New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Link Deps

by joa23 in joa23/linear-cli

Discover and link related issues as dependencies. An agent skill from joa23/linear-cli.

MITAuto-check passedProduct & Project Management

Install Link Deps

skills CLI
$ npx skills add joa23/linear-cli --skill link-deps -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install joa23/linear-cli link-deps --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/joa23/linear-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/skills/link-deps .claude/skills/link-deps && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
link-deps
GitHub stars
144
Token cost
~2.3k tokens
SKILL.md length
460 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Discover and link related issues as dependencies. An agent skill from joa23/linear-cli.

  • Works in 8 steps: Identify Related Work → Analyze for Dependencies → Establish Relationships → …
  • Product & Project Management work in your project
  • SKILL.md covers When to Use, The Problem, The Solution and Discovery Process, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Link Deps is an agent skill from joa23/linear-cli. Discover and link related issues as dependencies. Searches for issues that should be connected and recommends dependency relationships to establish proper work order.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management. The repository describes itself as: A token-efficient CLI for Linear. The licence is MIT.

When your agent uses it

  • Product & Project Management work in your project

Example prompts

  • “/link-deps”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Identify Related Work
  2. Analyze for Dependencies
  3. Establish Relationships
  4. Verify the Graph
  5. Start with Foundation Work
  6. Use Consistent Keywords
  7. Regular Discovery Sessions
  8. Document Reasoning

What it can do on your machine

Read from SKILL.md and the folder at commit 575c6f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Link Deps loads about 2.3k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from joa23/linear-cli at commit 575c6f0, republished under its MIT licence (© joa23). 460 words, ~2,313 tokens.

Download SKILL.mdSave it as .claude/skills/link-deps/SKILL.md (or your agent's skills folder).
name
link-deps
description
Discover and link related issues as dependencies. Searches for issues that should be connected and recommends dependency relationships to establish proper work order.

You are an expert at discovering hidden dependencies between issues and establishing proper work order.

When to Use

Use this skill when:

  • You have many unconnected issues in your backlog
  • Work order is unclear because dependencies aren't explicit
  • Issues reference each other in descriptions but aren't formally linked
  • You need to understand prerequisite work before starting a feature

The Problem

Teams often have hundreds of issues without explicit dependencies. This makes it hard to:

  • Know what to work on next
  • Understand what blocks what
  • Plan sprints effectively
  • Parallelize work

Common scenario: You have 500 backlog issues but don't realize ENG-123 must be done before ENG-456 can start.

The Solution

Use search with dependency filters to discover relationships:

bash
# 1. Find issues with similar keywords that might be related
linear search "authentication" --team ENG --format full

# 2. Check if any already have dependencies
linear search "authentication" --has-dependencies --team ENG

# 3. Look for blocked work to identify bottlenecks
linear search --has-blockers --state "Todo" --team ENG

# 4. Find circular dependencies that need fixing
linear search --has-circular-deps --team ENG

Discovery Process

Search for issues by theme:

bash
# Find all auth-related work
linear search "auth" --team ENG --format full

# Find all database-related work
linear search "database" --team ENG --format full

# Find all API-related work
linear search "API" --team ENG --format full
2. Analyze for Dependencies

For each group, look for:

  • Foundation work - Core infrastructure others depend on
  • Feature work - Built on top of foundation
  • Follow-up work - Enhancements after initial feature
3. Establish Relationships

Link dependencies using --blocked-by:

bash
# Feature depends on foundation
linear issues update ENG-456 --blocked-by ENG-123

# Follow-up depends on feature
linear issues update ENG-789 --blocked-by ENG-456

# Multiple dependencies
linear issues update ENG-500 --blocked-by ENG-123,ENG-456
4. Verify the Graph

Check your work:

bash
# Visualize the dependency tree
linear deps --team ENG

# Check for circular dependencies
linear search --has-circular-deps --team ENG

# Find what's blocking the most work
linear deps --team ENG | grep "blocks:"

Discovery Patterns

Pattern 1: Text-Based Discovery

Issues often reference each other in descriptions:

bash
# Search for issue IDs in descriptions
linear search "ENG-123" --team ENG

# This finds issues mentioning ENG-123 but not formally linked
# Link them: linear issues update <found-id> --blocked-by ENG-123
Pattern 2: Keyword Clustering

Group issues by technology/feature:

bash
# Find OAuth-related issues
linear search "OAuth" --team ENG

# Determine which is foundation (likely: "OAuth provider setup")
# Link others to it:
linear issues update ENG-457 --blocked-by ENG-450  # OAuth provider = ENG-450
Pattern 3: State-Based Discovery

Work in "Blocked" state often needs explicit blockers:

bash
# Find blocked issues without formal dependencies
linear search --state "Blocked" --team ENG

# For each, determine what blocks it and link:
linear issues update ENG-200 --blocked-by ENG-199
Pattern 4: Priority Inversion Detection

High priority work blocked by low priority:

bash
# Find high priority items
linear search --priority 1 --team ENG

# Check if any are blocked
linear search --priority 1 --has-blockers --team ENG

# Verify blockers are appropriately prioritized

Best Practices

1. Start with Foundation Work

Identify and link core infrastructure first:

bash
# Find database migration work
linear search "migration" --team ENG

# Find API foundation work
linear search "API foundation" --team ENG

# Link feature work to these foundations
2. Use Consistent Keywords

Tag issues to make discovery easier:

  • Add labels: foundation, feature, enhancement
  • Use consistent titles: "Foundation: OAuth", "Feature: Login with OAuth"
3. Regular Discovery Sessions

Run discovery weekly:

bash
# 1. Find new issues added this week
linear search --team ENG --limit 50

# 2. Check for unlinked work
linear search --has-blockers --team ENG

# 3. Update dependencies as you discover them
4. Document Reasoning

When linking dependencies, add a comment explaining why:

bash
linear issues update ENG-456 --blocked-by ENG-123
linear issues comment ENG-456 --body "Blocked by ENG-123 because we need OAuth provider before implementing login flow"
Show full SKILL.md (184 more words)Show less

Commands Reference

Discovery Commands
bash
# Find issues by keyword
linear search "<keyword>" --team <TEAM>

# Find issues with dependencies
linear search --has-dependencies --team <TEAM>

# Find blocked work
linear search --has-blockers --team <TEAM>

# Find circular dependencies
linear search --has-circular-deps --team <TEAM>

# Find issues blocked by specific issue
linear search --blocked-by <ISSUE-ID>

# Find issues blocking specific issue
linear search --blocks <ISSUE-ID>
Linking Commands
bash
# Add single blocker
linear issues update <ISSUE> --blocked-by <BLOCKER>

# Add multiple blockers
linear issues update <ISSUE> --blocked-by <BLOCKER1>,<BLOCKER2>

# Add dependency (what this depends on)
linear issues update <ISSUE> --depends-on <DEPENDENCY>

# Remove dependencies (update with empty string)
linear issues update <ISSUE> --blocked-by ""
Verification Commands
bash
# Visualize dependencies
linear deps <ISSUE-ID>
linear deps --team <TEAM>

# Check specific issue's blockers
linear issues blocked-by <ISSUE-ID>

# Check what an issue blocks
linear issues blocking <ISSUE-ID>

# List issue dependencies
linear issues dependencies <ISSUE-ID>

Example Workflow

Goal: Discover and link all authentication-related dependencies.

bash
# Step 1: Find all auth issues
linear search "auth" --team ENG --format full > auth_issues.txt

# Step 2: Identify foundation work (look for "OAuth provider", "JWT library", etc.)
# Found: ENG-450 "Setup OAuth2 provider"

# Step 3: Find all OAuth login features
linear search "OAuth login" --team ENG

# Found: ENG-451, ENG-452, ENG-453

# Step 4: Link features to foundation
linear issues update ENG-451 --blocked-by ENG-450
linear issues update ENG-452 --blocked-by ENG-450
linear issues update ENG-453 --blocked-by ENG-450

# Step 5: Find session management work
linear search "session" --team ENG

# Found: ENG-460 "Session management"

# Step 6: Link session work to OAuth (needs login first)
linear issues update ENG-460 --blocked-by ENG-451

# Step 7: Visualize the complete graph
linear deps --team ENG

# Step 8: Check for circular dependencies
linear search --has-circular-deps --team ENG

# Step 9: Find any remaining blocked work without explicit blockers
linear search --state "Blocked" --team ENG
# For each, add proper blocker using --blocked-by

Output Format

After running discovery, present findings as:

DEPENDENCY DISCOVERY REPORT: Team ENG
════════════════════════════════════════

DISCOVERED RELATIONSHIPS (12)
────────────────────────────────────────
Foundation Work:
  ENG-450 OAuth provider setup
    → blocks 3 features: ENG-451, ENG-452, ENG-453

  ENG-460 Session management
    → blocks 2 features: ENG-461, ENG-462

Feature Work:
  ENG-451 OAuth login
    → blocks 1 enhancement: ENG-470

RECOMMENDATIONS
────────────────────────────────────────
1. Prioritize ENG-450 (blocks 3 features)
2. Link ENG-475 to ENG-450 (mentioned in description)
3. Review circular dependency: ENG-480 ↔ ENG-481

COMMANDS TO RUN
────────────────────────────────────────
linear issues update ENG-475 --blocked-by ENG-450
linear issues update ENG-480 --blocked-by ""  # Break cycle

Automation Tips

For large backlogs (100+ issues), automate discovery:

  1. Export all issues: linear search --team ENG --limit 250 > backlog.txt
  2. Group by keyword: Use grep to find related issues
  3. Create dependency map: Document relationships in a spreadsheet
  4. Batch link: Run update commands for each discovered relationship
  5. Verify: linear deps --team ENG to check the final graph

Anti-Patterns to Avoid

❌ Don't over-link: Only link true dependencies, not "nice to have" relationships ❌ Don't create cycles: Always verify no circular dependencies ❌ Don't link to closed issues: Check issue state before linking ❌ Don't assume: If unsure whether A blocks B, ask the team

Success Metrics

After running link-deps, you should have:

  • ✅ Clear work order (know what to do first)
  • ✅ No circular dependencies
  • ✅ Foundation work identified and prioritized
  • ✅ Blocked work has explicit blockers
  • ✅ Dependency graph visualizes cleanly

Run linear deps --team <TEAM> and you should see a clear tree structure with minimal orphaned issues.

© joa23, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in internal/skills/link-deps of joa23/linear-cli.

Open the folder on GitHubat commit 575c6f0

Compare with similar skills

Link Deps next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Link Deps compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Link Deps this skilljoa23/linear-cli144—~2.3kAutomated safety check: PassMIT
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Game Changing FeaturesopenstatusHQ/data-table-filters2.3k3 repos~2.1kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Convex Create Componentspokvulcan/poker-planning1148 repos~2.6kAutomated safety check: PassMIT
Self Improving Agentfarm-fe/farm5.6k2 repos~3.3kAutomated safety check: NotesMIT

Similar skills

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    Product & Project ManagementAuto-check passed

  • Game Changing Features

    openstatusHQ/data-table-filters

    Find 10x product opportunities and high-leverage improvements.

    2.3k GitHub starsUsed in 3 repos~2.1k tokens
    Product & Project ManagementAuto-check passed

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Convex Create Component

    spokvulcan/poker-planning

    Builds reusable Convex components with isolated tables and app-facing APIs.

    114 GitHub starsUsed in 8 repos~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Self Improving Agent

    farm-fe/farm

    A universal self-improving agent that learns from ALL skill experiences.

    5.6k GitHub starsUsed in 2 repos~3.3k tokens
    Product & Project ManagementAuto-check: notes

  • Weekly Engineering Retro

    garrytan/gstack

    Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from joa23/linear-cli

All 8 skills in this repo

  • Triage

    joa23/linear-cli

    Triage and prioritize Linear backlog issues using the linear CLI.

    144 GitHub stars~699 tokensUpdated 24 days ago
    Auto-check passed

  • Deps

    joa23/linear-cli

    Visualize and analyze issue dependencies in Linear. An agent skill from joa23/linear-cli.

    144 GitHub starsUsed in 1 repo~914 tokens
    Auto-check passed

  • Prd

    joa23/linear-cli

    Create agent-friendly Linear tickets with PRDs, sub-issues, and clear success criteria.

    144 GitHub stars~621 tokensUpdated 24 days ago
    Auto-check passed

  • Retro

    joa23/linear-cli

    Analyze completed Linear cycles for retrospectives. An agent skill from joa23/linear-cli.

    144 GitHub starsUsed in 1 repo~790 tokens
    Auto-check passed

  • Cycle Plan

    joa23/linear-cli

    Plan Linear cycles using velocity analytics. An agent skill from joa23/linear-cli.

    144 GitHub stars~1.2k tokensUpdated 24 days ago
    Auto-check passed

  • Release

    joa23/linear-cli

    Pre-release checklist to ensure CHANGELOG, version numbers, tests, and documentation are updated before cutting a release.

    144 GitHub stars~3.2k tokensUpdated 24 days ago
    Auto-check passed

Categories

Questions about Link Deps

What does Link Deps do?

Discover and link related issues as dependencies. An agent skill from joa23/linear-cli. Link Deps is an agent skill from joa23/linear-cli. Discover and link related issues as dependencies.

When should I use Link Deps?

Link Deps fits situations like: product & Project Management work in your project.

How do I install Link Deps in Claude Code?

Run `npx skills add joa23/linear-cli --skill link-deps -a claude-code`. Or copy the skill folder (internal/skills/link-deps in joa23/linear-cli) into .claude/skills/link-deps in your project. Claude Code loads it when a task matches its description.

How do I install Link Deps in Codex?

Run `npx skills add joa23/linear-cli --skill link-deps -a codex`. Or copy the skill folder (internal/skills/link-deps in joa23/linear-cli) into .agents/skills/link-deps in your project. Codex loads it when a task matches its description.

Can I use Link Deps in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joa23/linear-cli --skill link-deps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/link-deps, .gemini/skills/link-deps, .github/skills/link-deps and .opencode/skills/link-deps in your project.

What does Link Deps need to run?

SKILL.md names no scripts, command-line tools or credentials: Link Deps is instructions for the agent only.

Does Link Deps access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Link Deps safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Link Deps use?

Link Deps is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Link Deps use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Link Deps?

Skills that share tags, products or a category with Link Deps: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Game Changing Features (openstatusHQ/data-table-filters, 2.3k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Convex Create Component (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Link Deps?

joa23 (a GitHub user) maintains it in joa23/linear-cli, which has 144 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 13, 2026.

Source: joa23/linear-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.