agentleFS
Sign inStart free
L2-ootmL2-ootm/L2-ATLAS-PROJECT/skills/atlas/gsd/SKILL.md

gsd

Skill2 starsChanged 5 months agoMITView on GitHub

The L2 Systems execution doctrine, native to ATLAS. A ground-up rebrand and refit of the GSD ("Get Stuff Done") framework for the ATLAS structure: missions instead of orchestrator scripts, durable actors instead of ad-hoc subagents, the audit ledger instead of trust, and the LLM Wiki instead of loose learning notes. The doctrine in one line: verified progress over apparent progress — every goal becomes a bounded slice, every slice ends delivered or honestly blocked, never "should work". Based on where…

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. jigripokri/POHA★ 121same name
    2. 354685856-sn/claude-code-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    When ambiguous: Read .planning/STATE.md to see current phase, or ask the operator.

    line 28
  2. Distinctive:

    Read state before editing.

    line 49
  3. Distinctive:

    Stop and surface: destructive actions, secrets, goal drift, or the same failure twice with no new information.

    line 54

≈ “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

GSD/L2 — Goal · Slice · Deliver

The L2 Systems execution doctrine, native to ATLAS. A ground-up rebrand and refit of the GSD ("Get Stuff Done") framework for the ATLAS structure: missions instead of orchestrator scripts, durable actors instead of ad-hoc subagents, the audit ledger instead of trust, and the LLM Wiki instead of loose learning notes.

The doctrine in one line: verified progress over apparent progress — every goal becomes a bounded slice, every slice ends delivered or honestly blocked, never "should work".

Mode Router

Based on where you are in the execution loop, route to the appropriate step:

Intent SignalStepFileProduces
"bootstrap", "new project", "init"Bootstrapinit.md.planning/ contract: PROJECT.md, ROADMAP.md, STATE.md
"discuss", "context", "scope"Contextdiscuss.mdPhase CONTEXT.md — decisions locked before planning
"plan", "spec", "tasks"Planplan.mdPLAN.md — tasks with done-conditions, goal-backward checked
"build", "implement", "execute"Buildexecute.mdAtomic commits + SUMMARY.md, deviations recorded
"verify", "test", "prove"Proveverify.mdVERIFICATION.md — evidence-tiered, UAT owed listed
"ship", "close", "merge"Closeship.mdMilestone audit, handoff, wiki filing
"status", "progress", "where"Anytimeprogress.mdSituational report + route to the next step
"debug", "fix", "broken"On failuredebug.mdRoot cause with proof before any fix

When ambiguous: Read .planning/STATE.md to see current phase, or ask the operator.

The Loop

GOAL ──► DISCUSS ──► PLAN ──► EXECUTE ──► VERIFY ──► SHIP
  ▲          │          │         │           │        │
  └──────────┴──────────┴─── PROGRESS (route anytime) ─┘
                              DEBUG (on any failure)

How to Invoke

  • Any surface: /gsd (progress + routing), /gsd-init, /gsd-discuss, /gsd-plan, /gsd-execute, /gsd-verify, /gsd-debug, /gsd-ship — contributed by the gsd module (atlas module sync once per checkout).
  • Any runtime: the skills are plain markdown; native ATLAS, Claude Code, or Codex follow them by reading the file. No harness-specific machinery.

Rules That Outrank Convenience

  1. Read state before editing; the repo is the memory, not the conversation.
  2. One slice at a time, smallest coherent scope, deferred work written down.
  3. Atomic commits; a commit that mixes concerns is a defect.
  4. Claims carry evidence or the label "not verified".
  5. Failures are reported with the output, never smoothed over.
  6. Stop and surface: destructive actions, secrets, goal drift, or the same failure twice with no new information.

ATLAS-Native Mapping

Upstream GSD conceptGSD/L2 on ATLAS
Orchestrator + subagent fleetATLAS mission (judged long-horizon loop) + durable actors (atlas_actor spawn/status/wait)
Slash commands in one CLI/gsd-* module commands on every surface (WebUI palette, Chat composer, terminal) via modules/gsd
"Tests pass" claimsEvidence tiers: registered → configured → reachable → verified-live, with audit run ids as citations
Learnings markdownLLM Wiki filing with provenance (when running inside ATLAS)
Session handoffskills/atlas/handoff.md (pack-level, shared)
.planning/ contractUnchanged — GSD/L2 is drop-in compatible with existing GSD planning directories

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.

Check your setup, free