agentleFS
ashley-eyekyamashley-eyekyam/probematrix-learnings-coach/skills/safety-committee-guide/SKILL.md

safety-committee-guide

Skill0 starsChanged 29 days agoMITView on GitHub

Produce a discussion guide from a ProbeMatrix investigation export for joint health and safety committees, workforce safety representatives and union safety reps - a plain-language account, the questions the workforce should raise with management, what to look for on site, and how to keep the discussion about systems rather than blame. Use when someone asks for safety committee material, a worker consultation pack, a guide for safety reps, a workforce engagement session or a town-hall discussion on an investigation.

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/safety-committee-guide.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

Safety Committee Guide

Audience: workforce representatives and joint safety committees. They give the workforce a voice, raise concerns and check that learning reaches the people who do the work. They need a fair account and good questions.

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 profile <ws>
PMLC select <ws> --tier T1 T2 --brief
PMLC select <ws> --level 4 --top-rated --brief
PMLC select <ws> --relation norm_setter learner challenger --brief

Write

  1. What happened, in a page, in plain language, roles only.
  2. What the investigation says about the system: the five learnings most relevant to the workforce, with a clear statement that the analysis places most causes at supervision and organisational level when the profile shows that.
  3. Questions to raise with management: ten, about staffing, training, procedures, equipment, authority to stop work, and how concerns are handled.
  4. What to look for on site: a walk-round prompt list drawn from the conditions in the findings.
  5. Running the discussion: a 60-minute agenda, ground rules (no names, no blame, focus on conditions), and how to record and send concerns to management.
    • Anonymity and confidentiality. Offer an anonymous route for concerns. Record concerns by topic, not by who raised them. Do not name or describe a person so that the crew can tell who it is (a small crew's single operator is identifiable by role alone). Minutes and the concern log go to management without names.
  6. Follow-up: what the committee should ask to see at 30, 60 and 90 days.

Output

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

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

Sections → kinds:

  1. para.
  2. learning ×5, plus a para on where the analysis places the causes.
  3. question ×10, with to = the management role.
  4. check items.
  5. A para with the ground rules, then a table agenda with columns Minutes and Item.
  6. check items, with when = "30 days", "60 days" or "90 days".

Set "scope": {"tiers": ["T1", "T2"]}. Put data-quality corrections in data_quality, findings left out on purpose in exclusions, and same-condition findings in supporting_cites.

{"kind": "question", "question": "Who may stop a restart when the test record is missing?", "why": "…",
 "to": "Maintenance manager", "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.