agentleFS
NagiliantNagiliant/Genesis-Legacy-V2/skills/genesis-resume/SKILL.md

Resume

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Reconstruct the exact pipeline position from disk, load the frontier spec in full, list failed approaches not to retry, and present the next action. Read-only, any time.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pause, report and 8 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.
  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 7 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 7 projects that use this

  • MicrosoftSkill

    config

    Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 4 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • GitHubSkill

    state-management

    CoreAI Sandbox's TanStack Query + mock-JSON data layer. USE WHEN: editing data-fetching hooks (`app/hooks/use*.ts`), adding mock data in `app/data/`, or wiring a component to query state.

    Also in 3 projects that use this

  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 2

    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:

    Read approval state: build a map of approved phases, complete groups, implemented specs.

    line 23
  2. Distinctive:

    Check for partial work at the frontier: implementation files present but no approval, uncommitted git changes, logged failed approaches.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 51 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

Resume — Pick Up Where I Left Off

The "I just got here — what's happening?" command. Reconstructs the pipeline position from disk, loads only the active group's state and the frontier (next) spec in full, lists failed approaches not to retry, and presents the next action. Read-only — never writes approval records.

Inputs

  • approvals/master.json + the one active group-{N}.json (max two approval files)
  • .genesis/project-state.md (active feature + mode)
  • units.json (lowfield)
  • tried.json (failed approaches), filtered to the frontier spec
  • The most recent journal entry under journal/ (for absence sizing)
  • git status (uncommitted work)

Process

  1. Determine the feature (argument, else the active feature from project-state.md; if several, ask).
  2. Read approval state: build a map of approved phases, complete groups, implemented specs.
  3. Find the frontier — the first unapproved item in pipeline order: master phases (brainstorm → feature → specify → clarify → northstar), then groups in order, within a group its specs in order, then per-group audits A1–A5, then the F-pass.
  4. Check for partial work at the frontier: implementation files present but no approval, uncommitted git changes, logged failed approaches.
  5. Load context efficiently: distilled summaries for completed groups/specs, full content only for the frontier spec.
  6. Present the tried log for the frontier spec ("Do NOT retry: {approach} — failed because {reason}").
  7. Compose an absence-aware briefing sized by time since the last journal entry (<4h brief, 4–24h one sentence, 1–7 days 3–5 sentences, 7+ days full), state the tier and why, then present the next action.

Output

RESUME: <feature>
Feature phase: <status> (<phases> approved)
Groups: N/total complete
Active group: N (<title>)   Active spec: <spec-id> (<title>)
Status: clean|partial — <detail>
Tried: N approaches logged (<summary>)
Next: <next pipeline action>

Mode differences

Brownfield adds a scope reminder (files in scope) and regression notes. Lowfield adds a unit-progress summary and the next unit action.

Natural language triggers

- "resume"
- "where did I leave off"
- "what's next"
- "catch me up"

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.