agentleFS
ldaumeldaume/agentic-engineering-harness/skills/writing/writing-product/SKILL.md

writing-product

Skill3 starsChanged 3 months agoMITView on GitHub

Use whenever writing or revising a product status report or update, an adaptive Now/Next/Later or FaST-compatible roadmap, a progress update, a problem brief, bet brief, experiment card, product decision record, or outcome review (Statusbericht, Roadmap, Fortschritt, Problem Brief). Carries the outcome, evidence, uncertainty, risk, and learning structure instead of ticket activity, velocity, or ceremony. Not for deciding what to build; that is a product decision, not a document.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer outcome over output, evidence over backlog weight, flow over utilization, learning over false certainty, explicit investment …

    line 16
  2. Distinctive:

    Keep distinct: signal, problem, opportunity, candidate bet, focus, delivery, adoption and outcome, learning.

    line 24
  3. Distinctive:

    Never imply that FaST assigns fixed teams or requires team-specific long-term feature roadmaps.

    line 31
  4. Distinctive:

    If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Product & Agile Writing

Make the actual state of a product visible: software development is product and system evolution under uncertainty, so the text reports changed reality and learning, not motion. This skill writes the document; deciding what is worth building belongs to product-craft when installed.

Stance

Prefer outcome over output, evidence over backlog weight, flow over utilization, learning over false certainty, explicit investment boundaries, shared ownership, visible risk, built-in quality. Do not introduce Scrum, SAFe, story points, velocity, fixed teams, or ceremonies as a default, because they answer a process question the reader did not ask.

Problem before solution

Keep distinct: signal, problem, opportunity, candidate bet, focus, delivery, adoption and outcome, learning. Do not collapse them into "feature", because a roadmap of features hides which problem each one is a bet on.

FaST

FaST-compatible artifacts show collective product direction and visible work. Never imply that FaST assigns fixed teams or requires team-specific long-term feature roadmaps.

Route

  • status report: references/status.md
  • FaST planning: references/fast.md
  • adaptive roadmap: references/roadmaps.md
  • progress update: references/progress.md
  • problem brief, bet brief, experiment card, decision record, outcome review: references/product-docs.md

Gate

From this skill's directory, run python3 ../writing-core/scripts/quality_gate.py --artifact <type> --lang <de|en> FILE with type one of agile_status|fast_roadmap|agile_progress|product_document. If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand. Fix every error; judge each warning, because warnings are heuristics, not rules.

Done when

A reader can name the desired outcome, the current state, the evidence, the uncertainty or risk, the decision or investment boundary, and the next learning or delivery step.

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.