agentleFS
david-vrbadavid-vrba/claude-power-skills/skills/heavy/SKILL.md

heavy

Skill4 starsChanged 5 months agoMITView on GitHub

Launch a pre-engineered "heavy prompt" from your local library in the current interactive session — big self-contained research/build/optimize jobs that write line-addressable structured output. /heavy lists the library; /heavy NN launches or resumes run NN.

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 3 are distinctive, and 12 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 12

    Very specific

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

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

    No argument: read heavy/library/INDEX.md, print the catalog (ID, Title, Goal, Cost), and ask the user which to run (this is the ONLY place …

    line 26
  2. Distinctive:

    If none matches, list the catalog and stop.

    line 35
  3. Very specific:

    Read its frontmatter: id, output_dir, phases, subagents, websearch_max, est_cost.

    line 36
  4. Very specific:

    If subagents: false (the default), you MUST do all work yourself in this session — do not spawn the Agent tool or any sub-workflow.

    line 37
  5. Very specific:

    Run folder is the prompt's output_dir (e.g.

    line 42
  6. Very specific:

    Read it, note completed_steps and current_step, append a resume event to heavy/state/runs.ndjson, and continue execution skipping completed …

    line 44
  7. Very specific:

    Else (new run): create output_dir, write the initial STATUS.json:

    line 47
  8. Very specific:

    Create 00-summary.md with the opening `yaml block (status: in_progress), append a launch event to heavy/state/runs.ndjson, add an …

    line 61
  9. Distinctive:

    Follow the prompt body's PHASES/STEPS in order.

    line 72
  10. Very specific:

    Commit after: add the step id to completed_steps, set last_commit, then git add heavy/ && git commit -m "heavy(NN): <step id>" (scoped — …

    line 79
  11. Very specific:

    Never: use AskUserQuestion. When a decision is unclear, take the documented default and record it under <!-- SEC:assumptions --> in …

    line 85
  12. Very specific:

    Run /compact at ~70% context.

    line 89
  13. Distinctive:

    When the prompt's DONE criteria are met:

    line 94
  14. Very specific:

    Update the run's row in heavy/output/INDEX.md to done with a one-line summary + folder link.

    line 97
  15. Very specific:

    All run state lives under the run folder (STATUS.json) and heavy/state/ — there is no other state store to keep in sync.

    line 107

≈ “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

Heavy-prompt launcher

Runs one big self-contained prompt from your heavy/library/ in this interactive session (so it uses your interactive subscription, not metered/headless API billing). A heavy prompt is meant to be launched and left — so once a prompt is running, do not stop to ask the user anything.

The library, outputs, and conventions live in your project repo under heavy/ (you can also keep it at ~/.claude/heavy/). Read heavy/README.md once for the full model. Paths below are relative to your repo root (the current working directory):

  • heavy/library/ — the heavy prompts (NN-slug.md) + INDEX.md + _TEMPLATE.md
  • heavy/output/ — one run folder per launch, plus output/INDEX.md
  • heavy/state/runs.ndjson — append-only event log of launches/resumes/completions

The argument $ARGUMENTS is the heavy-prompt number NN (may be empty).


Step 1 — Route on the argument

  • No argument: read heavy/library/INDEX.md, print the catalog (ID, Title, Goal, Cost), and ask the user which to run (this is the ONLY place a question is allowed — the human is present at launch). Then stop and wait. Do not auto-pick.
  • NN given: proceed unattended through the steps below and never use AskUserQuestion again for the rest of the run.

Step 2 — Load the prompt

  • Resolve the library file: heavy/library/NN-*.md (the file whose stem starts with NN-). If none matches, list the catalog and stop.
  • Read its frontmatter: id, output_dir, phases, subagents, websearch_max, est_cost.
  • If subagents: false (the default), you MUST do all work yourself in this session — do not spawn the Agent tool or any sub-workflow.

Step 3 — Resolve the run folder (resume or init)

  • Run folder is the prompt's output_dir (e.g. heavy/output/01-some-study/).
  • If output_dir/STATUS.json exists and status == "in_progress": this is a RESUME. Read it, note completed_steps and current_step, append a resume event to heavy/state/runs.ndjson, and continue execution skipping completed steps. Reuse this same folder — never create a new dated one.
  • Else (new run): create output_dir, write the initial STATUS.json:

    {
      "prompt_id": "NN-slug",
      "started": "<ISO8601>",
      "phases": [...from frontmatter...],
      "current_phase_index": 0,
      "current_step": null,
      "completed_steps": [],
      "last_commit": null,
      "lock": {"started": "<ISO8601>"},
      "status": "in_progress"
    }

    Create 00-summary.md with the opening yaml block (status: in_progress), append a launch event to heavy/state/runs.ndjson, add an in_progress row to heavy/output/INDEX.md, then git add heavy/ && git commit (the commit is the first checkpoint). (Get the timestamp from date -u +%Y-%m-%dT%H:%M:%SZ — do not invent times.)

    Never git add -A — other concurrent work may have unrelated uncommitted changes, and -A would sweep them into the heavy commit. Everything a run writes lives under heavy/, so git add heavy/ is the correct, complete, scoped stage.

Step 4 — Execute the phases

Follow the prompt body's PHASES/STEPS in order. For each step:

  1. Advance before work: set current_step and (if entering a new phase) bump current_phase_index in STATUS.json.
  2. Do the step, writing output as anchored, append-only sections (<!-- SEC:id --> … <!-- /SEC:id -->) into the prompt's specified files. Never rewrite a completed earlier section; only append new ones (re-running a partial step may rewrite that step's own anchored block).
  3. Commit after: add the step id to completed_steps, set last_commit, then git add heavy/ && git commit -m "heavy(NN): <step id>" (scoped — never -A). This is the durable checkpoint.
  4. At the end of each phase, regenerate MAP.md (table: | id | title | file | lines | ~tokens | one-liner |) and append a phase_done event to heavy/state/runs.ndjson.

Discipline while running:

  • Never use AskUserQuestion. When a decision is unclear, take the documented default and record it under <!-- SEC:assumptions --> in 00-summary.md.
  • WebSearch ≤ websearch_max for the whole run.
  • Respect the prompt's GUARDRAILS (security, low-risk-edits-only, verify external facts).
  • Run /compact at ~70% context. If the session is cut off, the next /heavy NN resumes from STATUS.json.

Step 5 — Finish cleanly

When the prompt's DONE criteria are met:

  • Finalize 00-summary.md (set yaml status: done), regenerate MAP.md.
  • Set STATUS.json status: "done", clear lock.
  • Update the run's row in heavy/output/INDEX.md to done with a one-line summary + folder link.
  • Append a done event to heavy/state/runs.ndjson.
  • Final git add heavy/ && git commit -m "heavy(NN): done" (scoped — never -A).
  • Print a short banner: prompt id, status, output folder, top findings, how many commits.
  • Stop. A heavy run is one bounded job — do not loop or relaunch.

Notes

  • This is launched in an interactive session on purpose (your interactive subscription, not metered API billing). It is human-launched every time — do not schedule it to fake a human.
  • All run state lives under the run folder (STATUS.json) and heavy/state/ — there is no other state store to keep in sync.

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.