agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.status/SKILL.md

speckit.status

Skill3 starsChanged 45 days agoMITView on GitHub

Progress Dashboard - Calculate phase and task progress from tasks.md with evidence and risk visibility.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .agents/specs/[feature]/tasks.md, spec.md, plan.md, and linked evidence when available.

    line 10
  2. Distinctive:

    Every parsed task is counted exactly once, phase totals reconcile globally, and all non-complete risks are listed.

    line 24
  3. Distinctive:

    Read-only: do not edit tasks.md, checkboxes, specs, or implementation files.

    line 27
  4. Distinctive:

    Do not claim delivery from a checkbox alone.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Mission

Produce a read-only, reproducible progress report from the feature task list.

Inputs and Outputs

  • Read .agents/specs/[feature]/tasks.md, spec.md, plan.md, and linked evidence when available.
  • Output a console dashboard plus pending, blocked, overdue, and unverified task lists. Never mutate tasks.md.

Protocol

1. Parse and Validate

  • Accept - [ ], - [x], and - [X]; detect duplicate IDs, missing phase headings, dependencies, and task paths. Report malformed structure instead of guessing.

2. Calculate

  • Group tasks by phase and user story; calculate completed, pending, blocked, and total counts and percentages. Treat blocked or unverified tasks as incomplete and reconcile totals.

3. Evidence and Risk

  • Link tests, review, build, or acceptance evidence for completed tasks. Surface blocked dependencies, stale claims, missing paths, and absent acceptance evidence.

4. Report

  • Render a stable timestamped dashboard with phase bars, totals, next actions, blockers, and evidence gaps. Diagnose unreadable or empty task files without fabricating progress.

Completion Gate

Every parsed task is counted exactly once, phase totals reconcile globally, and all non-complete risks are listed.

Guard Rails

  • Read-only: do not edit tasks.md, checkboxes, specs, or implementation files.
  • Do not claim delivery from a checkbox alone; distinguish claimed completion from verified evidence.

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.

Reviews can't be read right now.

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.

Check your setup, free