agentleFS
Sign inStart free
iwesysiwesys/IWE/.claude/skills/personal-guide-render/SKILL.md

personal-guide-render

Skill0 starsChanged 24 days agoMITView on GitHub

The personal guide is assembled automatically on the platform server

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the file is not found → notify the pilot:

    line 59
  2. Distinctive:

    Stop (do not proceed to Step 1).

    line 64

≈ “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

Personal Guide: How It Is Assembled

Current State (2026-07-29)

Guide assembly is a cloud capability of the Platform: it reads the pilot's data from the Platform databases, calls an LLM using the Platform API key, and publishes the result to the guide's GitHub Repository. All of this happens on the platform server automatically on a schedule — a new lesson appears every morning, and the full set is rebuilt every Monday.

Manual rebuild from chat ("rebuild now") is not yet available: the server-side MCP tool for this has not been published yet. When it is released, this Skill will call it directly — watch for Template updates.

When to use

The pilot asks to "rebuild the guide", "update my plan", or "assemble today's guide" — or asks why today's guide is missing.

Algorithm

Step 0. Check the precondition (setup complete)

Call personal_search(source: "DS-personal-guide", path: "README.md").

HD #503: previously this step checked the platform path .claude/skills/... — that path lives in the Template (layer L1) and is never copied to the user Repository DS-personal-guide, so the check always returned empty and blocked all subsequent steps. The real indicator of a completed bootstrap is README.md: bootstrap itself creates it when the Repository is initialized (notes structure Gateway: inbox/, docs/, README.md), meaning it exists BEFORE the first render.

If the file is not found → notify the pilot:

Skills are not installed or installation is not complete.
Run /personal-guide-start for initial setup.

Stop (do not proceed to Step 1).

Step 1. Determine the date

date = the Skill argument if provided (format YYYY-MM-DD), otherwise today.

Determine the ISO week of the selected date in the format YYYY-Www, using the ISO week year (which may differ from the calendar year around New Year).

Step 2. Check whether the guide has been delivered

Check the pilot's DS-personal-guide Repository for the presence of guide/<ISO-week>.md (weekly material), guide/<date>.md (daily material), and panel/<date>.md (dashboard). The first two paths are candidates for different modes: do not require both to be present and do not determine the mode by day of the week alone.

If guide.json is available, explicitly compare the paths listed in sections.weekly and days against the selected period. Confirm the mode only when there is an explicit reference to the corresponding material; otherwise, indicate that the mode is not confirmed. A table of contents is not a completeness indicator: do not require non-existent fields mode, complete, or a dashboard reference.

Report the result separately for each checked path:

Files checked for <date>:
<learning material path> — found / not found.
panel/<date>.md — found / not found.
Mode: weekly / daily (confirmed by table of contents) / not confirmed.

The presence of files confirms their availability, but does not confirm a new successful generator run or that the content is current. Do not declare the set complete based on a single file or a single table of contents.

If no learning material is found for the selected period, or the dashboard is missing:

The guide is assembled on the platform server automatically (every morning on a schedule).
Manual rebuild from chat is not yet available — the server-side tool is in development.
If the guide is missing by midday — contact platform support.
<!-- USER-SPACE --><!-- /USER-SPACE -->

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