agentleFS
InSciCoInSciCo/i-framework/.claude/skills/product-status/SKILL.md

product-status

Skill4 starsChanged 4 months agoMITView on GitHub

Render a read-only dashboard of the Product/ folder — stage/gate completion, risk-burndown state, feature counts by classification and priority, the ranked innovation edge list, and gaps (UVP elements with no feature, features missing acceptance criteria, unclassified features). Use to review progress or spot holes.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Cherry-picked matrix: if competition.md exists and the "Us" column is ✓ on every row, flag it — a credible comparison has ≥1 row where a …

    line 28
  2. Very specific:

    Unverified competitor claims: if competition.md exists, count cells marked ?

    line 29

≈ “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-status — the dashboard (read-only)

You summarize the whole Product/ folder at a glance. Never modify files — if you find problems, list them as gaps for the founder to fix with the relevant skill.

Procedure

  1. Read everything. The three stage artifacts (and their gate: frontmatter), Product/Features/F*.md (frontmatter + body), Product/features-index.md if present, and Product/competition.md if present.
  2. Compute:
    • Stage/gate completion — which of the three gates are passed vs. open (the risk-burndown line).
    • Feature counts — total, by classification, by priority (MoSCoW), by status.
    • Innovation edge list — innovation features sorted by innovation_weight desc, each with its contributes_to UVP.
    • Weight distribution — are weights spread or clustered?
  3. Run integrity checks (the high-value part) — validate cross-file consistency and list every violation:
    • Dangling UVP reference: a feature's contributes_to value that matches no UVP id in innovation.md.
    • UVP orphan: a UVP element in innovation.md with no innovation feature tracing to it.
    • Classification/weight mismatch: implementation with weight ≠ 0; innovation with weight 0; innovation missing contributes_to.
    • Thin feature: missing a user-story clause, or <3 acceptance criteria.
    • Broken dependency: a depends_on id that points to no existing feature.
    • Portfolio flags: apply the same thresholds as /classify — >40% innovation; and, only when there are ≥3 innovation features, innovation weight span <30 points (skip the spread check below that count).
    • Cherry-picked matrix: if competition.md exists and the "Us" column is ✓ on every row, flag it — a credible comparison has ≥1 row where a rival matches or beats us.
    • Unverified competitor claims: if competition.md exists, count cells marked ? and surface them as items to verify (with the snapshot date).
  4. Render a concise dashboard — a risk-burndown header, a counts table, the ranked edge list, and a clearly separated Gaps / next actions section that names which skill fixes each gap (/feature, /classify, /innovate).

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.