Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Skill Resolver

ASecurity

Resolve Claude/Codex skill files by name when neither the user nor the current session catalog identifies the artifact. Use for unresolved name-only lookup or resolver ambiguity; not when an exact path or a catalog root-alias mapping already identifies the requested skill.

12 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsbashdebugginggitdocumentation

Works with

claude code

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add benthamite/dotfiles --skill skill-resolver --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Resolver?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Resolver
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/benthamite-skill-resolver-dotfiles/badge)](https://www.skillsdirectory.com/skills/benthamite-skill-resolver-dotfiles)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: skill-resolver
description: Resolve Claude/Codex skill files by name when neither the user nor the current session catalog identifies the artifact. Use for unresolved name-only lookup or resolver ambiguity; not when an exact path or a catalog root-alias mapping already identifies the requested skill.
---

# Skill Resolver

Use the resolver for name-only lookup when the requested file is not already
identified. Honor an exact path or the current session's supplied skill catalog,
including its root-alias mapping; do not replace that identity with a same-named
file found elsewhere. The resolver locates and prints skill files; it does not
install, edit, or synchronize skills.

## Workflow

1. Skip the resolver when an exact `SKILL.md` path is already supplied by the user or session catalog. Expand catalog aliases using that catalog's mapping.
2. Choose the lookup scope: use `--tool codex` in Codex, `--tool claude` in Claude Code, and `--tool any` only when comparing paired copies or debugging tool-agnostic ambiguity.
3. Choose the lookup directory. Use the current working directory for the active project; pass `--cwd /path/to/project` when resolving a project-local skill for another workspace.
4. Run `path` to get the file path, `cat` to read the skill, `list` to inventory discovered files, `duplicates` to expose same-name copies, or `roots` to inspect the helper's search order. Check exit status before using stdout as a path or instruction body. Read the complete body before applying it.
5. If the resolver reports ambiguity or no match, inspect `list` and `roots` before continuing; do not substitute a likely-looking path.
6. For edits, resolve symlinks and use the canonical tracked source in the requested scope. Global dotfiles skills live under `claude/skills/<name>/` or `codex/skills/<name>/`; a project-local skill stays in that project's skill tree. Do not migrate a local skill globally or edit a managed plugin cache merely because a matching file was found. Keep intended Claude/Codex pairs synchronized except for intentional tool metadata or manifest-recorded divergences.

Command:

```bash
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill
```

Common operations:

```bash
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill path diagnose --tool codex
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill cat diagnose --tool codex
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill path diagnose --tool claude
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill list --tool codex
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill roots --tool codex
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill duplicates --tool codex
/Users/pablostafforini/My\ Drive/dotfiles/bin/agent-skill path skill-resolver --tool codex --cwd "/Users/pablostafforini/My Drive/dotfiles"
```

Rules:

- If neither the user nor session catalog identifies the file, resolve the name with `agent-skill` before guessing a path.
- Use `--tool claude` when operating in Claude Code and `--tool codex` when operating in Codex.
- The resolver's precedence is a lookup convenience, not a claim about either runtime's loading order or enabled skill catalog. It includes local compatibility/workspace sources; a discovered file may be disabled or unavailable in this session. Use the supplied session catalog or runtime inspection to establish availability.
- Honor `CODEX_HOME` and Claude's `CLAUDE_CONFIG_DIR` for the active account. Do not silently switch to another account to make a lookup succeed.
  `CLAUDE_HOME` is a legacy helper-only option, honored only when
  `CLAUDE_CONFIG_DIR` is unset.
- Codex lookup includes native `.agents/skills` project/user roots and
  `/etc/codex/skills`, alongside the local `.codex/skills` compatibility
  sources. Project-native roots stop at the nearest Git root.
- Claude plugin lookup uses enabled-plugin and installed-version records, not
  every directory left in a cache. A failed or malformed plugin inventory is
  incomplete discovery, not proof that no matching plugin is installed.
  Its enablement input is the account's `settings.json`; it does not reconstruct
  merged project/local/managed enablement policy. Project-scoped installation
  paths are filtered against `--cwd`.
- If the resolver reports ambiguity or no match, stop and investigate the skill inventory instead of substituting a likely-looking path.
- A successful lookup authorizes reading the requested artifact, not executing its workflow. Preserve explicit-only invocation policies while inspecting or auditing skills.

Native Codex locations were checked against the
[OpenAI skills documentation](https://learn.chatgpt.com/docs/build-skills)
on 2026-09-05. Local compatibility roots and lookup precedence remain specific
to this helper; check `roots` instead of assuming native runtime equivalence.

Attribution

benthamitebenthamite
View sourceMore from benthamite →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →