SkillAgentSearch skills...

wids-pick-leader

Pick next reading_group leader via longest-gap algorithm with random tie-break; operator confirms

Install / Use

npx skills add mrojas54/wids-nyc-reading-group-assistant

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

63/100

Supported Platforms

Claude Code

Tags

Our assessment of wids-pick-leader

wids-pick-leader scores 63/100 on our quality scale, 3972nd of 4,589 Development & Engineering skills we index.

Its Claude Commands is 3.6 KB long, well organised into 9 sections with 6 code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
0/20
Freshness
5/15

Maintenance, license and trust

  • We could not determine when the repository was last updated.
  • Our last check on 2026-09-02 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

wids-pick-leader compared with similar skills

All 4 of these similar skills score higher than wids-pick-leader; compare them before choosing.

SkillScoreStarsUpdatedFormat
wids-pick-leader (this skill)by mrojas54630—Claude Commands
claude-memby thedotmack10098.9ktodayCLAUDE.md
Agent-Reachby Panniantong10094.6k1d agoCLAUDE.md
Understand-Anythingby Egonex-AI10085.7ktodayCLAUDE.md
headroomby headroomlabs-ai10074.8ktodayCLAUDE.md

Frequently asked questions

How do I install wids-pick-leader?
Run npx skills add mrojas54/wids-nyc-reading-group-assistant. The install tabs above show the steps for each supported agent.
Which AI agents does wids-pick-leader work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is wids-pick-leader safe to use?
It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is wids-pick-leader still maintained?
We could not determine when the repository was last updated.

description: Pick next reading_group leader via longest-gap algorithm with random tie-break; operator confirms argument-hint: [pick <member_id>]

/wids-pick-leader [pick <member_id>]

Two phases: present pick → confirm or override.

Step 1 — Find the upcoming reading_group

-- planned_by_admin_id IS NOT NULL excludes member-proposed placeholders
-- from proposePaper: those are also type='reading_group' status='prep'
-- with leader_id NULL, so without this filter a newer placeholder would
-- win ORDER BY created_at and step 6 would stamp a leader onto it.
SELECT id FROM meetings
WHERE type='reading_group' AND status='prep' AND leader_id IS NULL
  AND planned_by_admin_id IS NOT NULL
ORDER BY created_at DESC LIMIT 1;

If no row: halt: "No reading_group needing a leader. Run /wids-meeting-start admin first."

Step 2 — Run longest-gap algorithm

WITH last_led AS (
  SELECT m.leader_id AS member_id,
         MAX(m.scheduled_at) AS last_led_at
  FROM meetings m
  WHERE m.type='reading_group' AND m.status='done' AND m.leader_id IS NOT NULL
  GROUP BY m.leader_id
),
eligible AS (
  SELECT v.member_id,
         mem.name,
         COALESCE(ll.last_led_at, '1970-01-01'::timestamptz) AS last_led_at
  FROM volunteers v
  JOIN members mem ON mem.id = v.member_id AND mem.active = true
  LEFT JOIN last_led ll ON ll.member_id = v.member_id
  WHERE v.meeting_id = <rg_id>
),
ranked AS (
  SELECT member_id, name, last_led_at,
         RANK() OVER (ORDER BY last_led_at ASC) AS rnk
  FROM eligible
)
SELECT member_id, name, last_led_at, rnk FROM ranked ORDER BY rnk, random();

If empty: halt: "No volunteers for this reading group. Either send the form again or assign manually."

Step 3 — Pick the winner

The first row of the ranked result (rnk=1) is the algorithmic winner. If multiple rows have rnk=1 (ties), the ORDER BY random() already gave one specific tie-broken winner.

Step 4 — Argument handling

If invoked as /wids-pick-leader pick <id>: that's a direct override. Skip presentation, go to step 6 with that member_id.

Otherwise (no args): proceed to step 5 (present + confirm).

Step 5 — Present pick with reasoning

Recommended leader: <winner.name> (member_id=<winner.member_id>)
Reason:
  - <"Never led" if last_led_at = 1970-01-01 else "Last led on <date> (<X> months ago)">
  - <"Tied with: <other tied names>; randomly picked from ties" if applicable>

Other eligible volunteers:
  <for each row with rnk > 1: name (id=<id>) — last led <date or "never">>

Reply:
  'confirm'                — lock in <winner.name>
  'pick <member_id>'       — override with someone else
  'skip'                   — abort

Wait for response.

Step 6 — On confirm or pick: update DB and announce

UPDATE meetings SET leader_id = <chosen_id> WHERE id = <rg_id>;

Generate the announcement text:

🎉 The next reading group will be led by <chosen_name>!

Date: <rg.scheduled_at if known else "TBD — see admin meeting outcome">
Paper: <papers.title if known else "TBD — leader will pick">

@<chosen_name> — when you're ready, run `/wids-find-paper` to start
hunting for a paper, then `/wids-make-guide` ~2 weeks before the meeting.

Output: "WhatsApp announcement (copy and paste into the group chat):\n\n<announcement>"

Step 7 — Audit log

INSERT INTO command_log (source, name, status, summary)
VALUES ('slash_command', '/wids-pick-leader', 'success',
        'Picked leader=<chosen_id> for reading_group=<rg_id>; <action>');
-- action = 'algorithm pick confirmed' or 'override to <name>'

Failure handling

  • No volunteers → halt as above.
  • DB update fails → log failure, no announcement.

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
UpdatedNaNy ago
Forks0

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low