Регистрация косяка агента в системе учёта WP-316 L1. Без LLM — детерминированный скрипт без WP Gate.
日本語の概要は準備中です。原文の説明を表示しています。
Create a new IWE skill with proper frontmatter, gates, scaffold and verification. Use when the pilot says: /skill-creator or «создай скилл <name>». The skill enforces WP Gate precondition, Routing Gate, IntegrationGate hard-check, collects parameters in 4 short steps, generates a scaffold SKILL.md from a template, shows a draft, writes files, and reminds about verify-skill.sh.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Scope: create a new skill OR guide an update to an existing skill in
.claude/skills/or.kimi/skills/. Not in scope: full re-scaffold without deleting the oldSKILL.mdfirst (delete manually, then call/skill-creatoragain); creating a WP; creating a Pack. Role: ad-hoc content-role «Инженер скиллов»; formalize in Pack if ≥3 skills/year.
FMT-exocortex-template./skill-creator does not conduct the WP Gate ritual itself..claude/skills/ in the author repo.DP.SC.* and DP.ROLE.* must exist in the PACK repo. If not, the skill stops and offers to create them. Bypass only by explicit pilot instruction «пропусти gate» — no code flag.Look up the current weekly plan (current/WeekPlan W{N}.md) or ask:
К какому РП привязано создание скилла?
If no WP is named and none matches the skill topic → stop:
Создание скилла требует согласованного РП. Сначала откройте РП через WP Gate.
Ask or infer:
| Question | Default |
|---|---|
| Claude или Kimi? | Claude |
| project-level или user-level? | project-level |
| governance-репо для учёта? | ${IWE_GOVERNANCE_REPO:-DS-strategy} |
Target path:
.claude/skills/<name>/.kimi/skills/<name>/~/.claude/skills/<name>/ or ~/.kimi/skills/<name>/Check whether <target_path>/SKILL.md already exists.
If it exists → switch to update mode. Do NOT re-scaffold. Show the pilot:
Скилл <name> уже существует (версия X.Y.Z).
Что обновить?
[ ] description
[ ] slash / phrase triggers
[ ] version bump (current: X.Y.Z → new: ?)
[ ] algorithm step (add / edit)
[ ] bundled resource (add scripts/ references/ assets/)
[ ] полный пересоздать → удалите SKILL.md вручную, затем запустите /skill-creator снова
[ ] отмена → ничего не менять
Collect the pilot's choices. A requested description must contain at least 10 words; if shorter, explain the validation requirement and ask for an expanded wording before editing. Apply agreed changes directly to the existing SKILL.md via Edit.
Skip Steps 3–6 unless the pilot selected "bundled resource" or any change that expands the skill's scope or gates — in that case, run Step 3 (IntegrationGate) before applying.
For Step 7 (register + verify): run verify-skill.sh always. Run generate-skills-catalog.sh only if frontmatter changed (name, description, triggers, version).
Version bump rule: bump patch for trigger / description edits; bump minor for algorithm changes or adding a bundled resource; bump major for gate or scope changes.
If it does not exist → continue to Step 3 (normal creation flow).
Check PACK repo for files matching DP.SC.* and DP.ROLE.*. If missing:
Service Clause (DP.SC.*) и Role (DP.ROLE.*) не найдены.
Создайте их сейчас через /pack-new или соответствующий процесс.
Для продолжения без них скажите явно: «пропусти gate».
Stop until the gate is satisfied or explicitly bypassed by pilot words.
4a. Name and description
Имя скилла (hyphen-case): <name>
Краткое описание — что делает и когда использовать:
The description must contain at least 10 words; count the YAML value, not surrounding metadata.
4b. Agents and interaction axes
agents: single | multi
interaction: one-shot | multi-step
4c. Triggers
slash-команды (через запятую):
фразовые триггеры (через запятую):
Keep phrase triggers narrow: include a skill name placeholder to avoid accidental activation.
4d. Bundled resources
Какие bundled resources нужны?
[ ] scripts/
[ ] references/
[ ] assets/
Default: assets/ for scaffold template, scripts/ for verify script.
Choose scaffold template based on skill complexity:
assets/skill-scaffold-minimal.md): single-step skills without external gatesassets/skill-scaffold-full.md): multi-step skills with Preconditions and Bundled resourcesCopy chosen template to target path and substitute:
{{name}}, {{description}}, {{version}} (default 0.1.0), {{status}} (default experimental){{agents}}, {{interaction}}, {{layer}}{{slash_triggers}}, {{phrase_triggers}}{{gates_rationale}} — required when gates_required and gates_enforced are both emptyCreate selected bundled resource directories with placeholder files.
Print generated SKILL.md and file list to stdout. No P5 question. Pilot can cancel with:
/skill-creator undo
Undo works only before next commit or within 15 minutes.
Write files to target path. Then regenerate the catalog and run verify:
# Run from the workspace root. Set these two paths from the routing decision;
# creator_dir is the directory containing THIS instruction, not the new skill.
skills_dir=.claude/skills
creator_dir=.claude/skills/skill-creator
workspace="$PWD"
template_root="${IWE_TEMPLATE:-$workspace/FMT-exocortex-template}"
if [ -f "$workspace/update-manifest.json" ] && [ -f "$workspace/scripts/generate-skills-catalog.sh" ]; then
template_root="${IWE_TEMPLATE:-$workspace}"
fi
catalog_script="$workspace/scripts/generate-skills-catalog.sh"
if [ ! -f "$catalog_script" ]; then
catalog_script="$template_root/scripts/generate-skills-catalog.sh"
fi
catalog_output="$(dirname "$skills_dir")/skills-catalog.yaml"
if ! IWE_WORKSPACE="$workspace" bash "$catalog_script" \
--skills-dir "$skills_dir" --output "$catalog_output"; then
echo "Catalog generation failed; verification was not run." >&2
exit 1
fi
IWE_WORKSPACE="$workspace" IWE_TEMPLATE="$template_root" \
bash "$creator_dir/scripts/verify-skill.sh" <name> "$skills_dir"
Both commands must pass before the skill is considered created. For Kimi targets set skills_dir=.kimi/skills; if this instruction is installed there too, set creator_dir=.kimi/skills/skill-creator. If either tool is absent, stop with the missing path rather than claiming verification.
The verifier uses the shared workspace scripts/lib/find-python3.sh and the declared PyYAML and markdown-it-py dependencies in requirements.txt. Metadata must be the first complete YAML block; duplicate keys, invalid types, and empty required values fail. Required Markdown sections must be real headings outside code examples. Bundled resources are checked in scripts/, assets/, and references/.
Tell the user where the new skill lives and that nothing preserves it (issue #873): a
project-local skill under .claude/skills/<name>/ is usually outside git and outside the
day-close.sh backup, and update.sh neither erases nor carries it over. Until the template
owner picks a backup model, suggest keeping a copy in a git repository the user controls.
For skills with interaction: multi-step: run /vdv audit on the Algorithm section.
Not a gate — does not block creation — but catches steps with missing Input/Output linkage
before the skill is used in practice.
assets/skill-scaffold-minimal.md — scaffold for single-step skills without external gatesassets/skill-scaffold-full.md — scaffold for multi-step skills with Preconditions and Bundled resourcesscripts/verify-skill.sh — CLI wrapper using the shared Python resolverscripts/verify-skill.py — validates YAML metadata, gates, real sections, bundled resources, templates and platform-specific L1 locationFields used by some existing skills but not yet in the standard frontmatter schema:
argument-hint — CLI-style hint for script-executor skills (e.g. agent-fault, apply-captures). Encodes the argument contract. Keep until schema is extended or absorbed into description.routing.executor — indicates whether the skill runs via script, sonnet, or another executor. Useful for the dispatcher but not validated by verify-skill.sh. Candidate for standardization.Until standardized: leave these fields as-is in existing skills; do not remove during Step 2.5 updates.
content-audit.sh coverage (Ф9): audit script checks 5 structural criteria (gates_rationale, Algorithm section, step headings ≥3, step content ≥2 lines, When-to-use section). 7 YELLOW skills (single C3 issue) are simple alias/mode skills without numbered step headings. This is structural noise, not content error — these skills are functionally correct. See scripts/content-audit.sh for full output.generate-skills-catalog.sh after writing files (Step 7) — not before, not manually.scripts/verify-skill.sh.verify-skill.sh after editing an existing skill — always run it after any update.After creation, run:
bash .claude/skills/skill-creator/scripts/verify-skill.sh <skill-name> .claude/skills
Expected result: PASS with checks for: valid YAML frontmatter, description of at least 10 words, recognized non-empty triggers, gates_required/gates_enforced fields with valid enum values, bundled resource files exist, scaffold templates valid, L1 skills present in FMT.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Регистрация косяка агента в системе учёта WP-316 L1. Без LLM — детерминированный скрипт без WP Gate.
日本語の概要は準備中です。原文の説明を表示しています。
Разбор extraction-reports со status pending-review — решение R15 (accept/reject/defer) ЖИВЫМ ПИЛОТОМ, запись в Pack, обновление статуса, коммит. Вызывать при Close при наличии N>0 pending-review отчётов.
日本語の概要は準備中です。原文の説明を表示しています。
Оценка архитектурного решения по 7 характеристикам ЭМОГССБ (v3.1 — фильтр допуска, атрибут-сценарии, совет затронутых сторон; профиль без агрегатного балла, conjunctive screening). Используй когда пользователь предлагает архитектурное решение, новый инструмент или системное изменение.
日本語の概要は準備中です。原文の説明を表示しています。
Classifies raw pilot request → structured JSON {task_type, class, artifact, budget_estimate, confidence, routing_tag, resolution_path, schema_version, result_type, expected_result_kind, result_kind_resolution, hypothesis_relation}. Keyword-fast (<200ms) or Haiku fallback (<60s). Does NOT create WP or call executor.
日本語の概要は準備中です。原文の説明を表示しています。
Audit repository documentation: detect drift between code and docs, report coverage by category. Run manually or on triggered drift critical.
日本語の概要は準備中です。原文の説明を表示しています。
Аудит пользовательской инсталляции IWE. Запускает scripts/iwe-audit.sh + MCP healthcheck + smoke-test ритуала через sentinel-механику (контракт dry-run-contract.md), передаёт отчёт subagent'у в роли VR.R.002 Аудитор (context isolation) → verdict ✅/⚠️/❌ по 6 компонентам (Inventory, L1 drift, DS-strategy, L3 customizations, MCP, ритуал). Используй после restore из бэкапа, после update.sh, или при еженедельной сверке.
日本語の概要は準備中です。原文の説明を表示しています。