Competency ModelSAFE
Overview
An agent skill published by revfactory.
459e1bb8f76eOBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: competency-model description: "competency model design framework. jd-writer and screening-expert agent jobby core competency definitionand assessment standard establishto do when reference. 'competency model', 'job competency', 'skill matrix' request when usage. However, personcompany assessment whensystem building grade total design scope outside." --- # Competency Model — competency model design jd-writer / screening-expert agent competency based hiring design competency . ## competency model structure ### 3total competency framework | total | description | examplewhen | |------|------|------| | core competency (Core) | beforecompany | client during, , | | leadership competency | managementspecialist or more | vision present, , decision-making | | job competency (Functional) | job | , data analysis, specialistperson | ### competency level (Proficiency Level) | level | people | description | quality grade | |------|------|------|----------| | L1 | basis | perform, basic | /person | | L2 | execution | perform, tablelevel work | week | | L3 | | situation response, degree also possible | when | | L4 | specialist | level impact, | / | | L5 | | total level specialistnature, strategy | + | ### competency template ```markdown ## competency: [competencypeople] ### definition [Korean sentence definition] ### action indicator (Behavioral Indicator) **L1 (basis)** - [ possibleKorean action 1] - [ possibleKorean action 2] **L2 (execution)** - [ possibleKorean action 1] - [ possibleKorean action 2] **L3 ** - [ possibleKorean action 1] - [ possibleKorean action 2] ### assessment method - interview question: [structure question] - task: [actualbasis task] - reference: [confirm point] ``` ## jobby competency mapping examplewhen ### degree | competency | week(L2) | when(L3) | (L4) | |------|----------|----------|---------| | capability | ★★★ required | ★★★ required | ★★★ required | | whensystem design | ★ basis | ★★★ required | ★★★ required | | code review | ★ number | ★★★ | ★★★ | | | - | ★★ preferred | ★★★ required | | technical strategy | - | ★ | ★★★ week also | ## JD writing competency annualtotal ### STAR based qualification requirement ```markdown ## qualification requirement ### required (Must-have) - [competency 1] L3 or more: [specific /performance standard] example: "versusscale (DAU 100+) whensystem operations 2year or more" - [competency 2] L2 or more: [specific standard] ### preferred (Nice-to-have) - [competency 3]: [specific standard] - [competency 4]: [specific standard] ### minute (action technical) - [competency 1 L3 action indicator specialistannual technical] - [competency 2 L3 action indicator specialistannual technical] ``` ## screening matrix | assessment item | point | PASS standard | confirm method | |----------|------|----------|----------| | required competency A | 30 | 21point+ | capabilityfrom + task | | required competency B | 25 | 18point+ | capabilityfrom + interview | | preferred competency C | 15 | - | capabilityfrom | | document qualitynature | 15 | 10point+ | interview | | nature re-capability | 15 | 10point+ | interview | | **total** | **100** | **70point+** | | ## quality checklist | item | standard | |------|------| | competency number | job 5~8items | | level | L1~L5 action indicator specific | | required/preferred | required 3~4items, preferred 2~3items | | assessment method | competencyby 1items or more | | degree | natureby/annual duringquality tablecurrent |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
459e1bb8f76efull audit observations/trust-audit/skill/revfactory__competency-model.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 459e1bb8f76e | SAFE | B | 89 | first audit |
Questions
Is Competency Model safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Competency Model access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (459e1bb8f76e), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.