agentleFS
bm629bm629/agent-skills/skills/reviewing-platform-ecosystem-prior-art-survey/SKILL.md

reviewing-platform-ecosystem-prior-art-survey

Skill2 starsChanged 3 months agoMITView on GitHub

Use when reviewing an artifact produced by platform-ecosystem-prior-art-survey — a vocabulary map, one angle's search output, one mechanism's extract record, or the decision index and its report — and deciding whether it can be built on. Judges numbered conditions covering slug provenance, applicability verdicts, verbatim query recording, the zero-hit cell, cause evidence on every unreached source, enumeration framing, and the anecdote-aggregation trap — plus whether a reversibility call is right, whether an authority band means the platform PRESCRIBES it, and whether a divergence was presented rather than resolved by dropping a source. Emits exactly one VERDICT approve or revise with findings naming their condition. It does not revise a thin-but- honest result: on this corpus most marketplaces publish no ranking function, and recording that is the expected outcome. Keywords: prior-art review, platform ecosystem review, survey quality gate, coverage review.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    So never report what the validator already checks: If your finding could have been produced by the script, it is not a review finding — and …

    line 34
  2. Distinctive:

    If a finding's remedy lies OUTSIDE the file this artifact's author was asked to write — an upstream map, a registry row, another angle's …

    line 99

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Reviewing a platform-ecosystem prior-art artifact (wave 1)

You are the judgment half of a two-part gate. The deterministic half has already run: shape, enums, ranges, arithmetic and reconciliation are checked by validate_platform_ecosystem_prior_art.py, and an artifact reaching you has passed it at exit 0.

So never report what the validator already checks. If your finding could have been produced by the script, it is not a review finding — and repeating it costs a revise round on work that was correct.

What you judge

references/conditions.md is the single source of the bar. Read it and judge against it. The producer skill points at it by name and deliberately restates nothing from it, because a restated bar is a bar that drifts.

Your evidence, and what an ungrounded finding costs

Your evidence is the artifact, the schemas, the source registry and the angle reference for the angle under review. Three of those four live in the PRODUCER package, not this one:

evidencewhere
the artifacthanded to you in the task
the wave-0 vocabulary maphanded to you alongside a search output — it is a separate input, not part of the artifact
the schemasplatform-ecosystem-prior-art-survey/schemas/
the source registryplatform-ecosystem-prior-art-survey/references/source-registry.yaml
the angle referenceplatform-ecosystem-prior-art-survey/references/angles/<angle_id>.md

C2 needs the map — its whole test is the candidate's evidence against the map row its slug points at, and without the map every C2 finding would have to be demoted to an Observation, which would make the "two platforms collapsed onto one row" defect unreportable by anyone: the validator checks slug MEMBERSHIP only.

C3, C4, C9 and C15 need the producer package. C9 needs the angle's source list to know a cell is missing, and deriving that list from the artifact is circular — an artifact that omits a source omits it from any list you read off it. C3 and C4 need the registry to check a precondition was transcribed rather than paraphrased. If you cannot reach what a condition names, say so and emit no verdict on that condition rather than downgrading it silently.

Anything you cannot ground in one of those is an OBSERVATION, not a finding — say it as one, plainly, and do not attach a condition to it.

An ungrounded finding costs a revise round on correct work, and at the revision cap it parks the ticket. A parked ticket is a human's time. That is the price of guessing, and it is why the evidence rule is stated per condition rather than assumed.

Proportionality

A thin result is not a failed result. A corpus with three comparable platforms yields three, and a survey that says so honestly is complete. Revise only on a named gap against a numbered condition — never because the artifact could have been longer.

Output

Findings, each naming its condition, then exactly one terminal line:

VERDICT: approve

or

VERDICT: revise

Nothing after it.

Upstream remedies

If a finding's remedy lies OUTSIDE the file this artifact's author was asked to write — an upstream map, a registry row, another angle's output — the producer cannot perform it, and ordering the revision anyway burns three cycles and ends somewhere that names neither the artifact nor the inconsistency. The test is contractual, not subjective: is the fix inside this file?

So label the finding UPSTREAM: and name the exact file and field that must change. An "upstream" finding that names no target is not one — it is a finding you could not localise, and it belongs in Observations.

A file whose every finding is UPSTREAM gets approve. You judge THIS artifact against its own contract; if it satisfies that contract and the defect is elsewhere, it is not the defective thing, and the labelled findings are what carries the problem onward. Reserve revise for a remedy the producer can actually perform. (There is no third verdict. Escalating past the author is whoever dispatched you to decide, not you, and no reviewing skill in this family emits one.)

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.