agentleFS
anh-chuanh-chu/llm-wiki-pm/skills/llm-wiki-maintain/SKILL.md

llm-wiki-maintain

Skill7 starsChanged 9 days agoMITView on GitHub

Orchestrates the recurring daily-maintenance loop for the PM wiki — registry-driven multi-source sweep, ingest, daily or weekly brief, brief rotation, and a health check — with explicit interactive-vs-autonomous mode handling.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. gavishap/omnia-vault★ 53same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Suppress interactive prompts: Do not ask "want me to add this?" or wait on confirmations.

    line 32
  2. Distinctive:

    Stay within safe bounds: Never delete or supersede without a human.

    line 38
  3. Distinctive:

    If you can't tell which mode you're in, ask once ("interactive or autonomous run?") and proceed on the answer.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

LLM Wiki Maintain

The recurring maintenance loop, as one defined operation. "Every day: sweep all sources → ingest what's new → produce a brief → keep the wiki tidy" was previously improvised step-by-step on faith; this skill makes the order, the brief lifecycle, and the autonomous-mode behavior explicit.

This skill orchestrates — it does not reimplement. The actual work is done by the core llm-wiki-pm skill (orient, ingest, lint) and llm-wiki-brief (brief generation). Route to them at each step. If a sub-skill isn't installed, fall back to the core skill's matching operation.

Mode: interactive vs autonomous (decide first)

The skill's proactive behaviors (ambient "want me to add that?", per-step confirmations, post-task offers) assume a human is watching. In a scheduled or autonomous run nobody answers them — they stall or force a guess. So classify the run before doing anything:

  • Interactive — a human invoked this in a live chat. Act on the clear cases as in autonomous mode (core Maintain by default), then report; ask only for its ask-first cases, such as mass updates (10+ pages).
  • Autonomous — a scheduled/cron/loop run with no human in the loop (no one to answer a prompt). Then:
    • Suppress interactive prompts. Do not ask "want me to add this?" or wait on confirmations. Act on the clear cases.
    • Act-then-report, never block. Anything that would need a human decision (a risky mass update, an ambiguous create-vs-update, a possible contradiction) goes into a Needs Review queue in the brief instead of halting the run.
    • Stay within safe bounds. Never delete or supersede without a human; queue those. Snapshot before any overwrite (core rule still applies).

If you can't tell which mode you're in, ask once ("interactive or autonomous run?") and proceed on the answer; default to interactive.

The loop (ordered)

① Orient. Run the core Pre-Flight + orient (SCHEMA, index, log, overview, _status.md). Do not skip — every write still requires orient.

② Registry-driven sweep. Read the ## Sweep Registry in $WIKI/MY-INTEGRATIONS.md and sweep every source listed, under the core Source-completeness guard (≥2 varied queries, classify hits/empty-after-retries/failed, bound output — concise/limit≤15/narrow scope first). One batch sweep up front satisfies freshness-first for the whole run (see the Freshness↔batch rule); do NOT re-sweep per page. If no registry exists, build it from connected tools + Active Sources, confirm (interactive) or queue for review (autonomous), and write it before sweeping.

③ Ingest findings. For each new/changed signal, route to the core ingest flow (capture raw → thresholds → write/update → backlinks → log → MY-INTEGRATIONS). Pages are private by default; never mark a digest shareable. Stamp lifecycle: stub-intentional on by-design thin stubs.

④ Brief. Pick the cadence from the request or the schedule. Interactive: ask if it is unclear. Autonomous: use the run's declared cadence, default daily.

  • Daily: route to llm-wiki-brief (daily brief). If filing it as a page, write briefings/YYYY-MM-DD.md with lifecycle: dated-digest (keeps it out of the orphan count).
  • Weekly: route to llm-wiki-brief (weekly brief). If filing it as a page, write queries/weekly-brief-YYYY-MM-DD.md and link it from index.md. Never file a weekly brief under briefings/.

Either brief MUST include the Source Coverage ledger (one row per registered source) and, in autonomous mode, a Needs Review section.

⑤ Brief rotation. Daily briefs only: keep the last 7 days in briefings/; move older briefs to _archive/briefings/. Use git mv if the file is tracked, plain mv if not (check first — don't let an untracked file abort the run).

⑥ Health check. Run scripts/lint.py $WIKI. Surface the tiered summary, the export-surface (shareable) audit, and any new orphans/broken links. Optionally lint.py $WIKI --auto-fix to backfill+sort the index (interactive: offer it; autonomous: run it — it's non-destructive).

⑦ Report. One consolidated summary: sweep coverage ledger, pages created/updated, brief link, lint health delta, and the Needs Review queue.

Brief lifecycle convention

  • briefings/YYYY-MM-DD.md — current briefs, lifecycle: dated-digest.
  • _archive/briefings/ — daily briefs older than 7 days.
  • queries/weekly-brief-YYYY-MM-DD.md — weekly briefs, kept as query pages and never rotated.
  • Briefs are orphans by design; the dated-digest flag keeps them out of lint's orphan count. Never link-spam pages just to de-orphan a brief.

What this skill does NOT do

Single ingests, ad-hoc queries, updates, research work — route to the core skill or the matching sub-skill. This skill is the recurring daily or weekly loop only.

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.