agentleFS
ashley-eyekyamashley-eyekyam/probematrix-learnings-coach/skills/top-management-brief/SKILL.md

top-management-brief

Skill0 starsChanged 29 days agoMITView on GitHub

Produce a top-management brief from a ProbeMatrix investigation export for the CEO, executive committee, corporate HSE and corporate function heads - which learnings transfer across sites and the enterprise, which corporate policies, standards and investments they implicate, and what to decide at enterprise level. Use when someone asks for an ExCo or CEO brief, an enterprise-wide lessons note, cross-site learning, corporate standards review after an incident, or "what does head office need to do".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    Use the Learnings Register if one exists.

    line 20
  2. Very specific:

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

    line 32

≈ “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

Top Management Brief

Audience: T5 corporate leadership. They set policy, enterprise standards and investment, and they decide whether a lesson from one site is applied at every site.

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 T5 --brief
PMLC select <ws> --level 4 --top-rated
PMLC select <ws> --tag people corporate assurance --level 4 --brief   # people, corporate, assurance

Use the Learnings Register if one exists; otherwise identify the L4 learnings directly.

Write (four pages at most)

  1. Executive summary (half a page): what happened, in two sentences; the three enterprise-level learnings; the decisions requested.
  2. Transferability: for each L4 learning, would the same condition plausibly exist at other sites? Classify as site-specific / likely at similar sites / enterprise-wide, with the reason (shared standard, shared system, shared culture, shared vintage of equipment).
  3. Policies and standards implicated: which corporate policies, standards or programmes (change management, spares and sourcing, maintenance strategy, emergency planning, competence, audit) the findings touch, and what the evidence shows about their implementation.
  4. Decisions for top management: four to six, each with options, trade-off, and the enterprise indicator that would show progress (e.g. "% of sites with verified emergency-isolation authority").
  5. Assurance: how the organisation will know the learning has been applied across sites (link to auditor-assurance-pack).

Output

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

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

Sections → kinds:

  1. para, with the four HFACS levels defined once. The three enterprise learnings go in bottom_line.
  2. table with columns Learning, Transferability (site-specific, likely at similar sites, or enterprise-wide) and Reason, plus row_cites.
  3. para, with group = the policy or standard.
  4. decision ×4–6. Follow each one with its enterprise indicator, in the same group.
  5. question, with to = the role asked.

Set "scope": {"levels": [4], "min_rating": "top"}. Put data-quality corrections in data_quality, findings left out on purpose in exclusions, and same-condition findings in supporting_cites. Use board-ready language. Neutral, factual tone; no blame of management or staff; roles only. Name the function that owns the change, not the post (see owner wording in learning-principles.md).

{"kind": "table", "columns": ["Learning", "Transferability", "Reason"],
 "rows": [["…", "Likely at similar sites", "…"]], "row_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.