- name
SKILL.md
Tệp skill vẫn nằm trong kho mã của nhà phát hành.
Dán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add coreyhaines31/makerskills --skill skillify -a cursor -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add coreyhaines31/makerskills --skill skillify -a claude-code -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add coreyhaines31/makerskills --skill skillify -a codex -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add coreyhaines31/makerskills --skill skillify -a grok -yGửi tin nhắn đã sao chép trong cuộc trò chuyện Grok Bot. Bot sẽ lấy tệp SKILL.md này từ GitHub và thêm vào bộ skill mà mọi Bot của bạn dùng chung.
Install this skill: https://github.com/coreyhaines31/makerskills/tree/HEAD/skills/skillifyTừ nhà phát hành
One skill, four 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).
Route by signal:
If ambiguous, ask before proceeding. Never guess between CREATE and ADAPT if there's an external URL involved.
Build a new skill from chat / video / dump / scratch.
Don't reinvent SKILL.md format rules. For frontmatter, description-writing, references/ structure, and skill best practices:
skill-creator (skill, from anthropics/skills): Anthropic's official guide for creating new skills, improving existing ones, and measuring how they perform. Use it if installed; skillify still works without it.Call those directly when in doubt about format. skillify orchestrates your workflow — which repo, which conventions, which cross-references. Format expertise lives upstream.
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.
from-chat:
from-dump:
from-video:
watch-video <url> visual — get transcript + key visual moments + summary.<workdir>/transcript.txt, <workdir>/moments.md, <workdir>/summary.md.second-brain as call-<slug>.md or note-<slug>.md.Heuristic: recording >10 minutes = process probably too big for one skill. Suggest splitting before drafting.
from-scratch: Interactive Q&A:
watch-video, read-book, paste)---
name: <kebab-case>
description: <rich, trigger-rich, ~2–4 sentences. Lead with "When you want to..." Include 4–8 trigger phrases in quotes. Differentiate from adjacent skills.>
metadata:
version: 0.1.0
---
Description rules (load-bearing — agents route by description match):
For deeper description-writing guidance, consult skill-creator (from anthropics/skills) if installed.
<target-repo>/skills/<name>/
├── SKILL.md
└── references/
└── ...
Body follows existing skills' pattern (project-manager, decide, second-brain):
# /<name> — <one-line purpose>## Step N — <phase> sectionsAppend to target repo's README skill table:
| [`<name>`](./skills/<name>/SKILL.md) | <one-line purpose> |
Commit + push. Report new skill path, commit hash, and reminder that /plugin install or symlink may need a refresh.
skill-creator for a quality pass?" (if installed)Port an external skill (GitHub URL, agentskills.io, local disk, or pasted SKILL.md) into your namespace.
Accept:
https://github.com/<owner>/<repo> or full path to SKILL.md)~/.claude/plugins/ in Claude Code, ~/.agents/skills/ or ~/.codex/skills/ elsewhere)# GitHub repo: clone shallow
git clone --depth 1 <url> /tmp/skillify-adapt-<short-id>/
# OR fetch a single file
gh api -H "Accept: application/vnd.github.raw" repos/<owner>/<repo>/contents/SKILL.md > /tmp/adapt-source.md
Capture the commit SHA so attribution can point at a stable revision.
Read source SKILL.md + any references/ it ships. Classify into three buckets per references/adapt-buckets.md:
Output classification as a table for approval before writing anything. Don't silently rewrite — surface the changes.
Read the source's LICENSE. Per references/adapt-license-check.md:
For permissive licenses, attribution is the only requirement — handled in Step 6.
Same table as CREATE Step 3.
Keep verbatim: copy as-is; add `` marker if helpful.
Adapt:
watch-video, read-book, paste)project-manager, their video tool → watch-video, their note system → second-brain, their decision framework → decide~/outputs/ → your ~/Documents/<skill>-<...>/ convention; their config → your references/ patternAdd:
Write references/attribution.md:
# Attribution
- **Source**: <original SKILL.md URL>
- **Repository**: <repo URL>
- **Author**: <name + handle>
- **Commit SHA**: <SHA at time of adapt>
- **License**: <license name + URL>
- **Adapted**: <YYYY-MM-DD>
## What was kept verbatim
- ...
## What was adapted
- <old> → <new>
## What was added
- ...
## License compliance
<upstream LICENSE text if MIT/BSD/Apache requires it, OR reference where in this repo it lives>
## Upgrade path
Run `git ls-remote <repo-url> HEAD`. If SHA differs from above, re-run `/skillify <same-url>` for a 3-way merge.
For MIT / Apache / BSD, LICENSE text either gets copied into this file or the source LICENSE file gets copied to the skill dir.
Same as CREATE Steps 6–7. Commit message: "Adapt <name> skill from <source-name>".
skill-creator for a QA pass?" (if installed)loopify?"Improve existing skill(s) from learnings.
Default when invoked mid-conversation with substantive recent activity: from-chat.
For from-chat / from-dump / usage: look for change-worthy signals (full taxonomy in references/update-change-types.md):
Output: a clear list of N learnings, each phrased as a single change.
For targeted: skip extraction — user already named the change.
For each learning, search across all SKILL.md + references/ in the current repo (and optionally all sibling repos from your repos.yaml with --cross-repo):
grep -rln "<key terms>" ~/code/makerskills/skills/ --include="*.md"
# Across all sibling repos (list yours in $MAKERSKILLS_CONFIG/skillify/repos.yaml):
config="${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/skillify/repos.yaml"
for raw in $(yq -r '.repos[].path' "$config"); do
repo="${raw/#\~/$HOME}" # expand leading ~ to $HOME so grep resolves the real path
grep -rln "<terms>" "$repo/skills/" --include="*.md" 2>/dev/null
done
Classify by confidence:
See references/update-propagation.md for the cross-skill propagation playbook.
For each learning: is this skill-specific or a broader principle?
Example: "links go in first comments, not body" → applies to jab-hook AND is a broader social principle → both update jab-hook AND save feedback_social_link_placement.md.
Offer the memory write explicitly: "This looks like a principle, not just a skill rule. Save to memory as feedback_<slug>.md?"
For each affected file, show change as before/after or unified diff:
### `skills/<skill>/SKILL.md` — proposed change
**Before** (lines NN–NN):
> <existing text>
**After**:
> <new text>
**Why**: <one-line rationale>
**Version bump**: 0.2.0 → 0.2.1 (PATCH — clarification)
**Approve / edit / skip?**
Per-file approval. Don't batch — small changes are easy to OK; bundling forces all-or-nothing.
See references/update-versioning.md for semver rules.
Edit to apply the exact changemetadata.version per the suggested levelBatch multiple file changes within one skill into a single commit.
Group by skill. Examples:
"slide-deck: emphasize spoken-aloud voice (write for the ear, not the page)""jab-hook, marketingskills:social: link placement (no inline URLs)"Show:
skill-creator QA pass would be useful (if installed)Don't add ceremony to surgical edits. If the user says "add this one bullet to X.md," just Edit. UPDATE mode earns its keep when:
For one-line updates with no cross-skill implications: just Edit.
Watch a skill run before real users do. Role-play realistic users through the SKILL.md, judge each transcript against a fixed rubric, and turn every failure into a patch. Works on published skills (regression check before/after an UPDATE) and on fresh CREATE/ADAPT drafts.
Full scenario set, rubric, and judging rules: references/test-rubric.md. Read it before Step 2.
<repo>/skills/<name>/SKILL.md (repo per CREATE Step 3)Pin the version under test. Subagents read from disk while they run. If the working tree can change underneath them (you switch branches, merge, edit), point them at a frozen copy: git worktree add <scratch>/wt-<skill> <commit> (remove it afterward), or a snapshot copy of the skill folder. Otherwise they test whatever's checked out when they get to it and report gaps that aren't real.
Read the SKILL.md and every references/ file it tells the agent to load — once. From here on the simulated wielder knows only those files. Anything it needs that isn't there is a finding, not something to fill in. If your host can spawn subagents, run each scenario in its own subagent whose prompt gives only the skill path, the scenario, and the dry-run rules, and tells it to read nothing else. Otherwise, play both sides yourself and state the quarantine in one line first.
Dry run, always. Nothing a simulated wielder does leaves the transcript. That means no file writes, drafts, issues, commits, pushes, or paid API calls; show them instead. The full rules are in references/test-rubric.md.
3–6 from the table in references/test-rubric.md: canonical, terse, and boundary always; refusal, lazy-answerer, die-and-resume, and missing-config when the skill's design calls for them. One-line persona each. Show the list; go unless the user swaps one.
6–12 turns each, USER: / WIELDER:. Realistic user (weak answers, pushback, shortcut attempts). Literal wielder (follows the files, flags ambiguity, never idealized). Stop once the scenario's question is answered.
Every applicable rubric criterion gets PASS / WEAK / FAIL with a quoted line as evidence. No quote, no finding.
A clean pass is a real result. Say so and stop.
watch-video — load-bearing for CREATE / from-video. Visual-mode output (transcript + key visual moments + summary) is the input for skill synthesis. Always call in visual mode for process recordings — UI state matters as much as words.second-brain — optionally capture source video/dump as raw/call-<slug>.md or raw/note-<slug>.md so the source artifact lives alongside the skill it produced.toolify — sibling in the -ify trifecta. Use toolify when the goal is adding an integration/MCP/API, not authoring a skill.loopify — sibling in the -ify trifecta. Use loopify for agent-loop setup rather than a skill.skill-creator (from anthropics/skills): format and best-practices expertise, plus a QA pass after any mode. Optional; skillify still works without it.watch-video, read-book, paste). Single-word noun names are fine for distinctive concepts (decide, paste, skillify).${MAKERSKILLS_MEMORY:-${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/memory}/, never a hardcoded Claude Code memory path.CLAUDE.md or AGENTS.md for user-owned schema/config docs.open, MLX) — e.g. wl-copy/xclip, xdg-open, faster-whisper.references/attribution.md.references/test-rubric.md.When you want to create, adapt, or update an Agent Skill (Claude Code, Codex, Cursor, and other hosts) in one of your repos (listed in ~/.config/makerskills/skillify/repos.yaml; defaults to makerskill
---name: skillifydescription: When you want to create, adapt, or update an Agent Skill (Claude Code, Codex, Cursor, and other hosts) in one…---# skills/skillify/SKILL.mdTổng quan
When you want to create, adapt, or update an Agent Skill (Claude Code, Codex, Cursor, and other hosts) in one of your repos (listed in ~/.config/makerskills/skillify/repos.yaml; defaults to makerskills). Modes — CREATE (from chat, video, dump, or scratch) turns a workflow into a new skill. ADAPT ports an external skill with keep/adapt/add classification, license check, and attribution. UPDATE improves existing skills from learnings with cross-skill propagation, memory-vs-skill triage, and semver. TEST role-plays users through a skill and judges transcripts against a rubric. Checks new skills for host portability. Triggers on "/skillify," "create a skill," "make this a skill," "adapt this skill," "port this skill," "update X skill," "propagate this learning," "improve [skill]," "fix [skill]," "test this skill," "exercise [skill]." Part of the -ify trifecta — integrations and MCP servers go to toolify, schedules and loops to loopify.
Câu hỏi thường gặp
Tải skills/skillify/SKILL.md từ nhà phát hành, hoặc sao chép đường dẫn và mở kho mã. PlugMCP chỉ liệt kê skill và không lưu trữ tệp này.
Nhà phát hành duy trì nó tại https://github.com/coreyhaines31/makerskills.
Claude, Cursor, Codex và Grok Build có thể đọc tệp SKILL.md mà bạn thêm từ kho mã của nhà phát hành. Grok Bot cài đặt skill khi bạn gửi liên kết thư mục GitHub của skill trong cuộc trò chuyện.