- Skills
- 57
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 2
JAB Works 的 Skills 57
orphan
暂无简介
no-blurb
暂无简介
workflow
Routes any dev task into the right execution tier (Small/Medium/Large) and carries condux's operating rules — proportional effort, lazy skill loading, soft gates, implement-yourself-by-default.
usage-trace
Checks and manages durable, local usage capture — ingest, health status, and the opt-in limit snapshot — for Claude Code and Codex. Capture itself runs automatically at session start.
toolkit-skill-standards
Use when writing or reviewing a SKILL.md for jabworks/agentic-toolkit — frontmatter budgets, the trigger contract ("Use when…" description or when_to_use field), progressive disclosure into references/, and keeping a new description out of existing skills' trigger space. Triggers include "review this skill description", "write the frontmatter", "does this collide with an existing skill", "where should this content live". Not for scaffold/sync mechanics; use toolkit-foundry.
toolkit-research-frontier
Use when planning improvement work on jabworks/agentic-toolkit itself — open problems (trigger-collision automation, YAML-strict frontmatter checks, docs-catalog enforcement), existing assets, the next three concrete steps, and the four-front library-health campaign with commands and success criteria. Triggers include "let's improve our toolkit", "let's improve this repo", "what should we improve next", "toolkit roadmap", "open problems", "run the health campaign".
toolkit-plugin-reference
Use when writing or editing plugin.json, marketplace.json, or package manifests in jabworks/agentic-toolkit and the exact schema matters — required fields, the .claude-plugin/.codex-plugin pairing and where it diverges (interface, hooks), the skills-path form, how the four install channels consume the repo, and which SKILL.md frontmatter fields are real. Triggers include "what fields does plugin.json need", "claude vs codex manifest", "marketplace entry format", "how opencode loads skills".
toolkit-orientation
Use when landing in jabworks/agentic-toolkit with no context — mapping skills/ vs dist/plugins/ vs dist/opencode/ vs dist/cursor/ vs packages/, which tree is editable, how bundles (condux, toolkit-ops) nest, which docs to trust, and where NOT to write. Triggers include "how is this repo organized", "where do skills live", "what is dist for", "which files are generated", "where do I edit this skill".
toolkit-foundry
Use when creating a new skill for jabworks/agentic-toolkit, registering it, or shipping the generated trees — "scaffold a new skill", "register this skill", "sync dist", "bump the toolkit version" — plus changes to the @jabworks/condux npm package. Not for adapting a generic skill to the jabworks stack (adapting-skills), nor for reviewing a SKILL.md's content and trigger wording (toolkit-skill-standards).
toolkit-failure-archaeology
Use when about to re-fight an old battle in jabworks/agentic-toolkit — checking whether a mistake happened before, mining git history for precedent, or recording a new incident. Holds the evidenced incident ledger (dist drift, YAML breakage, missed registration, stale plugin caches) with commit hashes and the doctrine each produced. Triggers include "has this happened before", "why do we do it this way", "add this to the ledger". Not for recalling past sessions; use concord:remember.
toolkit-debugging-playbook
Use when a skill or plugin from jabworks/agentic-toolkit misbehaves — a skill doesn't trigger, a plugin doesn't show up after install, dist looks out of date, the installed copy differs from the repo, or a manifest fails to parse. Symptom → first discriminating command → root cause, with false friends and stop-and-ask points. Triggers include "why isn't my skill triggering", "why isn't X showing up", "plugin not showing up", "dist drift", "stale plugin", "skill broken".
toolkit-change-control
Use when deciding whether a change to jabworks/agentic-toolkit is done and safe to ship — classifying the change (including retiring a skill or a hook), picking the version bump, and gating on the publish checklist (mirror synced, manifests paired, marketplace entry, node --test green). Triggers include "is this skill shipped", "am I done shipping this skill/plugin", "ready to publish", "what version do I bump", "did I register this plugin", "retire this skill", "remove this hook".
test-first-development
Tests-first development — write tests before implementation. Opt-in only: one upfront consent (write tests first + auto-run), then run the cycle without re-asking.
technical-spec
Persists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree — one folder per feature, one file per concern.
subagent-execution
Execute a plan using named specialist agents. Default is to implement yourself — only spawn when there is a concrete justification.
subagent-deployment
Fan out 2+ independent tasks across named agents (explorer/researcher/planner/coder) in a single message when they share no files and no dependencies. For ad-hoc independent work discovered outside a formal plan.
spec-browser
Use when there are many tech specs under specs/ and you need to navigate them as one doc site, generate a catalog agents can reference, or answer "what specs do we have / where is the spec for X". Triggers include "browse specs", "spec index", "list all specs", "spec site", "navigate specs".
session-report
Generates a self-contained HTML report of session usage — tokens, cache efficiency, subagent costs, and slash command frequency — from local transcripts.