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

Threadify Your Next Moves

ASecurity

Review supplied buyer conversations against a confirmed offer and prepare up to three evidence-backed next actions, one at a time. Use when the owner asks what to do next with current conversations.

2 stars
0 votes
0 copies
1 views
Added 9/29/2026
ai-agentsnode

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add lennoxsaint/Threadify-workflows --skill threadify-your-next-moves --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Threadify Your Next Moves?

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

Security grade badge for Threadify Your Next Moves
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lennoxsaint-threadify-your-next-moves/badge)](https://www.skillsdirectory.com/skills/lennoxsaint-threadify-your-next-moves)

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: threadify-your-next-moves
description: Review supplied buyer conversations against a confirmed offer and prepare up to three evidence-backed next actions, one at a time. Use when the owner asks what to do next with current conversations.
---

# Threadify Your Next Moves

Read `references/threadify-001.md`, `references/workflow-manifest.json` and `references/workflow-readme.md` from this skill directory.

Start locally with the user's offer and supplied conversations. Do not ask for a provider choice first. If no confirmed offer exists, invoke `threadify-offer-builder`, confirm its local handoff, then resume this workflow.

Lock the confirmed offer facts before interpreting a conversation. Never add a curriculum, deliverable, result, promise, price or limit that the offer record does not contain. Ask only for a missing fact that would materially change fit or the next action.

Use the installed exact-release CLI at `node ~/.threadify-workflows/current/cli/bin/threadify-workflows.mjs conversations`; when `THREADIFY_WORKFLOWS_HOME` was set during installation, resolve `current/cli/bin/threadify-workflows.mjs` below that state root instead. In a source checkout, use `node bin/threadify-workflows.mjs conversations`. Choose an absolute private state directory on macOS or Linux. Keep the full conversation source outside the workflow state. Import only the stable source reference, observation time and factual evidence needed for the decision.

A lead requires evidence of interest in help or an offer relevant to the confirmed offer. An explicit relevant help request counts as recipient interest even when it is phrased as a question, such as "I want help with this. Does your offer cover it?" A generic public question does not qualify. Recipient interest remains separate from permission to use a private channel. Prepare up to three actions only when each has direct support; returning none is valid. Run `review` and present exactly one bound action and its hash.

For conversations supplied locally, label the source `not_rechecked` unless it was reopened in the current run, and require reinspection before action. When additional public research is needed, invoke `threadify-qualified-buyer-research` and reuse its Offer Context, qualification gates, narrow-query order, five-result sampling, and stop limits. Do not create a second open-ended search loop here. Qualified Buyer Research may stage one offer-free public reply in a verified composer when requested, but it always stops before Send. Reopen the source before proposing any new external action from inspected research.

Treat the bundled synthetic fixture only as a mechanics test. Label it synthetic and never cite it as customer, market or provider evidence.

Use `decide` with `approve` or `reject` only after the owner responds to that exact display. Approval is not delivery. Before an external action, re-open the source and provide fresh inspection evidence; if the action changed after inspection, prepare and review a new bound action. For private contact, require both recipient interest and permission for the proposed channel. Persist with `begin-attempt` before the host acts, then reconcile with `receipt`. Never replay `attempt_pending`, `unknown` or `succeeded` actions.

If a host tool is unsupported, provide the manual artifact in the workflow README. Optional reminders are review-only candidates, require explicit host-native opt-in and send nothing.

Attribution

lennoxsaintlennoxsaint
View sourceSee grades on GitHubMore from lennoxsaint →
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', ...

698621 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 →