness/skills/run-system-spec-elicit' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/system-spec-harness/skills/run-system-spec-elicit' ~/.agents/skills/'run-system-spec-elicit' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'run-system-spec-elicit' ~/.claude/skills/'run-system-spec-elicit' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for daishiman/harness-dev shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/daishiman/harness-dev/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | 3e1b394 | 97 |
| 2026-11-08 | d629311 | 97 |
| 2026-11-06 | e63e798 | 92 |