agentleFS
akshay-diwadkarakshay-diwadkar/first-four-hours/skills/workbench/assess/SKILL.md

assess

Skill1 starsChanged 4 days agoMITView on GitHub

Assess a PR or code change against its issue/spec, acceptance criteria, repository rules, tests, and base behavior for correctness, code quality, maintainability, and proportionate security. Use for PR review, re-review, acceptance-criteria checks, or merge readiness.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use verify and handoff.

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.
  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 1

    Distinctive

    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:

    If you wrote or planned this change in this context, hand the whole stage to a fresh-context owner per the Bounded Delegation Protocol, …

    line 18

“Common” is measured: kept by at least 6 in 10 of the 16 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

Assess

Authority

Assess reconciles one exact target/base/head with the original user request, authoritative requirements, any available Blueprint, repository rules, tests, and base behavior. Snapshot every used external target, authority, evidence, proof, or diagnosis; Git/repository-local truth needs none. Unknown required external currentness means blocked.

The assessment is read-only: never repair, edit the target, merge, approve, or mutate GitHub. Construct owns implementation; Diagnose owns broader defect/risk investigation. assessment.md is a result, never approval, certification, or merge authority. Posting its findings is a separate step after check, only on the user's explicit yes.

Assessment

If you wrote or planned this change in this context, hand the whole stage to a fresh-context owner per the Bounded Delegation Protocol, reading nothing else; read it before any other delegation too.

Otherwise first read assess guidance, plus Blueprint evidence when a sealed Blueprint exists, delta review when an earlier assessment does, and pull requests when the target pull request's head may be missing from the current repository. Establish exact target/base/head, current authority, base truth, and requested delta once. Derive requirements from authority and the change from base/head before reading PR prose, comments, audits, or prior reviews; those are hints that may add candidates, never clear one. Each turn re-reads your context, so issue independent reads, searches, and checks together, calling alone only when the input depends on an earlier result.

Then, at any change size, consult reason before committing to the assessment approach: full or delta review, scope, and depth.

Author and seal

Copy the minimal bundle template outside the skill and target repository and fill it per the guidance's bundle fields; it has no default verdict. Prepare a new slug first; sealing accepts only its ignored .first-four-hours/assessments/<slug>/assessment.md and never replaces one. The agent decides currentness, depth, compliance, severity, findings, limitations, Diagnose need, and result; scripts verify only shape, exact Git/snapshot identity and freshness, locators, safe output, and integrity.

python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input slug=<slug> --format json prepare
python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input bundle=/absolute/assessment-bundle.json \
  --input output=<prepared output_path> --format json run

Result precedence: blocked when unavailable or contradictory authority/evidence/proof prevents a trustworthy result; else findings, reporting every independently material defect discovered in the bounded assessment; else clear. assessment.md holds only the compact result.

Complete

python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input output=<prepared output_path> --format json check

Report the sealed result, path, and each finding's severity, defect, and scenario as sealed, with no approval or readiness claim beyond it. When the result is findings and target is a pull request's URL, read publishing and offer to post them. Stop after one current assessment.md is sealed and checked and any offer is settled. End with one optional next step fitting this outcome: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.

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.