skillify
When you want to create, adapt, or update a Claude Code skill in one of your sibling repos (list your own repos in ~/.config/makerskills/skillify/repos.yaml; defaults to makerskills). Routes to the right mode automatically. Modes — CREATE (from-chat / from-video / from-dump / from-scratch) turns a workflow, brief, recording, or fresh idea into a new skill. ADAPT ports an external skill (GitHub URL, agentskills.io, local disk) into your namespace with three-bucket classification (keep/adapt/add) + license check + attribution. UPDATE improves existing skills from learnings with cross-skill propagation, memory-vs-skill triage, and semver discipline. Defers to Anthropic's guidance (compound-engineering:create-agent-skill, compound-engineering:skill-creator, compound-engineering:heal-skill) for schema and best-practice depth. Triggers on "/skillify," "create a skill," "make this a skill," "skill from this chat," "extract a skill from what we've been doing," "adapt this skill," "port this sk
coreyhaines31 · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add coreyhaines31/makerskills --skill skillify技能说明
name: skillify description: When you want to create, adapt, or update a Claude Code skill in one of your sibling repos (list your own repos in ~/.config/makerskills/skillify/repos.yaml; defaults to makerskills). Routes to the right mode automatically. Modes — CREATE (from-chat / from-video / from-dump / from-scratch) turns a workflow, brief, recording, or fresh idea into a new skill. ADAPT ports an external skill (GitHub URL, agentskills.io, local disk) into your namespace with three-bucket classification (keep/adapt/add) + license check + attribution. UPDATE improves existing skills from learnings with cross-skill propagation, memory-vs-skill triage, and semver discipline. Defers to Anthropic's guidance (compound-engineering:create-agent-skill, compound-engineering:skill-creator, compound-engineering:heal-skill) for schema and best-practice depth. Triggers on "/skillify," "create a skill," "make this a skill," "skill from this chat," "extract a skill from what we've been doing," "adapt this skill," "port this skill," "fork this skill," "borrow this skill," "update X skill," "apply this to the relevant skills," "propagate this learning," "improve [skill]," "fix [skill]," "iterate on [skill]." Part of the -ify trifecta (skillify / toolify / loopify) for extending Claude Code. metadata: version: 0.2.0
/skillify — Create, adapt, or update a skill
One skill, three modes. Routes automatically to the right one based on input signal.
Consolidates and replaces the prior create-skill, adapt-skill, and update-skill (all merged as of v0.2.0 for vocabulary-moat consistency with the -ify trifecta).
Step 0 — Detect mode
Route by signal:
| Signal | Mode |
|---|---|
| Invoked mid-conversation with substantive recent workflow discussion | CREATE / from-chat (default) |
/skillify from-video <url> OR /skillify + a video URL | CREATE / from-video |
/skillify from-dump + pasted brief/transcript/notes | CREATE / from-dump |
/skillify from-scratch <name> OR "make a new skill called X" with no context | CREATE / from-scratch |
/skillify <github-url> OR "adapt this skill" / "port this skill" / "fork this skill" + external source | ADAPT |
/skillify <existing-skill> <change> OR "update X skill" / "propagate this learning" | UPDATE / targeted |
/skillify update (mid-conversation) | UPDATE / from-chat — scan recent chat for learnings |
/skillify usage <skill> | UPDATE / usage — review recent runs, suggest improvements |
If ambiguous, ask before proceeding. Never guess between CREATE and ADAPT if there's an external URL involved.
Mode: CREATE
Build a new skill from chat / video / dump / scratch.
Step 1 — Confirm the input source
| Sub-mode | What |
|---|---|
| from-chat (default) | Extract the skill from the workflow discussed in this conversation. Most common case. |
| from-video | User recorded a Loom / Zoom / screen-share. Calls watch-video in visual mode → transcript + key visual moments → SKILL.md. Best for visual/UI-heavy workflows. |
| from-dump | User pastes a brief, prior conversation transcript, exported chat, or notes. |
| from-scratch | Fresh idea with no source material — interactive Q&A. |
Step 2 — Defer to Anthropic guidance for the schema
Don't reinvent SKILL.md format rules. For frontmatter, description-writing, references/ structure, and skill best practices:
compound-engineering:create-agent-skill(agent) — expert guidance for creating + editing Claude Code skillscompound-engineering:skill-creator(skill) — deeper guide for effective skillscompound-engineering:heal-skill(skill) — for fixing existing skills- anthropics/skills — official Anthropic examples
- agentskills.io — open Agent Skills spec
Call those directly when in doubt about format. skillify orchestrates your workflow — which repo, which conventions, which cross-references. Format expertise lives upstream.
Step 3 — Pick target repo
Load the user's sibling repo list from ${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/skillify/repos.yaml if present. Otherwise default to makerskills (this repo). Example format:
# ~/.config/makerskills/skillify/repos.yaml
repos:
- name: makerskills
domain: Personal cross-cutting operator work
path: ~/code/makerskills
- name: marketingskills
domain: Generic marketing tactics
path: ~/code/marketingskills
Infer target if obvious from the skill's domain; ask if ambiguous.
Step 4 — Synthesize per sub-mode
from-chat:
- Read backward through this conversation. Look for a workflow repeated multiple times, a process re-explained, opinions restated, tooling/voice/output decisions.
- Identify the load-bearing pieces: trigger, steps, references, success shape, voice.
- Surface gaps that need clarification before scaffolding — ask 2–4 tight questions.
- Draft SKILL.md, citing chat moments inline ("Per your message about X…") so the user can verify.
from-dump:
- Parse the dump (Notion page, Slack thread, Loom transcript, teammate brief, exported ChatGPT conversation).
- Same synthesis logic as from-chat.
- Cite where in the dump each rule came from.
from-video:
- Take the URL or local path.
- Call
watch-video <url> visual— get transcript + key visual moments + summary. - Read outputs:
<workdir>/transcript.txt,<workdir>/moments.md,<workdir>/summary.md. - Synthesize: trigger (first 30s), steps (visual moments + matching transcript), tools used, decision points ("if X do Y" moments), success shape (last few seconds), voice cadence.
- Surface gaps — ambiguous moments needing clarification.
- Draft SKILL.md citing video moments by timestamp.
- Optionally save the source to
second-brainascall-<slug>.mdornote-<slug>.md.
Heuristic: recording >10 minutes = process probably too big for one skill.
阅读完整来源 ↗