agentleFS
ashley-eyekyamashley-eyekyam/probematrix-learnings-coach/skills/site-leadership-coach/SKILL.md

site-leadership-coach

Skill0 starsChanged 29 days agoMITView on GitHub

Produce learning for site and asset leadership from a ProbeMatrix investigation export - plant manager, head of operations, site leadership team - on the decisions, trade-offs, resourcing, authority and culture signals that shaped the event, with the decisions leadership must now take and what leaders should visibly model. Use when someone asks what plant or site leaders should learn, for a leadership-team debrief, a site leadership workshop, a management review after an incident, or "what does the plant manager need to decide".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write the pack <run>/outputs/site-leadership-coach.json (schema: learnings-coach/references/pack-schema.md), then:

    line 33

≈ “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

Site Leadership Coach

Audience: T4 plant / asset leadership. They set site priorities, allocate budgets and people, delegate authority and, by what they tolerate, set the norms.

Engine: PMLC = python3 <skills-root>/learnings-coach/scripts/pmlc.py (this skill needs the learnings-coach skill installed alongside it). Read learnings-coach/references/learning-principles.md.

Gather

PMLC select <ws> --tier T4 --brief
PMLC select <ws> --level 4 --top-rated
PMLC select <ws> --relation norm_setter learner absent challenger
PMLC causal <ws> --top 40          # organisational hubs
PMLC timeline <ws> --before incident

Write

  1. Bottom line for the leadership team: five learnings, each one sentence.
  2. How the site set this up: the organisational hubs from the causal map (L4 factors with the most downstream links), told as two or three pathways from leadership conditions to the event. Evidence trail on each step.
  3. Signals that reached leadership level (from the timeline) and what happened to them.
  4. Culture signals: what the organisation had come to treat as normal, what leaders modelled or tolerated, where challenge was absent. Describe norms, not people.
  5. Decisions for the leadership team: six to ten decisions, each framed as a choice with its trade-off (cost, production, staffing, authority), the learning it answers, and the leading indicator leadership will watch. Include delegation-of-authority questions if the findings show escalation delays.
  6. What leaders will do visibly in the next 30 days: walk-throughs, questions to ask in reviews, things to stop accepting.

Output

Write the pack <run>/outputs/site-leadership-coach.json (schema: learnings-coach/references/pack-schema.md), then:

PMLC check-pack <ws> <run>/outputs/site-leadership-coach.json   # fix every problem it lists
PMLC pack <ws> <run>/outputs/site-leadership-coach.json         # -> site-leadership-coach.html (primary) and .md

Sections → kinds:

  1. The pack's bottom_line: five entries.
  2. A graph from PMLC causal-item <ws> --top 20. Paste it unchanged; drop nodes only if you need to. Follow it with one para per pathway, with group = the pathway's name.
  3. A timeline, with signal, received_by and response on each event.
  4. para.
  5. decision ×6–10 (options, trade_offs, owner). Follow each one with the indicator leadership will watch, in the same group.
  6. check items, with when = "next 30 days".

Close with a workshop section: one table with columns Time, Activity and Built on, for a two-hour agenda built on sections 2, 4 and 5.

Set "scope": {"tiers": ["T4"]}. Put data-quality corrections in data_quality, findings left out on purpose in exclusions, and same-condition findings in supporting_cites. Owner wording: owner is the function that owns the change, not who "was involved" (learning-principles.md).

{"kind": "decision", "group": "Spares specification", "decision": "Require a specification for every critical-spares order",
 "options": ["…", "…"], "trade_offs": "…", "owner": "Site operations function", "cites": ["FND-…"]}

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.