Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Capability Upgrade

ASecurity

Compatibility route to $capability-builder for project-owned Agent Skill creation; deep research preserved as conditional reference.

3 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agents

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add Sheldon-92/TAD --skill capability-upgrade --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Capability Upgrade?

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

Security grade badge for Capability Upgrade
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sheldon-92-capability-upgrade/badge)](https://www.skillsdirectory.com/skills/sheldon-92-capability-upgrade)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: capability-upgrade
description: Compatibility route to $capability-builder for project-owned Agent Skill creation; deep research preserved as conditional reference.
---

# /capability-upgrade — Compatibility Route (Phase 1)

This Skill is a thin compatibility entry for the **old** Capability Pack flow. New capability work uses **`$capability-builder create`**. The deep research material from the previous version is preserved as a conditional reference and is not loaded by default.

## Routing

- **New capability work** (new domain, new pack-style request, YAML domain pack mention) → **use `$capability-builder create`** per `.claude/skills/capability-builder/SKILL.md` and its mandatory `references/create-protocol.md`. That path creates exactly one project-owned Agent Skill at `.agents/skills/<name>/`, validates, behavior-proves, and projects to `.claude/skills/<name>/`.
- **Existing project Skill change** (you already have `.agents/skills/<name>/` and want to evolve it) → **future `$capability-builder evolve`** (Phase 2, not in this release). Record `STOPPED_WITH_REASON: evolve is Phase 2` and stop. No writes.
- **Existing legacy Capability Pack edit** (`.tad/capability-packs/<name>/` maintenance, retiring, converting, or editing a pack in the old tree) → **STOP `LEGACY_PACK_OUT_OF_SCOPE`**. Phase 1 neither retires nor edits legacy packs. No writes. Ask the human to choose a separately scoped legacy-maintenance task or a new project-owned Skill. Do not silently reinterpret a pack upgrade as Skill creation.
- **General capability routing question** (which pack for a task? `pack-collisions.yaml` gap) → read pack registry / collision file inside the Builder flow, not here.

## What This Skill No Longer Produces

New work does NOT produce the old Capability Pack scaffold:
- no `CAPABILITY.md`
- no generated `README.md` / `CHANGELOG.md` at Skill root
- no per-Skill `install.sh`
- no `checklists/` / `tools/` / `references/` / `examples/` pack tree
- no TAD manifest/catalog

The minimal output on the new path is one canonical Agent Skill directory with `SKILL.md` only; optional `references/`, `scripts/`, `assets/` only when evidence justifies.

## Conditional Deep Research

The preserved legacy research remains available at:
- `.claude/skills/capability-upgrade/references/legacy-pack-research.md` (and `.agents` mirror)

Load it **only** when a named research gap is identified and local project evidence is insufficient. Record the gap name when you load it. Do not load it speculatively.

## Failure Modes

- If a request requires changing TAD core, installer, roles, Gates, or framework Skills → `STOPPED_WITH_REASON`.
- If an `evolve` or `package` request is made → visible stop per Builder router (no pretend execution).
- If `LEGACY_PACK_OUT_OF_SCOPE` would be widened → return to Alex instead of widening scope.

## References

- `references/legacy-pack-research.md` — exact byte copy of pre-Phase-1 `capability-upgrade/SKILL.md` (conditional, evidence-gap only).
- Builder router: `.claude/skills/capability-builder/SKILL.md`
- Builder protocol: `.claude/skills/capability-builder/references/create-protocol.md`

Attribution

Sheldon-92Sheldon-92
View sourceSee grades on GitHubMore from Sheldon-92 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →