agentleFS
ChianWChianW/C31/skills/utils/gsd-progress/SKILL.md

gsd-progress

Skill1 starsChanged 3 months agoMITView on GitHub

Output language: Respond automatically in the user's conversation language. Detect where the project stands and suggest (or auto-execute) the next GSD command. Read memory/.planning/STATE.md and memory/.planning/ROADMAP.md. If either file is missing, stop and report: From STATE.md, extract: - Phase: the numeric or named phase (e.g., "0", "1", "Exploration") - Status: pending / discussed / planned / executed / verified / shipped If Status is not explicitly stated, infer from the content: - "Active Tasks: None yet." or no tasks marked…

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use gsd-next and gsd-onboard.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • open-gsdSkill

    gsd-next

    Smart entry — detect project state and route to the right next GSD action.

    Also in 3 projects that use this

  • open-gsdSkill

    gsd-onboard

    Guide existing codebase onboarding through mapping, doc ingest, and planning setup

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After completing a phase and the user needs direction

    line 25
  2. Very specific:

    Read memory/.planning/STATE.md and memory/.planning/ROADMAP.md.

    line 31
  3. Distinctive:

    If either file is missing, stop and report:

    line 33
  4. Very specific:

    If Status is not explicitly stated, infer from the content:

    line 44
  5. Very specific:

    Check for --auto flag in arguments, or if the user message contains "auto".

    line 66
  6. Very specific:

    Never modify STATE.md or ROADMAP.md.

    line 83
  7. Distinctive:

    If status cannot be inferred, report "Unable to determine status" and ask the user to clarify.

    line 84
  8. Distinctive:

    Keep output concise; show only status and next step.

    line 85

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Multilingual Triggers

LanguageTrigger phrases
ENprogress, next step, what next, 下一步, 继续, gsd-progress, where are we
ZH下一步, 继续, 进度
JA次のステップ, 進捗確認

Output language: Respond automatically in the user's conversation language.

gsd-progress — Next-Step Detector

Detect where the project stands and suggest (or auto-execute) the next GSD command.

When to Use

  • User says "progress", "next step", "what next", "下一步", "继续", or runs gsd-progress
  • After completing a phase and the user needs direction

Workflow

Step 1: Read Planning Files

Read memory/.planning/STATE.md and memory/.planning/ROADMAP.md.

If either file is missing, stop and report:

No active project found. Run `gsd-new-project` first to initialize planning artifacts.

Step 2: Detect Current Phase

From STATE.md, extract:

  • Phase: the numeric or named phase (e.g., "0", "1", "Exploration")
  • Status: pending / discussed / planned / executed / verified / shipped

If Status is not explicitly stated, infer from the content:

  • "Active Tasks: None yet." or no tasks marked done → pending
  • Tasks exist but no implementation details → discussed
  • Plan or task list is present and not yet executed → planned
  • Code has been written or files modified → executed
  • Review or testing completed → verified
  • Deployed or released → shipped

Step 3: Determine Next Command

StatusSuggestion
No project (files missing)gsd-new-project
pendingC31-brainstorm or gsd-discuss-phase
discussedC31-plan or gsd-plan-phase
plannedC31-work or gsd-execute-phase
executedC31-review or gsd-verify-work
verifiedgsd-ship
shipped"Project is shipped. Run gsd-new-project for a new project."

Step 4: Suggest or Execute

Check for --auto flag in arguments, or if the user message contains "auto".

  • Suggest mode (default): Print the detected status and recommended command.
    📊 Current status: {phase_name} — {status}
    👉 Next step: {command}
  • Auto mode (--auto or "auto"): Execute the recommended command directly. Report before executing:
    📊 Auto-detected status: {phase_name} — {status}
    🚀 Executing: {command}

Rules

  • Never modify STATE.md or ROADMAP.md.
  • If status cannot be inferred, report "Unable to determine status" and ask the user to clarify.
  • Keep output concise; show only status and next step.
  • Under 300 lines total.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.