agentleFS
ashley-eyekyamashley-eyekyam/probematrix-learnings-coach/skills/supply-chain-contractor-learnings/SKILL.md

supply-chain-contractor-learnings

Skill0 starsChanged 29 days agoMITView on GitHub

Produce learning for procurement, stores, materials management, vendors, OEMs and contractors from a ProbeMatrix investigation export - part specifications and substitutions, local sourcing without quality control, OEM support for ageing equipment, vendor documents, contractor work control and agency or outsourced roles. Use when someone asks what procurement, stores, the supply chain, vendors, OEMs or contractors should learn, or wants a supplier or contractor briefing, spares policy input, or contractor-management lessons after an incident.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Contractors and outsourced roles: if findings involve contractor or agency staff (e.g.

    line 25
  2. Very specific:

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

    line 30
  3. Very specific:

    If the export has few supply-chain findings, say so in a para and keep the pack short.

    line 51

≈ “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

Supply Chain & Contractor Learnings

Audience: the Learning Clusters tagged supply or contractor (in the default taxonomy F06 materials management, F16 vendors, OEMs and suppliers, F17 contractors), plus any agency roles named in the findings.

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> --tag supply contractor --brief
PMLC select <ws> --text "procure|stores|spare|OEM|vendor|supplier|local|substitut|contract|agency|outsourc" --brief

Write

  1. How the part (or service) reached the job: the path from need to installed item, with each decision point and who took it (roles), from the evidence. Mark points with no record.
  2. Learnings for procurement and stores: specification, technical approval of substitutes, quality checks at receipt, storage and shelf-life, traceability.
  3. Learnings for engineering and maintenance at the supply interface: who may approve a substitute, and how it is recorded (link to interface-learnings).
  4. Learnings for vendors and OEMs: documents and support for legacy equipment; what to ask vendors for.
  5. Contractors and outsourced roles: if findings involve contractor or agency staff (e.g. security, fire, inspection agencies), what reporting lines, competence and supervision the findings question.
  6. Recommendations and indicators: e.g. "% of critical spares with an approved specification", "substitutions approved through change control".

Output

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

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

Sections → kinds:

  1. A timeline with one event per decision point: received_by = the role that took the decision, and response = "No record" where there is none.
  2. learning items with group = Procurement and stores / Engineering at the supply interface / Vendors and OEMs / Contractors and outsourced roles (only the groups the evidence supports).
  3. recommendation (change, hoc_tier, indicator).

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

{"kind": "timeline", "events": [{"date": "YYYY-MM", "text": "…", "received_by": "Stores/procurement officer",
 "response": "No technical approval recorded", "cites": ["FND-…"]}]}

Contractor just-culture rule. The host organisation's system owns contractor and vendor learnings: its selection, briefing, supervision and interfaces. Write "the contractor's task was not covered by the host's permit briefing", not "the contractor failed". When the pack is shared outside the organisation, use no company names: write the function ("the maintenance contractor"); check-language --share external flags organisation names (JC9).

If the export has few supply-chain findings, say so in a para and keep the pack short.

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.