sop-enrich
Skill0 starsChanged 37 days agoNo licenceView on GitHub
Enrich/validate an EXISTING Petermann SOP (PC-NNN) against the canonical SOP schema in the GBG Company OS — fill honest gaps, flag missing required fields, recompute the Missing Info Gaps readiness doc. Use WHENEVER Kyle or Andrew says 'enrich this SOP', 'validate PC-003', 'what's missing on this SOP', 'check the SOP register against Fibery', 'sop-enrich', 'recompute the SOP gaps', 'is this SOP ready for approval', or points at an SOP Library entry / register row that needs its metadata completed or audited. Reads the SOP from BOTH surfaces (Fibery SOP Library + vault sop-register.md), drafts CONTENT gaps automatically (Summary, Missing Info Gaps recompute, body normalization), but for COMMITMENT gaps (steward/Owner, risk_tier, approval authority, status) asks a bounded question rather than inventing — leaves them honestly blank if unanswered. Every body edit is version-first: MINOR bump + Version History row, never a silent overwrite. NEVER flips Status (Needs Review→Approved is the human validation gate per OS-001), never sets Approved By/Approval Date, never renumbers a sop_id, never writes SOP process content (steps/policies). MVP is Petermann-ONLY: refuses any SOP whose entity isn't exactly Petermann (RU-/DL-/OS-/OPS- or multi-entity → read-only gap report, zero writes). NOT for creating a new SOP (humans author SOPs per OS-001), NOT for Tasks/Projects/Initiatives in Triage (use triage-enrich), NOT for approving/validating an SOP's actual process steps.
In this repository8 other files it gives its agents.
- feedback-intakeSkill
- initiative-intakeSkill
- linear-issue-intakeSkill
- linear-project-intakeSkill
- model-advisorSkill
- project-intakeSkill
- task-intakeSkill
- triage-enrichSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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
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.

