Agent skill

Work Item Sequencing

by forcedotcom in forcedotcom/salesforcedx-vscode

Numbering convention for ordering GUS work items within an epic.

BSD-3-ClauseAuto-check passedDevelopment

Install Work Item Sequencing

skills CLI
$ npx skills add forcedotcom/salesforcedx-vscode --skill work-item-sequencing -a claude-code

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

GitHub CLI
$ gh skill install forcedotcom/salesforcedx-vscode work-item-sequencing --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/forcedotcom/salesforcedx-vscode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/work-item-sequencing .claude/skills/work-item-sequencing && 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
work-item-sequencing
GitHub stars
1k
Token cost
~1.1k tokens
SKILL.md length
491 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Numbering convention for ordering GUS work items within an epic.

  • Works in 5 steps: Lay out work items. → Must-precede → sequential top-level (1,… → Parallel under a step → same parent,… → …
  • Planning an epic
  • SKILL.md covers Convention, When to number, ADRs sequence first and Assigning (planning), plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Work Item Sequencing is an agent skill from forcedotcom/salesforcedx-vscode. Numbering convention for ordering GUS work items within an epic. Numeric prefixes in Subjectc express sequencing (do X before Y) and parallelism. Use when planning an epic, when the user states a dependency between work items, or when asked what's unblocked/ready in an epic.

Its SKILL.md is about 1.1k 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 Development, covering Architecture decision records. The repository describes itself as: Salesforce Extensions for VS Code. The licence is BSD-3-Clause.

When your agent uses it

  • Planning an epic
  • The user states a dependency between work items
  • Asked whats unblocked/ready in an epic

Example prompts

  • “/work-item-sequencing”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Lay out work items.
  2. Must-precede → sequential top-level (1, 2).
  3. Parallel under a step → same parent, distinct suffix (1.1, 1.2).
  4. Independent → leave unnumbered.
  5. Prefix Subject__c with number + space. Create via gus-cli.

What it can do on your machine

Read from SKILL.md and the folder at commit f7bb6fe. 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.

    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

Work Item Sequencing loads about 1.1k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 491 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 forcedotcom/salesforcedx-vscode at commit f7bb6fe, republished under its BSD-3-Clause licence (© forcedotcom). 491 words, ~1,066 tokens.

Download SKILL.mdSave it as .claude/skills/work-item-sequencing/SKILL.md (or your agent's skills folder).
name
work-item-sequencing
description
Numbering convention for ordering GUS work items within an epic. Numeric prefixes in Subject__c express sequencing (do X before Y) and parallelism. Use when planning an epic, when the user states a dependency between work items, or when asked what's unblocked/ready in an epic.
review
never

Work Item Sequencing

Numbering convention for order + parallelism among work items in one epic. Number = prefix in Subject__c, space-delimited. Per-epic scope; cross-epic deps go in WI body prose, not numbers.

Companion to gus-cli (CLI mechanics: query, create, update, statuses, IDs).

Convention

Prefix Subject__c with a dotted number + single space:

1 Set up the runtime service
2 Migrate the parser to the runtime
1.1 Add config schema
1.2 Add config loader
  • Sequential (1, 2, 3): in order. 2 waits on 1; 3 waits on 2.
  • Parallel (1.1, 1.2): same-parent siblings, no waiting on each other.
  • Group gating: next number at a level waits for all work under prior numbers. 2 waits on 1 + every 1.x/1.x.y.
  • Arbitrary depth (1.1.1, …): same recursive rule.
The rule

WI ready when every WI sorting before it (at shallower-or-equal ancestor level) is done. Siblings parallel; sibling-group gates next number at parent level.

1.2 ready once 1.1 + descendants done. 2 ready once everything under 1 done.

Done

Done = Status__c is Closed or Completed.

Fixed is not done — usually means PR not merged yet. Non-terminal statuses (Fixed, Ready for Review, QA In Progress) never satisfy a prerequisite. See gus-cli ## Status__c values.

When to number

Optional.

  • Use: epic-level planning, or when user states a dependency.
  • Skip: standalone work; don't renumber an epic of accumulated independent items.

Unnumbered = no deps, nothing depends on it. Always ready; never gates, never gated. Don't infer order from date/position — no number means independent.

ADRs sequence first

Epic needing a new or updated ADR (per ADR-FORMAT "When to offer": hard-to-reverse + surprising + real trade-off) → the ADR-writing WI(s) get the lowest number: 1 (single ADR) or 1.1/1.2 (parallel siblings). Dependent WIs start at 2. Rationale: dependents encode a decision; the ADR must exist first so downstream work builds on a recorded decision, not an unstated one.

Before creating the rest of the epic, confirm the required ADRs with the user — which decisions need recording, repo-wide (docs/adr/) vs package-local (packages/*/docs/adr/). Then sequence the ADR WI(s) as 1/1.x and everything else 2+.

No ADR needed → number normally.

Show full SKILL.md (175 more words)Show less

Assigning (planning)

  1. Lay out work items.
  2. Must-precede → sequential top-level (1, 2).
  3. Parallel under a step → same parent, distinct suffix (1.1, 1.2).
  4. Independent → leave unnumbered.
  5. Prefix Subject__c with number + space. Create via gus-cli.

Dense from 1 per group preferred; gaps harmless (sort is by value).

Reading ("what's ready/unblocked in this epic?")

  1. Query epic WIs incl Status__c. Query without open-only filter — done prerequisites are Closed, which open-only excludes (see gus-cli "What's unfinished in this epic").
  2. Parse leading dotted number from each Subject__c. None → unnumbered.
  3. Readiness: unnumbered → ready; numbered → ready iff all prior-sorting ancestors done.
  4. Report 3 groups: Ready now (unblocked numbered + all unnumbered), Blocked (name blocking number), Done (optional).

Sort by integer segments (1.2 before 1.10, not lexical). Unnumbered sort last.

Edge cases

  • Malformed (1., 1..2, 1.x): treat unnumbered + flag — likely typo'd dependency.
  • Duplicate (two 1.2): allowed = parallel siblings. Don't flag.
  • Orphan child (1.1, no 1): rule still holds; don't require parent to exist.
  • Non-sequence number (W-12345 backport, version 2.40 release): only leading N/N.N… + space counts. Ambiguous → ask.

© forcedotcom, BSD-3-Clause. 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 .claude/skills/work-item-sequencing of forcedotcom/salesforcedx-vscode.

Open the folder on GitHubat commit f7bb6fe

Compare with similar skills

Work Item Sequencing 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.

Work Item Sequencing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Work Item Sequencing this skillforcedotcom/salesforcedx-vscode1k—~1.1kAutomated safety check: PassBSD-3-Clause
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT
Cto AdvisorIbrahim-3d/orchestrator-supaconductor3804 repos~2.4kAutomated safety check: PassMIT
Improve Codebase Architectureywwynm/EverythingDone14415 repos~1.3kAutomated safety check: PassGPL-3.0
Domain Modelingbrim-borium/spotify_sdk1665 repos~806Automated safety check: PassApache-2.0
Design Doc MermaidSpillwaveSolutions/design-doc-mermaid1751 repos~5.6kAutomated safety check: PassNone

Similar skills

  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    380 GitHub starsUsed in 4 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Improve Codebase Architecture

    ywwynm/EverythingDone

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.

    144 GitHub starsUsed in 15 repos~1.3k tokens
    DevelopmentAuto-check passed
  • Domain Modeling

    brim-borium/spotify_sdk

    Build and sharpen a project's domain model. An agent skill from brim-borium/spotify_sdk.

    166 GitHub starsUsed in 5 repos~806 tokens
    DevelopmentAuto-check passed
  • Design Doc Mermaid

    SpillwaveSolutions/design-doc-mermaid

    Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code.

    175 GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed
  • Learning Opportunities

    DrCatHicks/learning-opportunities

    Facilitates deliberate skill development during AI-assisted coding.

    2.5k GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from forcedotcom/salesforcedx-vscode

All 37 skills in this repo
  • Command UI

    forcedotcom/salesforcedx-vscode

    Command palette, CodeLens, context menus, package.nls titles, and NotificationModeService.

    1k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Services Extension Consumption

    forcedotcom/salesforcedx-vscode

    Consume the salesforcedx-vscode-services extension API. An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~5k tokensUpdated today
    Auto-check passed
  • Changelog

    forcedotcom/salesforcedx-vscode

    Polish the automated CHANGELOG on develop before the next stable build.

    1k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Core Extension API

    forcedotcom/salesforcedx-vscode

    Public API exported by salesforcedx-vscode-core activate(). An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~842 tokensUpdated today
    Auto-check passed
  • Drivable Vscode

    forcedotcom/salesforcedx-vscode

    Operate a real VS Code instance through drivable-vscode. An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Effect Best Practices

    forcedotcom/salesforcedx-vscode

    Enforces Effect-TS patterns for services, errors, layers, atoms, and Effect.pipe composition.

    1k GitHub stars~6.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Work Item Sequencing

What does Work Item Sequencing do?

Numbering convention for ordering GUS work items within an epic. Work Item Sequencing is an agent skill from forcedotcom/salesforcedx-vscode. Numbering convention for ordering GUS work items within an epic.

When should I use Work Item Sequencing?

Work Item Sequencing fits situations like: planning an epic; the user states a dependency between work items; asked whats unblocked/ready in an epic.

How do I install Work Item Sequencing in Claude Code?

Run `npx skills add forcedotcom/salesforcedx-vscode --skill work-item-sequencing -a claude-code`. Or copy the skill folder (.claude/skills/work-item-sequencing in forcedotcom/salesforcedx-vscode) into .claude/skills/work-item-sequencing in your project. Claude Code loads it when a task matches its description.

How do I install Work Item Sequencing in Codex?

Run `npx skills add forcedotcom/salesforcedx-vscode --skill work-item-sequencing -a codex`. Or copy the skill folder (.claude/skills/work-item-sequencing in forcedotcom/salesforcedx-vscode) into .agents/skills/work-item-sequencing in your project. Codex loads it when a task matches its description.

Can I use Work Item Sequencing 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 forcedotcom/salesforcedx-vscode --skill work-item-sequencing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/work-item-sequencing, .gemini/skills/work-item-sequencing, .github/skills/work-item-sequencing and .opencode/skills/work-item-sequencing in your project.

What does Work Item Sequencing need to run?

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

Does Work Item Sequencing 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 Work Item Sequencing 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 Work Item Sequencing use?

Work Item Sequencing is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Work Item Sequencing use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Work Item Sequencing?

Skills that share tags, products or a category with Work Item Sequencing: PR Design Doc (OpenHands/OpenHands, 90k stars), Cto Advisor (Ibrahim-3d/orchestrator-supaconductor, 380 stars), Improve Codebase Architecture (ywwynm/EverythingDone, 144 stars) and Domain Modeling (brim-borium/spotify_sdk, 166 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Work Item Sequencing?

forcedotcom (a GitHub organization) maintains it in forcedotcom/salesforcedx-vscode, which has 1,035 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 7, 2026.

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