agentleFS
Cassandra-CollectiveCassandra-Collective/Ephesus/.claude/skills/goal/SKILL.md

goal

Skill2 starsChanged 3 months agoMITView on GitHub

Drive the current milestone's goal run end-to-end — resolve the milestone from the Resume here block of docs/PROGRESS.md (M9, not yet authorised to start, as of 2026-10-11), enforce the Architect's sole git authorship and a properly named feature branch before any commit, then loop the /build-package cycle through the milestone's packages and close with /milestone-review. Use when asked to run the milestone, start "the M<x> run", or invoked as /goal.

  • Commits and pushes

50 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use origin, update-cli-config and 10 more.

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.
  • 0mlkrizzz655335vSkill

    origin

    origin CLI 管理。安装、登录、更新、修复 origin.cursor.com 的 CLI。"disabled-environments:

    Also in 3 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 4 projects that use this

  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 3 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 4 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 4 projects that use this

  • MicrosoftSkill

    automate

    Propose an automation from a completed task or a new idea, then create it after approval. Use when the user asks to create an automation or wants scheduled local or cloud agent work.

    Also in 4 projects that use this

  • +1 more from 32103210
  • +3 more from 0mlkrizzz655335v

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    Sole authorship: Every commit in this repository is authored by the Architect and nobody else:

    line 15
  2. Very specific:

    Never add Co-Authored-By, session, or any identity-bearing trailer.

    line 23
  3. Distinctive:

    Never commit directly to main.

    line 55
  4. Very specific:

    When every package is ticked, run /milestone-review: exit criteria verified *by execution* (for M3: the UC-02 and UC-08 demos.

    line 84

“Common” is measured: kept by at least 6 in 10 of the 45 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

Run the current milestone goal

You are executing a full milestone run, not a single package. The contract for every step is BUILD-PROMPT.md; this skill only adds the run's session mechanics (identity, branching, sequencing). Where they seem to disagree, BUILD-PROMPT wins.

0. Session preconditions — before reading anything else

  1. Sole authorship. Every commit in this repository is authored by the Architect and nobody else:

    git config user.name "MERT EFE ŞENSOY"
    git config user.email "sensoymertefe@gmail.com"

    Never add Co-Authored-By, session, or any identity-bearing trailer; never put a model identifier in a commit message, file, or PR body. This is enforced three ways (ENGINEERING-STANDARDS §2): .githooks/ refuse the commit, CI's attribution job scans the whole history, and you verify yourself — run node scripts/check-attribution.cjs now and after every push. If hooks are unarmed (fresh clone that skipped npm install), run node scripts/arm-hooks.cjs.

  2. Green baseline. npm ci (or confirm node_modules is current), then npm run typecheck && npm run lint && node scripts/check-invariants.cjs must pass before you write a line. A red baseline is a blocker to report, not to absorb.

1. Resolve the milestone

Open docs/PROGRESS.md and read its Resume here block: it names the current milestone, its next package, and what waits on the Architect. If the block says the milestone's build is not yet authorised — M9 and every Phase 9 milestone, as of 2026-10-11 — ask the Architect through AskUserQuestion whether it may start, and stop there on anything but a yes. The milestone's goal doc is the handover once it may (docs/M9-GOAL.md for M9). Do not resolve the milestone from "the first unchecked box": deferred items and exits that wait on the Architect sit above the real next step. Read the milestone's package plan in full, including the Architect-verdict and carried-items paragraphs at its head: those decisions are already made — do not re-litigate them.

2. Branch policy — one package, one branch

  • Cut each work package's branch from up-to-date main, named feature/m<x>-<n>-<slug> after the package it carries (e.g. feature/m3-1-secret-broker, feature/m3-6-floor-layout-v2). Bug-fix-only branches use fix/<topic>.
  • Never commit directly to main; never reuse a branch whose work has merged; never rewrite history on a pushed branch.
  • One package per branch. Push with git push -u origin <branch>. Do not open a PR unless the Architect asks; when asked, the PR carries the package's evidence (BUILD-PROMPT §4 PROVE).
  • Merging to main is the Architect's call per package unless they have given a standing instruction for the run.

3. Execute the packages, in order

For each unchecked package, run the /build-package loop (READ → PLAN → BUILD → TEST → PROVE → COMMIT → REPORT) on that package's branch. Hard rules, restated because milestone runs tempt shortcuts:

  • npm run typecheck && npm run lint && node scripts/check-invariants.cjs && npm run test:coverage && node scripts/check-coverage.cjs green before every commit (BUILD-PROMPT §4's TEST line since M8.0). Never proceed on red; never weaken a test to pass it.
  • The package's owed tests (its Tests: line in PROGRESS.md) are part of the package, not a follow-up.
  • Tick the package in docs/PROGRESS.md with a one-line evidence note in the same commit series; log minor choices in docs/DECISIONS-LOG.md.
  • A must-ask (BUILD-PROMPT §8) stops the package: write the question with options + recommendation into the session report and move to the next independent package if one exists.
  • 3 genuinely different failed attempts on a blocker → stop, record, report.

4. Close the milestone

When every package is ticked, run /milestone-review: exit criteria verified by execution (for M3: the UC-02 and UC-08 demos; S-GATE, S-BREAKER, S-LEDGER, S-SECRETS green), PROGRESS verdict recorded, docs re-synced (/doc-sync if drift is suspected). A milestone with a red or unverified exit criterion is not closed.

5. End of every session

Finish with the BUILD-PROMPT §9 session report, and re-run node scripts/check-attribution.cjs — the run is not clean until it says so.

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.