agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/weekly-signals/SKILL.md

weekly-signals

Skill0 starsChanged 3 months agoMITView on GitHub

Use when /weekly-signals is invoked or during weekly review. Reads patterns.md and the week's daily notes, surfaces deferral patterns and flagged items, and outputs a paste-ready Accountability Signals block for the Weekly Review.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Don't: write to the Weekly Review automatically — output for Shane to paste manually.

    line 10
  2. Distinctive:

    If count > 0: "Your Inbox has N unprocessed items.

    line 15
  3. Distinctive:

    Read these files from the vault:

    line 18
  4. Distinctive:

    Follow Qwen Protocol with:

    line 22
  5. Distinctive:

    If Qwen is unavailable:

    line 31
  6. Distinctive:

    Read the following files via bash:

    line 35

≈ “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

Skill: /weekly-signals

Aggregate the week's accountability signals into a paste-ready block — deferral patterns, logging gaps, and OKR alignment — without auto-writing to vault.

Don't: write to the Weekly Review automatically — output for Shane to paste manually. Don't skip the inbox check — uncleaned inboxes skew the signal.

Steps

  1. Check inbox — count non-fixture files in Inbox/ (exclude: Inbox Processing.md, todo.md, Chores.md)
    • If count > 0: "Your Inbox has N unprocessed items. Run /inbox-process first, or continue with the weekly review?"
    • If count = 0: proceed
  2. Determine the current week's date range (Monday–Sunday, YYYY-MM-DD format)
  3. Read these files from the vault:
    • Context/patterns.md
    • Context/accountability.md
    • All Daily Notes/[date].md files for the current week (read each that exists)
  4. Follow Qwen Protocol with:
    • task: "You are Shane's weekly accountability analyst. Review this week's daily notes and patterns.md (provided). Surface: (1) tasks deferred 2+ times this week, (2) any PATTERN ALERT items, (3) logging gaps (days with no session log), (4) OKR alignment score — what % of logged work maps to the 3 active OKRs? Output a markdown block titled '## Accountability Signals' ready to paste into a Weekly Review note. Be honest, not cheerful."
    • skill: "weekly-signals"
    • context: content of all files concatenated
  5. Output Qwen's result to Shane — do NOT write to the Weekly Review automatically. Shane pastes it manually.
  6. Offer to explain any pattern or signal in more detail.

Fallback (if qwen unavailable)

If Qwen is unavailable:

  1. Check inbox — same as main step 1
  2. Determine the current week's Monday–Sunday date range (YYYY-MM-DD)
  3. Read the following files via bash:
    • obsidian read file="Context/patterns"
    • obsidian read file="Context/accountability"
    • obsidian read file="Daily Notes/[date]" for each date in the week that exists
  4. Aggregate signals:
    • Deferred 2+ times this week: count how many EOD Audits each task appeared in as deferred
    • PATTERN ALERTs: collect any PATTERN ALERT lines from the week's EOD Audits
    • Logging gaps: note any days where the session log was empty or missing
    • OKR alignment: for each day's session log, classify each logged item as OKR-aligned or not; compute a rough percentage
  5. Output the following block to Shane (do NOT write to vault — Shane pastes manually):
    ## Accountability Signals — Week of [Monday date]
    
    **Deferred 2+ times:**
    - [task] — deferred [N] times
    
    **Pattern Alerts:**
    - [PATTERN ALERT items from patterns.md with 3+ deferrals]
    
    **Logging Gaps:** [days with no session log, or "none"]
    
    **OKR Alignment:** ~[N]% of logged work mapped to active OKRs
    - Aligned: [examples]
    - Off-OKR: [examples]
  6. Offer to explain any signal in more detail

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.