marketplace-dev
- Repo stars 1,187
- Forks 185
- Author updated Jun 14, 2026, 10:01 AM
- Author repo claude-code-skills
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @daymade · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: marketplace-dev
description: >- Use when the skill should install, update, and roll back. Convert a Claude Code skills reposi…
category: other
runtime: no special runtime
---
# marketplace-dev output preview
## PART A: Task fit
- Use case: >- Use when the skill should install, update, and roll back. Convert a Claude Code skills repository into an official plugin marketplace so users can install skills via claude plugin marketplace add and get auto-updates. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Phase 0: Evidence Intake / Phase 1: Analyze the Target Repo / Step 1: Discover all skills” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “>- Use when the skill should install, update, and roll back. Convert a Claude Code skills repository into an official plugin marketplace so users can install skills via claude plugin marketplace add and get auto-updates. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Phase 0: Evidence Intake / Phase 1: Analyze the Target Repo / Step 1: Discover all skills” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/plugin-name`, `/daymade-docs`, `/path`, `/plugin`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Phase 0: Evidence Intake / Phase 1: Analyze the Target Repo / Step 1: Discover all skills”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: marketplace-dev
description: >- Use when the skill should install, update, and roll back. Convert a Claude Code skills reposi…
category: other
source: daymade/claude-code-skills
---
# marketplace-dev
## When to use
- >- Use when the skill should install, update, and roll back. Convert a Claude Code skills repository into an official…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Phase 0: Evidence Intake / Phase 1: Analyze the Target Repo / Step 1: Discover all skills” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "marketplace-dev" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Phase 0: Evidence Intake / Phase 1: Analyze the Target Repo / Step 1: Discover all skills
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} marketplace-dev
Convert a Claude Code skills repository into an official plugin marketplace so users
can install skills via claude plugin marketplace add and get auto-updates.
Input: a repo with skills/ directories containing SKILL.md files.
Output: .claude-plugin/marketplace.json + validated + installation-tested + PR-ready.
Phase 0: Evidence Intake
Before editing an existing marketplace, collect evidence instead of relying on the default template:
- Read the current
.claude-plugin/marketplace.json. - Read this repo's marketplace rules (
CLAUDE.md, README install section, changelog). - Read official docs for marketplace/plugin path semantics.
- If refining from prior failures, mine local Claude Code session history.
Each project's sessions live under ~/.claude/projects/<escaped-cwd>/:
- Top-level files:
<session-id>.jsonl - Subagent transcripts:
<session-id>/subagents/agent-*.jsonl
Useful search patterns (adjust keywords to the failure you are debugging):
grep -lc "marketplace.json\|claude plugin validate\|claude plugin install" \
~/.claude/projects/<escaped-cwd>/*.jsonl
grep -lc "Unrecognized key\|Plugin not found\|No manifest found\|Duplicate plugin" \
~/.claude/projects/<escaped-cwd>/*.jsonl \
~/.claude/projects/<escaped-cwd>/*/subagents/*.jsonl
Extract lessons as evidence-backed rules: command attempted, observed output, root cause, final working command/config. Do not encode guesses from memory.
Phase 1: Analyze the Target Repo
Step 1: Discover all skills
# Find every SKILL.md
find <repo-path>/skills -name "SKILL.md" -type f 2>/dev/null
For each skill, extract from SKILL.md frontmatter:
name— the skill identifierdescription— the ORIGINAL text, do NOT rewrite or translate
Step 2: Read the repo metadata
VERSIONfile (if exists) — this becomesmetadata.versionREADME.md— understand the project, author info, categoriesLICENSE— note the license type- Git remotes — identify upstream vs fork (
git remote -v)
Step 3: Determine categories
Group skills by function. Categories are freeform strings. Good patterns:
business-diagnostics,content-creation,thinking-tools,utilitiesdeveloper-tools,productivity,documentation,security
Ask the user to confirm categories if grouping is ambiguous.
Step 4: Choose plugin boundaries
Claude Code has three separate levels:
marketplace -> plugin -> skill
- Marketplace name is used for install identity:
plugin@marketplace. - Plugin name is the slash namespace:
/plugin-name:skill-name. - Skill name comes from
SKILL.mdfrontmatter when the skill path points to a directory containingSKILL.mddirectly.
Choose each plugin boundary by installation/update/cache intent:
- Single-skill plugin: use when the skill should install, update, and roll back independently with a narrow cache.
- Suite plugin: use when related skills should share one namespace and one
install command, for example
/daymade-docs:mermaid-tools.
For detailed source/cache patterns and pitfalls, read
references/cache_and_source_patterns.md before changing source or skills.
Phase 2: Create marketplace.json
The official schema (memorize this)
Read references/marketplace_schema.md for the complete field reference.
Key rules that are NOT obvious from the docs:
$schemafield is REJECTED byclaude plugin validate. Do not include it.metadataonly has 3 valid fields:description,version,pluginRoot. Nothing else.metadata.homepagedoes NOT exist — the validator accepts it silently but it's not in the spec.metadata.versionis the marketplace catalog version, NOT individual plugin versions. It should match the repo's VERSION file (e.g.,"2.3.0").- Plugin entry
versionis independent. For first-time marketplace registration, use"1.0.0". strict: falseis required when there's noplugin.jsonin the repo. Withstrict: false, the marketplace entry IS the entire plugin definition. Having BOTHstrict: falseAND aplugin.jsonwith components causes a load failure.sourcedefines the installed plugin root. For single-skill plugins, pointsourcedirectly at the skill directory (e.g.,"./tunnel-doctor") and omitskillsentirely — this is the official pattern used by 167/168 plugins inanthropics/claude-plugins-official. For suite plugins, usesource: "./<suite>"with explicitskillsarray listing subdirectories. Avoidsource: "./"(installs full repo as cache) andskills: ["./"](rejected by Claude Code 2.1.x path-escape validator).- Reserved marketplace names that CANNOT be used:
claude-code-marketplace,claude-code-plugins,claude-plugins-official,anthropic-marketplace,anthropic-plugins,agent-skills,knowledge-work-plugins,life-sciences. tagsvskeywords: Both are optional. In the current Claude Code source,keywordsis defined but never consumed in search.tagsonly has a UI effect for the value"community-managed"(shows a label). Neither affects discovery. The Discover tab searches onlyname+description+marketplaceName. Includekeywordsfor future-proofing but don't over-invest.
Generate the marketplace.json
Use this template, filling in from the analysis:
{
"name": "<marketplace-name>",
"owner": {
"name": "<github-org-or-username>"
},
"metadata": {
"description": "<one-line description of the marketplace>",
"version": "<from-VERSION-file-or-1.0.0>"
},
"plugins": [
{
"name": "<skill-name>",
"description": "<EXACT text from SKILL.md frontmatter, do NOT rewrite>",
"source": "./<skill-name>",
"strict": false,
"version": "1.0.0",
"category": "<category>",
"keywords": ["<relevant>", "<keywords>"]
}
]
}
Naming the marketplace
The name field is what users type after @ in install commands:
claude plugin install dbs@<marketplace-name>
Choose a name that is:
- Short and memorable
- kebab-case (lowercase, hyphens only)
- Related to the project identity, not generic
Description rules
- Use the ORIGINAL description from each SKILL.md frontmatter
- Do NOT translate, embellish, or "improve" descriptions
- If the repo's audience is Chinese, keep descriptions in Chinese
- If bilingual, use the first language in the SKILL.md description field
- The
metadata.descriptionat marketplace level can be a new summary
Maintaining an existing marketplace
When adding a new plugin to an existing marketplace.json:
- Bump
metadata.version— this is the marketplace catalog version. Follow semver: new plugin = minor bump, breaking change = major bump. - Update
metadata.description— append the new skill's summary. - Set new plugin
versionto"1.0.0"— it's new to the marketplace. - Bump existing plugin
versionwhen its SKILL.md content changes. Claude Code uses version to detect updates — same version = skip update. - Bump existing plugin
versionwhen itssourceorskillschanges. The installed cache path and component resolution changed even if SKILL.md did not. - Audit
metadatafor invalid fields —metadata.homepageis a common mistake (not in spec, silently ignored). Remove if found.
Phase 3: Validate
Step 1: One-shot pre-flight check
Run the bundled validator. It runs four checks in sequence and exits non-zero on any required failure:
bash scripts/check_marketplace.sh # validates current repo
bash scripts/check_marketplace.sh /path # validates a target repo
What it checks:
| # | Check | Failure means |
|---|---|---|
| 1 | JSON syntax of .claude-plugin/marketplace.json |
file is not parseable JSON |
| 2 | claude plugin validate . (skipped if claude CLI missing) |
schema-level rejection (e.g. Unrecognized key: "$schema", duplicate names) |
| 3 | source + skills resolution for every plugin entry |
a plugin entry points to a SKILL.md that does not exist on disk |
| 4 | Reverse sync (disk → manifest) | WARN-only: a SKILL.md on disk is not registered in any plugin entry |
Common schema failures and fixes:
Unrecognized key: "$schema"→ remove the$schemafieldDuplicate plugin name→ ensure all names are uniquePath contains ".."→ use./relative paths onlyNo manifest found in directorywhen validating an installed cache path → validate the marketplace manifest or plugin source, not astrict: falsecache directory.
Step 2: Installation test
# Add as local marketplace
claude plugin marketplace add .
# Install a plugin
claude plugin install <plugin-name>@<marketplace-name>
# Verify it appears
claude plugin list | grep <plugin-name>
# Check for updates (should say "already at latest")
claude plugin update <plugin-name>@<marketplace-name>
# Clean up
claude plugin uninstall <plugin-name>@<marketplace-name>
claude plugin marketplace remove <marketplace-name>
Step 3: Cache footprint test
After installation or update, inspect the actual cache. This is the only way to
confirm source produced the intended snapshot:
PLUGIN=<plugin-name>
MARKET=<marketplace-name>
CACHE=$(jq -r --arg id "$PLUGIN@$MARKET" '.plugins[$id][0].installPath' ~/.claude/plugins/installed_plugins.json)
find "$CACHE" -maxdepth 1 -mindepth 1 -exec basename {} \; | sort
Expected results:
- Single-skill plugin cache:
SKILL.mdplus its ownscripts/,references/,assets/as applicable. - Suite plugin cache: only the suite member skill directories and suite-scoped resources.
- If unrelated skill directories appear,
sourceis too broad. - If cache entries are symlinks, the plugin is not self-contained; use canonical source directories instead of symlink farms.
Step 4: GitHub installation test (if pushed)
# Test from GitHub (requires the branch to be pushed)
claude plugin marketplace add <github-user>/<repo>
claude plugin install <plugin-name>@<marketplace-name>
# Verify
claude plugin list | grep <plugin-name>
# Clean up
claude plugin uninstall <plugin-name>@<marketplace-name>
claude plugin marketplace remove <marketplace-name>
Pre-flight Checklist (MUST pass before proceeding to PR)
Run this checklist after every marketplace.json change. Do not skip items.
Automated checks
bash scripts/check_marketplace.sh
All four checks must pass. Treat the reverse-sync WARN as a real signal: an
unregistered SKILL.md on disk is almost always either an accidentally-dropped
skill you forgot to register, or dead code that should be removed.
Metadata check
Verify these by reading marketplace.json:
-
metadata.versionbumped from previous version -
metadata.descriptionmentions all skill categories - No
metadata.homepage(not in spec, silently ignored) - No
$schemafield (rejected by validator)
Per-plugin check
For each plugin entry:
-
descriptionmatches SKILL.md frontmatter EXACTLY (not rewritten) -
versionis"1.0.0"for new plugins, bumped for changed plugins -
sourcepoints directly at the skill directory (e.g.,"./skill-name") - Single-skill plugins omit the
skillsfield (auto-discovery fromsource) - Suite plugins list
skillspaths relative tosource -
strictisfalse(no plugin.json in repo) -
nameis kebab-case, unique across all entries
Final validation
bash scripts/check_marketplace.sh
Must print RESULT: PASSED before creating a PR. A WARN [4/4] is acceptable
only when you have consciously decided to leave a SKILL.md unregistered.
Phase 4: Create PR
Principles
- Pure incremental: do NOT modify any existing files (skills, README, etc.)
- Squash commits: avoid binary bloat in git history from iterative changes
- Only add:
.claude-plugin/marketplace.json, optionallyscripts/, optionally update README
README update (if appropriate)
Add the marketplace install method above existing install instructions:
## Install
 <!-- only if demo exists -->
**Claude Code plugin marketplace (one-click install, auto-update):**
\`\`\`bash
claude plugin marketplace add <owner>/<repo>
claude plugin install <skill>@<marketplace-name>
\`\`\`
PR description template
Include:
- What was added (marketplace.json with N skills, M categories)
- Install commands users will use after merge
- Design decisions (pure incremental, original descriptions, etc.)
- Validation evidence (
claude plugin validate .passed) - Test plan (install commands to verify)
Bundled hooks (optional, auto-activated)
This skill ships two PostToolUse hooks under hooks/:
hooks/post_edit_validate.sh— runsclaude plugin validatewhenever amarketplace.jsonfile is written or edited.hooks/post_edit_sync_check.sh— warns when aSKILL.mdis edited but the matching plugin entry inmarketplace.jsondoes not bump itsversion.
Both hooks are declared in this plugin's own manifest entry (plugins[].hooks),
so they activate automatically when the plugin is enabled in a Claude Code
session. No manual settings.json edit is required. To disable them, remove
the hooks block from this plugin entry in the user's installed copy or use
/plugin disable marketplace-dev (they take effect only when the plugin is
enabled).
These hooks are editor-time guardrails. They do NOT replace
scripts/check_marketplace.sh — always run the pre-flight check before a PR.
Anti-Patterns (things that went wrong and how to fix them)
Read references/anti_patterns.md for the full list of pitfalls discovered during
real marketplace development. These are NOT theoretical — every one was encountered
and debugged in production.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review