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

board-brief

Skill0 starsChanged 28 days agoMITView on GitHub

Produce a board-level briefing from a ProbeMatrix investigation export for directors and the board safety or risk committee - what the investigation reveals about governance, risk oversight and assurance, the questions directors should ask management, and what good assurance evidence would look like. Use when someone asks for a board paper, board safety committee briefing, directors' brief, governance lessons, oversight questions or "what should the board ask" after an incident.

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:

    Look specifically for: audit recommendations left open, internal audits that did not detect conditions, indicators that looked green while …

    line 21
  2. Very specific:

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

    line 33

≈ “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

Board Brief

Audience: the board and its safety / risk committee. Directors do not manage the site; they oversee whether management's systems work and whether the assurance they receive is true. Their learning is about oversight and assurance, not operations.

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 and the board question block in output-style.md.

Gather

PMLC profile <ws>
PMLC select <ws> --level 4 --top-rated --brief
PMLC select <ws> --tag assurance --level 3 4 --brief        # audit and assurance findings
PMLC timeline <ws> --before incident                 # signals that existed before the event

Look specifically for: audit recommendations left open, internal audits that did not detect conditions, indicators that looked green while conditions degraded, risk acceptance without documented authority.

Write (two to three pages)

  1. What happened and why it matters to the board (one paragraph, no technical detail beyond what a director needs).
  2. What the investigation says about the management system: three to five governance-relevant learnings (assurance that did not detect, signals that did not escalate, risk accepted without authority, resources).
  3. Questions for directors to ask management: eight to twelve, in the board question format (question, why it matters, what good evidence looks like). Mix: this site, all sites, assurance quality.
  4. Assurance the board should request: what independent verification, at which sites, by when (as a request to management, not a plan).
  5. Indicators for the board dashboard: three to five leading indicators that would have shown deterioration earlier.

Output

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

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

Sections → kinds: 1 and 2 para · 3 question ×8–12 (question, why, good_evidence, to the role asked) · 4 table (verification, sites, by when; row_cites) · 5 indicator ×3–5. Set "scope": {"levels": [3, 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.

{"kind": "question", "question": "How do we know critical spares meet their specification at every site?",
 "why": "…", "good_evidence": "…", "to": "Chief Executive", "cites": ["FND-…"]}

Neutral, factual tone; no blame of management or staff; roles only. Any owner is the function that owns the change, not who "was involved" (learning-principles.md).

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.