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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Roadmap Sync

ASecurity

Check ROADMAP.md against the actual code and git history and fix the drift, such as ticked items whose evidence is gone, finished work nobody ticked, and stale next actions or progress. Use when the user comes back after a break or from another machine, or asks whether the roadmap is up to date.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsrustgogit

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add TonyLikeDev/TrustMeBro --skill roadmap-sync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Roadmap Sync?

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

Security grade badge for Roadmap Sync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tonylikedev-roadmap-sync-d43549c9/badge)](https://www.skillsdirectory.com/skills/tonylikedev-roadmap-sync-d43549c9)

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

Files
SKILL.md
---
name: roadmap-sync
description: Check ROADMAP.md against the actual code and git history and fix the drift, such as ticked items whose evidence is gone, finished work nobody ticked, and stale next actions or progress. Use when the user comes back after a break or from another machine, or asks whether the roadmap is up to date.
---

# Roadmap sync

Progress script: `.bob/trustmebro/scripts/roadmap_progress.py`.

1. Read the roadmap and the plan, then `git log` since the last Change log date, plus uncommitted changes.
2. Check every `[x]` and `[~]`: does the evidence it names still exist? Run the test suite once if it is quick; a failing test turns its `[x]` back into `[~]`.
3. Find finished work nobody ticked: commits or files that complete an open item.
4. Check the format the TrustMeBro hooks need: a `<!-- trustmebro -->` first line in the roadmap, plan and layout (without it the hooks ignore the file; older files lack it), the `<!-- progress:start -->` / `<!-- progress:end -->` markers, and one `## <Phase>: <title>` heading per phase in the plan. Split merged headings such as "## Weeks 4 to 10" into one heading per phase.
5. Report the drift as a short list (item, what you found, proposed change). After the user confirms, apply it, add one Change log line (`- YYYY-MM-DD: synced with the code: ...`), update Next actions and "Last updated", and rerun the progress script.

Never change the plan here. Plan changes go through the deviation rule: ask the user, then log a dated line in the plan's Deviations section.

Attribution

TonyLikeDevTonyLikeDev
View sourceMore from TonyLikeDev →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

695601 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 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 →