Skip to main content
Glama

Skillporter

Skillporter, is the package manager for AI agent skills. It is a zero runtime dependency CLI and MCP server that installs, pins, audits, synchronizes and rolls back SKILL.md packages across 19 AI coding and autonomous agent harnesses, including Claude Code, OpenAI Codex, Cursor, Windsurf, GitHub Copilot, Gemini CLI, Hermes Agent, OpenHands and Goose.

uvx skillporter@latest diagnose .                 # run latest CLI without installing (uv)
pipx install skillporter                          # install the CLI globally (PEP 668 safe)
npx @shanmukhdheekonda/skillporter@latest diagnose . # run latest CLI without installing (npm)

Why skills need a package manager

Every AI agent harness reads skills from a different directory (.claude/skills/, .agents/skills/, .github/skills/, .windsurf/skills/, $HERMES_HOME/skills/, ~/.openclaw/skills/), and each one resolves them differently.

  • A skill placed in .claude/skills/ is invisible to OpenAI Codex, Gemini CLI, Zed, and Windsurf.

  • Hand-rolled symlinks break inside Docker builds, CI checkouts, git worktree, and Windows checkouts.

  • Manual copies across directories silently drift out of sync across teammates, while naive removals from shared .agents/skills/ directories break other agents.

  • An upstream skill can change under you between two sync runs, and an agent loads whatever it finds into its system context.

Skillporter treats skills the way a package manager treats dependencies: one manifest, one lockfile, one resolution step, and one install path that every harness can read.

Related MCP server: mcp-audit

What Skillporter does

Capability

How it works

Universal source resolution

Fetches from GitHub shorthand (owner/repo), Git URLs, local paths, or archives without executing bundled scripts.

Shared-path deduplication

Writes .agents/skills/<skill> once across 8 primary harnesses and preserves it during single-harness remove.

Static supply-chain assessment

Inspects Python ASTs, JS/TS, Markdown instructions, and bounded Base64/Hex/PowerShell payloads before any file is written.

Deterministic lockfiles

Pins resolved_commit, tree_hash, per-file SHA-256 file_hashes, and pin_state in skillporter.lock.

Portable .skillpack environments

Packages managed skills, provenance, lockfiles, and profiles into a SHA-256 verified offline archive (export / import / diff).

Granular harness & profile control

Supports --exclude-harness, --isolated, --on-conflict, move, adopt, harness inspection, and named profile switching.

Crash-safe transactions

Stages multi-harness installs behind a write-ahead journal.json and snapshots replaced copies into .skillporter/backups/.

Agent instruction consolidation

Discovers CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules/*.mdc, .github/copilot-instructions.md, .windsurfrules, and CONVENTIONS.md, detecting overlap, contradictions, outdated refs, and bidirectional edits (consolidate).

Smart project recommendations & insights

Inspects local project manifests offline (suggest), estimates per-harness token overhead (insights, context), and tests skill triggers (new, lint, preview, test).

Capability & policy governance

Compares declared vs. inferred capabilities (capabilities:), previews human-readable update diffs (update --check), and enforces skillporter.policy.yaml (policy).

Agent skill & hardened MCP server

Ships an official skillporter skill (self-skill install) plus a workspace-bounded JSON-RPC 2.0 MCP server (--allow-writes opt-in).

Installation

# Option A: run immediately without a global install, via uvx or npx
# Pass @latest so uvx/npx never reuse an older cached tool environment
uvx skillporter@latest diagnose .
npx @shanmukhdheekonda/skillporter@latest diagnose .

# Option B: install from PyPI with uv or pipx (PEP 668 safe)
uv tool install skillporter
pipx install skillporter

# Option C: standalone verified release installer (Linux and macOS)
# Verifies SHA256SUMS.txt and the GitHub OIDC provenance attestation
# (`gh attestation verify`) or an out-of-band pinned digest
# (`SKILLPORTER_SHA256=<64-hex>`). Never falls back to mutable `main`.
curl -fsSL https://github.com/Shanmukh-l33t/skillporter/releases/download/v3.2.0/install.sh -o install.sh
SKILLPORTER_VERSION=v3.2.0 sh install.sh

Python 3.9 or newer is required, and the standalone installer checks for it before unpacking anything. The package ships with no runtime dependencies, so there is nothing else to audit or pin.

Quick start (60 seconds)

# 1. Run the zero residue interactive demo (heals broken symlinks and SHA-256 drift in a temp dir)
skillporter demo

# 2. Consolidate scattered CLAUDE.md, AGENTS.md, and Cursor rules, or get local skill recommendations
skillporter consolidate
skillporter suggest

# 3. Install a skill conservatively into detected/configured harnesses (pass --harness all for all 19)
skillporter add anthropics/skills --skill pdf --harness detected

# 3. Inspect and security scan skills (text, JSON, or SARIF 2.1.0 for GitHub Code Scanning)
skillporter scan .
skillporter scan . --format sarif > skillporter.sarif

# 4. Initialize manifest, synchronize transitive dependencies, and verify the reproducible lockfile in CI
skillporter init
skillporter sync
skillporter lock --check

# 5. Diagnose reachability, audit provenance and override logs, or roll back to a verified snapshot
skillporter status
skillporter audit .
skillporter rollback pdf

# 6. Export, compare, and restore your entire skill environment across machines (works offline)
skillporter export my-environment.skillpack
skillporter diff my-environment.skillpack
skillporter import my-environment.skillpack --dry-run

# 7. Give your AI coding agents native control over Skillporter
skillporter self-skill install --harness detected

Supply chain security

Agent skills are untrusted supply chain packages: an agent loads SKILL.md directly into its system context and executes bundled scripts. Skillporter is built around that assumption rather than around convenience.

  • Silent skill drift and unpinned upstream changes: skillporter.lock pins resolved Git commits, SHA-256 tree digests, and per-file hashes, blocking unexpected upstream mutations during sync.

  • Known static supply chain hazards: inspects Python ASTs, JavaScript and TypeScript scripts, Markdown instructions, and bounded Base64, Hex and PowerShell payloads for embedded credentials, prompt injection override patterns, hidden Unicode and comments, shell pipe RCE, unsafe deserialization, symlink escapes, and multi-file staged execution before installation.

  • Unsafe archive and filesystem operations: blocks Zip-Slip and Tar-Slip inputs (../, ..\, drive paths, Windows reserved device names, Unicode NFC/NFD collisions, symlinks, special files, decompression bombs) and stages installs transactionally with crash recovery journals.

  • Unscoped agent filesystem writes: constrains skillporter mcp to the workspace root with default-deny write permissions (SKILLPORTER_MCP_ALLOW_WRITES=1 opt-in) and separates conflict overrides (--force) from security risk overrides (--allow-risky).

Important security note: static scanning (STATIC_SECURITY_ASSESSMENT) inspects files for known dangerous patterns and structural anomalies. A clean static scan is not proof that a skill is safe at runtime. Novel natural-language prompt injections or dynamically fetched payloads can still steer an agent at runtime.

How the scan is graded and where its limits are is documented in SECURITY.md.

Lockfile, sync and rollback

skillporter.lock is the reproducible record of what is installed:

  • Pins resolved_commit, tree_hash, per-file SHA-256 file_hashes, pin_state (PINNED_COMMIT, PINNED_CONTENT or UNPINNED_MUTABLE), dependencies, and adapter version.

  • skillporter sync honors locked Git commit SHAs even when upstream branches move, and rejects unexpected upstream content changes without --force.

  • skillporter lock --check verifies the lockfile in CI and fails on mismatch.

  • skillporter audit reports installed origins, lockfile drift, and .skillporter/audit.jsonl events, so any risk override is visible after the fact.

Rollback is transactional rather than a re-download. Replacements are staged in .skillporter/tmp/txn-* behind a write-ahead journal.json, prior versions are snapshotted into .skillporter/backups/, and skillporter rollback restores a skill together with its dependency graph from SHA-256 verified backups.

Harness support matrix (19 harnesses)

Skillporter distinguishes support status (NATIVE, COMPATIBLE, ADAPTED) from verification evidence (RUNTIME_VERIFIED, INTEGRATION_TESTED, FIXTURE_TESTED, DOCUMENTATION_VERIFIED). An adapter is never marked RUNTIME_VERIFIED unless it has been tested against a live harness runtime.

Harness

Project Path

User / Global Path

Support

Verification Evidence

Hermes Agent

.hermes/skills/

$HERMES_HOME/skills/<cat>/<name>

NATIVE

RUNTIME_VERIFIED

Claude Code

.claude/skills/

~/.claude/skills/

NATIVE

RUNTIME_VERIFIED

OpenAI Codex

.agents/skills/

~/.agents/skills/

NATIVE

RUNTIME_VERIFIED

Cursor

.agents/skills/, .cursor/skills/ (+2 compat)

~/.agents/skills/, ~/.cursor/skills/

NATIVE

FIXTURE_TESTED

GitHub Copilot

.github/skills/ (+2 compat)

~/.copilot/skills/ (+1 compat)

NATIVE

RUNTIME_VERIFIED

Gemini CLI

.agents/skills/, .gemini/skills/

~/.agents/skills/, ~/.gemini/skills/

NATIVE

RUNTIME_VERIFIED

Google Antigravity

.agents/skills/ (+1 compat)

~/.gemini/config/skills/

NATIVE

FIXTURE_TESTED

Windsurf

.windsurf/skills/

~/.codeium/windsurf/skills/

NATIVE

FIXTURE_TESTED

Cline

.cline/skills/ (+3 compat)

~/.cline/skills/

NATIVE

RUNTIME_VERIFIED

Roo Code

.roo/skills/ (+1 compat)

~/.roo/skills/ (+1 compat)

NATIVE

FIXTURE_TESTED

OpenCode

.opencode/skills/ (+2 compat)

~/.config/opencode/skills/ (+2 compat)

NATIVE

RUNTIME_VERIFIED

Zed

.agents/skills/

~/.agents/skills/

NATIVE

FIXTURE_TESTED

Replit Agent

.agents/skills/ (+1 compat)

~/.config/agents/skills/

NATIVE

FIXTURE_TESTED

JetBrains Junie

.junie/skills/ (+1 compat)

~/.junie/skills/ (+1 compat)

NATIVE

FIXTURE_TESTED

OpenClaw

.openclaw/skills/ (+2 compat)

~/.openclaw/skills/ (+1 compat)

NATIVE

FIXTURE_TESTED

OpenHands

.agents/skills/ (+2 compat)

~/.agents/skills/ (+1 compat)

NATIVE

FIXTURE_TESTED

Goose

.agents/skills/ (+1 compat)

~/.agents/skills/ (+1 compat)

NATIVE

FIXTURE_TESTED

Continue

.continue/skills/ (.continue/rules/ adapted)

~/.continue/skills/

COMPATIBLE

RUNTIME_VERIFIED

Aider / AiderDesk

.aider-desk/skills/ (CONVENTIONS.md adapted)

~/.aider-desk/skills/

ADAPTED

FIXTURE_TESTED

Each harness record ships its detection rules, path precedence, and vendor documentation reference. skillporter matrix prints the same matrix from the installed CLI, and skillporter detect reports which harnesses exist on the current machine.

MCP server

skillporter mcp runs a hardened JSON-RPC 2.0 Model Context Protocol server so an agent can query a workspace instead of shelling out. It exposes 18 tools (diagnose, detect, scan, inspect, matrix, status, diff, consolidate_preview, suggest, insights, context, preview, add, install, sync, remove, export, import), is read-only by default, refuses paths outside the workspace root, and requires an explicit opt-in before any write tool becomes available:

skillporter mcp                                   # read-only
skillporter mcp --allow-writes                    # enable write tools
SKILLPORTER_MCP_ALLOW_WRITES=1 skillporter mcp    # same, via the environment

Client setup for Claude Code and other MCP clients is covered in the MCP guide.

CLI reference

Command

Description

skillporter consolidate [path]

Discover, deduplicate, conflict-check, reconcile, and synchronize multi-agent instruction files (--apply, --status, --reconcile, --rollback)

skillporter context [path]

Inspect exact active instruction files, ignored foreign files, reachable skills, and startup token stack (--harness)

skillporter suggest [path]

Recommend relevant, security-graded skills from local project manifests (package.json, pyproject.toml, Dockerfile, Prisma, CI)

skillporter insights [path]

Measure skill and instruction context token overhead, duplicate waste, and opt-in local activation events

skillporter new <name>

Scaffold a spec-compliant skill directory (--with-scripts, --with-references, --with-tests)

skillporter lint [path]

Validate metadata, local file links, script references, capability declarations, and token limits (--strict)

skillporter preview <target>

Preview exact native and adapted rule outputs plus capability-loss notes for any harness (--harness)

skillporter test [path]

Run skill.test.yaml activation trigger and structural test suites (--model, --yes-send)

skillporter policy [action]

Initialize (init), display (show), or enforce (check) skillporter.policy.yaml governance rules

skillporter status [path]

Unified environment control center: manifest, lockfile, profiles, managed vs. unmanaged skills, and drift

skillporter export [file.skillpack]

Package managed skills, provenance, lockfile, and profiles into a SHA-256 verified portable .skillpack archive

skillporter import <file.skillpack>

Validate integrity, run static security checks, preview conflicts (--dry-run), and restore an environment offline

skillporter diff <target>

Compare current workspace against a .skillpack archive, project directory, or profile:<name>

skillporter profile <action>

Create (save), inspect (list, show), switch (use --prune), or remove (delete) named skill profiles

skillporter harness <action>

List, inspect capabilities and shared peers, or check status across all 19 supported harnesses

skillporter add <source>

Resolve, validate, security scan, and install skills (--exclude-harness, --on-conflict, --isolated, --dry-run)

skillporter install <dir>

Security scan and install a local skill directory (--exclude-harness, --on-conflict, --isolated, --dry-run)

skillporter move <skill>

Relocate an installed skill across harnesses safely (--from, --to, --isolated, --dry-run)

skillporter adopt [skills]

Bring existing unmanaged on-disk skills under Skillporter tracking, backup, and export (--all)

skillporter remove <skill>

Safely remove a skill while preserving shared .agents/skills/ still owned by other harnesses (--dry-run, --json)

skillporter sync [path]

Resolve pinned and transitive dependencies, verify lockfile hashes, and synchronize harnesses (--dry-run, --json)

skillporter outdated [skill]

Check managed skills against upstream versions and SHA-256 tree hashes without modifying files

skillporter update [skill]

Preview human-readable diffs (--check) or fetch, security/policy gate, back up, and update tracked skills (--dry-run, --allow-risky, --json)

skillporter rollback <skill>

Atomically restore a skill and its dependency graph from SHA-256 verified .skillporter/backups/ (--dry-run, --json)

skillporter lock [path] [--check]

Write or CI verify (--check) the deterministic skillporter.lock

skillporter scan [path]

Run static security and supply chain assessment (--format text|json|sarif, --max-risk-score)

skillporter audit [path]

Inspect installed skill origins, security posture, lockfile drift, and .skillporter/audit.jsonl events

skillporter diagnose [path]

Check reachability, broken symlinks, SHA-256 content drift, duplicates, and spec compliance

skillporter doctor [path] [--fix]

Comprehensive workspace health check and tamper safe repair (--dry-run, --json)

skillporter validate [path]

Validate SKILL.md against the Agent Skills specification (--format text|json|sarif)

skillporter inspect <source>

Inspect local or remote package structure, security posture, and adapted rule previews

skillporter graph [path]

Render or export (--json) the topological skill dependency graph

skillporter self-skill [install]

Bootstrap the official skillporter AI agent skill into detected or selected harnesses

skillporter sandbox run <skill>

[Experimental] Opt in, non-mutating dry run behavioral trace

skillporter explain <finding>

Explain any diagnostic, lockfile, validation, capability, policy, or sec-* code (--list for all codes)

skillporter search / info / pack / publish

Search the catalog, inspect metadata, build a deterministic .tar.gz with provenance.json, or publish

skillporter detect / matrix / demo

Detect installed harnesses, print the 19 harness matrix, or run the zero residue demo

skillporter mcp

Run the hardened JSON-RPC 2.0 MCP server (read-only by default; --allow-writes opt in)

Exit codes

  • 0: clean, or the operation succeeded

  • 1: policy or diagnostic finding (drift, broken symlink, spec error, security block, lockfile mismatch, cycle or conflict)

  • 2: usage or runtime error (invalid argument, unknown harness, missing path)

Documentation

  • Website: overview, interactive terminal demo, and live 19-harness matrix.

  • Documentation home: the full guide set, from installation through lockfiles, scanning, and CI.

  • Install: installation channels and provenance verification options.

  • FAQ: frequently asked questions.

  • Blog: engineering articles and release write-ups.

The same guides are versioned in the repository under docs/ if you prefer to read them on GitHub.

Contributing

Issues and pull requests are welcome. The short version:

  • Open an issue before starting a large architectural change.

  • New harness adapters must link the vendor documentation that proves the skill discovery path, and must not claim a verification level that has not been tested.

  • The core library stays on the Python standard library, with zero runtime dependencies.

Full setup instructions, the required local quality gates, and the adapter checklist are in CONTRIBUTING.md. To report a vulnerability, follow SECURITY.md instead of opening a public issue.

License

MIT. See LICENSE.

Available Tools

18 tools
skillporter_addA

[WRITE] Install skills from a workspace directory, archive, or repository into target harnesses (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: source (required), harnesses (required), path, force, +2 more.

skillporter_consolidate_previewA
Read-only

[READ] Discover agent instruction files (CLAUDE.md, AGENTS.md, .cursor/rules, copilot-instructions, etc.) and report overlap percentage, contradictions, and outdated file references without modifying files.

Inputs: path.

skillporter_contextB
Read-only

[READ] Inspect exact active instruction files, ignored foreign files, reachable skills, and startup token budget for a specific harness.

Inputs: harness (required), path.

skillporter_detectC
Read-only

[READ] Detect which AI coding and autonomous agent harnesses are installed or active.

Inputs: path.

skillporter_diagnoseA
Read-only

[READ] Diagnose Agent Skill reachability, broken symlinks, SHA-256 content drift, and spec compliance across AI agent harnesses in the workspace.

Inputs: path, scope.

skillporter_diffB
Read-only

[READ] Compare the workspace environment against a workspace-relative .skillpack archive or directory.

Inputs: target (required), path.

skillporter_exportA

[WRITE] Package the workspace skill environment into a portable .skillpack archive inside the workspace (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: output (required), path, managed_only.

skillporter_importB
Destructive

[WRITE] Validate and restore a workspace-relative .skillpack archive into selected harnesses (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: pack (required), path, force, dry_run, +2 more.

skillporter_insightsB
Read-only

[READ] Measure estimated token overhead of skills and instruction files, detect duplicates, and report local opt-in usage insights.

Inputs: path.

skillporter_inspectB
Read-only

[READ] Inspect a workspace or remote skill package structure, metadata, and security posture.

Inputs: source (required).

skillporter_installB

[WRITE] Install a local workspace skill directory into target harnesses (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: skill (required), harnesses (required), path, force, +2 more.

skillporter_matrixA
Read-only

[READ] Return the compatibility matrix of all 19 supported AI agent harnesses.

Inputs: no named parameters.

skillporter_previewB
Read-only

[READ] Preview the exact native or adapted rule content a target harness receives for a workspace skill, including any translation limitations.

Inputs: target (required), harness (required), path.

skillporter_removeA
Destructive

[WRITE] Remove an installed skill from target harnesses in the workspace (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: skill (required), path, harnesses.

skillporter_scanA
Read-only

[READ] Run static security and supply-chain checks on a skill directory (secrets, prompt injection, AST/JS/encoded analysis, symlink escapes).

Inputs: path (required).

skillporter_statusB
Read-only

[READ] Return the unified workspace environment snapshot (managed, unmanaged, orphaned, drifted, and per-harness skill states).

Inputs: path, scope.

skillporter_suggestB
Read-only

[READ] Analyze local project manifests and configuration (100% local, zero uploads) and recommend relevant, security-graded skills.

Inputs: path.

skillporter_syncB

[WRITE] Synchronize workspace skills across target harnesses (requires SKILLPORTER_MCP_ALLOW_WRITES=1).

Inputs: path, force, strategy, harnesses, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 18 tools

    Disambiguation3/5

    Several clusters overlap: add vs install vs import all move skills into harnesses, and inspect vs scan vs diagnose vs status all report on environment/skill health with fuzzy boundaries. Descriptions add some nuance (repository/archive vs local directory vs .skillpack restore), but an agent could easily pick the wrong one. Preview/context/consolidate_preview form a second slightly muddled read cluster.

    Naming Consistency5/5

    Every tool follows the identical skillporter_<verb_or_noun> snake_case pattern with no camelCase or style drift. Names are short, predictable, and readable across the whole set.

    Tool Count3/5

    18 tools is on the heavy side for a skill-portability server and pushes into the borderline range. Given the redundant install/add/import and inspect/scan/diagnose groupings, a few tools likely don't fully earn their place.

    Completeness4/5

    The surface covers the full lifecycle: detect/matrix/inspect/scan (discovery), suggest/insights/context (analysis), add/install/sync/import (apply), export/diff (portability), remove (teardown). Minor gaps like a direct update/rename operation are largely absorbed by sync and import.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Audits MCP server configurations for security risks including capability inventory, SSRF, prompt injection, and drift detection. Works in read-only mode and can also be used as an MCP server to let AI agents audit their own attack surface.
      182 PyPI
      4
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server that provides audit and safety-check tools for enterprise SDLC code integrity, enabling AI agents to scan workspaces for lifecycle gaps, mock-theater tests, DRY violations, and language-specific issues in shell, JavaScript/HTML, and Python.
      4
      14 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Read-only MCP server for the markdown files coding agents load: CLAUDE.md, AGENTS.md, GEMINI.md, SKILL.md, rules, commands and memory. Lints frontmatter, broken imports, invisible characters and hidden comments, shows which files load per tool and folder, and estimates token budgets. Never writes, deletes or touches the network.
      7
      4
      MIT