agentleFS
Sign inStart free
ychampionychampion/ystack/skills/weekly/SKILL.md

weekly

Skill4 starsChanged 2 days agoMITView on GitHub

Weekly founder review. Measures the week from evidence (conversations, pilots, payments, what shipped for whom) and from the founder's agent prompt history (building vs tooling vs customer time), applies commit / sharpen / kill to each idea, and sets next week's single bottleneck. Use once a week (Monday), or when the user asks "how are we doing", "what should I focus on" or for a weekly review.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, decide and 3 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.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 4 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 6 projects that use this

  • SentrySkill

    onboard

    Onboard a service to sentry-options. Use when integrating a new service, creating schemas, or setting up the multi-repo sentry-options workflow.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 1

    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:

    Default decision rule: commit when at least 3 target users show strong pull (a pilot, real data or access, payment, a letter of intent).

    line 34
  2. Very specific:

    Read bottleneck.md, ideas.md and every file in evidence/.

    line 39
  3. Very specific:

    Per idea: commit / sharpen / keep testing / kill, by the decision rule, with the reason.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 15 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

/weekly: one honest page about the week

The founder hub

This skill reads and writes a founder hub: one folder holding the startup's truth.

  • Location: the FOUNDER_HUB environment variable, default ~/founder. Below, <hub> means that folder.
  • Files this skill uses:
FileWhat it holds
<hub>/README.mdThe decision rule and evidence rules. If missing, use the defaults below
<hub>/bottleneck.mdThe current bet, this week's single bottleneck, the goal and its deadline. This skill rewrites it
<hub>/ideas.mdA table of candidate ideas: one line, who pays, evidence so far, status
<hub>/evidence/One or more files per idea: conversation logs, prospects, pipeline, payments, metrics
<hub>/weekly/<YYYY-MM-DD>.mdThe weekly reviews this skill writes

If the hub or a file is missing, say so and offer to create the minimal structure: the folder, README.md with the rules below, an empty bottleneck.md (current bet, bottleneck, goal, deadline), ideas.md with a table header (idea, one line, who pays, evidence so far, status), and empty evidence/ and weekly/. An empty hub still gets a review: it says the week produced no evidence. Never fail silently.

Default decision rule: commit when at least 3 target users show strong pull (a pilot, real data or access, payment, a letter of intent); sharpen when the pain is real but the framing or buyer is wrong; kill after about 15 targeted conversations with no strong pull. Compliments and "interesting" don't count. Default evidence rule: only what real people said or did, dated and sourced.

Read bottleneck.md, ideas.md and every file in evidence/.

1. Measure the week's attention from prompt history (optional)

python <this skill's folder>/scripts/attention.py 7

It reads Claude Code's ~/.claude/history.jsonl and Codex's ~/.codex/history.jsonl if they exist (pass other history files as extra arguments) and prints a keyword-based split: customer/selling, fundraising, tooling/meta, fixing, building/other, plus the projects touched (Claude Code only). It's a heuristic, about 80% accurate; report it as a rough split. If no history is found, or the harness keeps none, skip this section and say so.

2. Write weekly/<YYYY-MM-DD>.md

  • Evidence this week: conversations held; new strong-pull signals (pilot, data access, payment, letter of intent); sign-ups and usage; revenue. Numbers and names, from the evidence files only.
  • Shipped: what shipped, and for which named user. Work that shipped with no user attached is listed separately.
  • Attention: the prompt-history split and the projects touched. Call out tooling/meta above about 15%, and any new project started.
  • Per idea: commit / sharpen / keep testing / kill, by the decision rule, with the reason. Update ideas.md.
  • Next week's single bottleneck: one sentence, plus 3 concrete actions and what "done" looks like.

3. Update bottleneck.md

Rewrite it to match: current bet, the new bottleneck, goal, deadline. Keep any scope note the founder wrote there (for example which projects the hub does not govern). Then show the user the page, briefly. Be direct and specific. Don't cushion a zero.

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